Received: 17 November 2025; Revised: 29 December 2025; Accepted: 29 December 2025; Published Online: 30 December 2025.

J. Collect. Sci. Sustain., 2025, 1(3), 25412 | Volume 1 Issue 3 (December 2025) | DOI: https://doi.org/10.64189/css.25412

This article is licensed under Creative Commons Attribution NonCommercial 4.0 International (CC-BY-NC 4.0)

A Comprehensive Review of Smart and Sustainable Waste

Management Using Artificial Intelligence, Internet of

Things, and Robotics

Sneha R. Shegar,

Umesh Dattatray Gosavi, Arpita Ramdas Lende and Trupti Vijay Walunj

Department of Computer Engineering, Samarth College of Engineering & Management, Pune, Maharashtra, 412410, India

*Email: snehashegar1@gmail.com (S. R. Shegar)

Abstract

Urbanization and population growth have made waste management more challenging in urban areas such as parks,

streets, and public transport. Traditional waste collection requires significant manual labor and is inefficient,

expensive, and poses health hazards to sanitation workers. Recent advances in robots, Artificial Intelligence (AI), and

the Internet of Things (IoT) have enabled autonomous and intelligent waste management systems that can detect,

collect, and separate waste. This paper reviews intelligent robotic solutions for automated waste collection and

separation. Key subsystems are discussed, including perception, navigation, manipulation, sorting, and IoT for waste

management data generation. Sensor technologies such as ultrasonic, inductive, and moisture sensors, along with

machine vision and deep learning algorithms for waste classification, are examined. Communication architectures

using Global System for Mobile Communications (GSM), Global Positioning System (GPS), and mobile applications for

real-time tracking and operation are also discussed. Existing automated systems are reviewed, and despite significant

progress, long-term challenges remain related to energy efficiency, outdoor operation, and large-scale deployment.

The review further identifies critical research gaps in system-level integration, autonomy, and scalability, and

highlights future directions toward unified AI–IoT–robotic frameworks, energy-aware designs, and adaptive

navigation strategies for sustainable and smart urban waste management.

Keywords: Autonomous waste management; Intelligent robots; Internet of Things (IoT); Artificial intelligence (AI); Waste

segregation.

1. Introduction

The management and disposal of solid waste represent both environmental and operational challenges in contemporary

urban environments.

[1-3]

Changes associated with rapid industrialization, urbanization, and increased population sizes

have led to unprecedented amounts of solid waste generated daily in public space.

[4,5]

Many of the activities that happen

in parks, bus stations, railway stations, campuses, marketplaces, and many other usual public spaces generate extra

solid waste, litter, and debris beyond what is already common. Current waste collection and disposal methodologies

remain largely labor-intensive and are typically governed by fixed or irregular cleaning schedules; such approaches

are often suboptimal and inconsistently executed, resulting in inefficient resource utilization.

[6,7]

As the organic and

inorganic waste heaps and volumes grow, a traditional approach to cleaning is not successful and cannot keep up with

the need for cleansing.

[8]

Waste collection often becomes necessary only after bins overflow and litter spreads into

surrounding areas. Such unmanaged solid waste is aesthetically displeasing and poses serious ecological and public

health risks, including the spread of infectious diseases, blocked drainage systems, and contamination of soil and water

resources.

[9-11]

Therefore, the current crisis around solid waste management and disposal must shift more toward

automation where we rely less on human participation, yet are more efficient and sustainable.

[12,13]

The rapid advancements in robotics, automation, artificial intelligence (AI), and the Internet of Things (IoT) have

made the development of a new form of useful intelligent systems that can perform complicated tasks autonomously.

[14-

18]

Autonomous robots that can perceptually sense their environment, make informed decisions, and then act on those

decisions, are being increasingly used in various industries and markets, including manufacturing, logistics, healthcare,

and agriculture.

[19,20]

The use of robots with autonomous technology in waste management is relatively new but swiftly

advancing.

[21]

Autonomous waste-collecting robots have multiple sensors, embedded processors, and AI-based

autonomous decision-making capabilities, which allow them to detect, collect, classify, and process waste materials

more efficiently than humans.

[22,23]

Autonomous waste-collecting robots are particularly well suited for public spaces

characterized by high and unpredictable waste generation, where continuous cleanliness is essential and manual

cleaning may lead to inefficiencies or disruptions. Their deployment enables uninterrupted waste management

operations, thereby maintaining hygienic conditions and improving overall environmental quality. An autonomous

waste-collecting robot is a developing area of intelligent robotic waste management as it relates to fuzzy robotic

perception, incorporated IoT networks, and all aspects of autonomous waste collection and segregation.

[24]

Despite widespread implementation, existing waste management systems exhibit numerous operational and structural

limitations. Manually collecting waste is laborious, inefficient, and oftentimes unsafe.

[25]

Waste collectors are often

exposed to dangerous materials, sharp objects, and pathogens with no protective gear, leading to significant hazards to

health.

[26-29]

In addition, manual classification of waste is rarely effective at the collection point, resulting in recycling

waste mixed in with non-recycling waste, which undermines recycling efforts and increases overall landfill volume.

Furthermore, irregular schedules and lack of monitoring systems exacerbate the problems associated with waste

control. All of these factors can serve as barriers to realizing an automated solution that can efficiently collect waste,

actively monitor disposal practices in real time, and classify waste intelligently without the assistance of humans.

The incorporation of AI and IoT into waste management has numerous benefits and paradigm shifts.

[30-32]

AI machines

have perceptive and learning capabilities, so AI machines make predictions, detect, classify, and distinguish objects of

waste using computer vision, sensor fusion, and pattern learning algorithms.

[33]

IoT provides connectivity that enables

bi-directional communication between robots, operators, control centers, and mobile devices to monitor, track, and

ascertain decisions in real-time, thus, ensuring maximum efficiency.

[34,35]

Waste management robots can detect and

learn about the objects comprising waste using ultrasonic sensors, inductive proximity sensors, moisture sensors, and

RGB cameras, allow the robot to distinguish between waste such as whether it is dry, wet or metallic and make accurate

real-time sorting.

[18,36]

Adding GPS and GSM modules can further improve operational efficiency and effectiveness as

it provides tracking of the location tracking and updates the robot status live and alerts for abnormalities such as fault,

full bin or low battery.

[37]

The emergence of these technologies and their use in waste management could upend

traditional processes to more innovative, coordinated, and sustainable approaches.

Fig. 1: IoT based solid waste handling system. Reproduced from [37].

In the last few years, various researchers and developers have attempted different robotic systems to collect and sort

waste. These robots function with a combination of data from sensors and AI-based decision models that allow them

to detect and pick up waste.

[38]

Early systems primarily designed for mobile waste collection in urban streets include

DustCart developed in Europe,

[39]

which relied primarily on human–robot interaction. Later systems started to include

IoT-based modules to allow for remote monitoring and report on the status of the robot. More recently, systems have

utilized computer vision, powered by AI, to improve sample identification of waste and refuse. For instance,

convolutional neural networks (CNNs) and object detection models such as YOLO and MobileNet, may be used to

classify waste materials directly from an image from the onboard camera of the robot.

[40]

These systems are a notable

improvement because they make the detection of waste significantly more accurate, and allow a robot to handle

different types of waste in different environments, both with and without the assistance of a human operator. However,

despite numerous advances in technologies, most existing robotic waste collection solutions still do not possess full

autonomy. Many robotic waste collection solutions still hybrid forms, relying on operators to direct the solution,

predefined route paths, and limited ability to adapt to working environments; therefore, these solutions cannot easily

be implemented in public engaged spaces.

Although significant progress has been made in robotic and IoT-enabled waste management, several challenges still

hinder the large-scale deployment of fully autonomous waste collection robots.

[41]

Power management remains a major

limitation, particularly in achieving energy-efficient operation and integrating renewable energy sources such as solar

charging. Terrain adaptability is another challenge, as most robots are optimized for flat surfaces, whereas real-world

environments include slopes, curbs, and wet conditions. In addition, maintenance requirements, system durability, and

deployment costs affect scalability and return on investment. Ongoing research in lightweight materials, efficient motor

control, and artificial intelligence is expected to progressively address these challenges. This review examines the

technological foundations, current deployments, and research trends in robotic waste management, with a focus on

perception, navigation, sorting, and communication systems. It also highlights existing research gaps and outlines

future research directions toward sustainable urban sanitation.

Fig. 2: Conceptual architecture of an intelligent waste management system incorporating AI-based decision making, IoT

sensing, and robotic sorting mechanisms.

2. Literature survey

2.1 Review & taxonomy studies

Maghsoudi et al.

[42]

retrieved 9,095 articles on waste management published since 2000 from the Web of Science (WoS)

database. Based on these articles, a keyword network comprising 17,808 unique keywords (nodes) and 79,763 links

was constructed. To identify the major research areas in waste management, a community detection technique was

applied to the keyword network, resulting in the identification of ten main communities. These communities, named

according to waste management characteristics and waste types, collectively represent more than 90% of the overall

waste management research. Nižetić et al.

[42]

provide a collection of publications concerning innovative technology

towards dealing with the challenges of a modern city, focusing primarily on innovations in waste management. The

authors do this through a non-systematic review using relevant conference papers on sustainability and efficiency of

resource utilization. The paper discusses the key connections between waste management systems (WMS), recycling

and circular economy, as well as plastic pollution. However, research is limited in its extensive or systematic review

and lacks consistent criteria for selecting studies in addition to no formal structure meta-review can be established in

the future. Rodríguez-Guerreiro et al.

[43]

conducted a Scopus-based literature review on waste management in higher

education institutions, analyzing 293 publications across waste generation and composition, composting, food waste,

and edible food waste. The results show a strong increase in research after 2017, with composting receiving the greatest

attention, alongside studies on zero-waste and waste minimization strategies. Hariyani et al.

[44]

adopted a systematic

review methodology in accordance with the PRISMA guidelines, encompassing the stages of identification, screening,

eligibility, and inclusion. Relevant studies were retrieved from the Scopus database using keyword combinations

related to waste management and treatment technologies within titles, abstracts, and keywords. Following the removal

of duplicates, non-English, and inaccessible records, successive screening and full-text evaluation resulted in a final

dataset of 392 articles published between 2000 and 2025, which were subjected to in-depth analysis. Dawal et al.

[45]

reviewed 69 studies published between 2018 and 2024 using the PRISMA methodology to examine the application of

artificial intelligence, particularly machine learning and deep learning techniques, in municipal solid waste

management. The review highlights the potential of AI to improve decision-making, resource recovery, and circular

economy practices, while also identifying challenges related to data availability, quality, and interdisciplinary

integration in achieving sustainable urban waste management aligned with the UN SDGs. Pardini et al.

[46]

provide a

complete review of research on IoT architecture and communication protocols in waste management systems. This

study examined a series of research papers concerning IoT framework systems for monitoring smart bins and urban

waste. In conclusion, the authors examined how while technological solutions are improving, few IoT systems really

add any extra capability for citizen engagement (which is extremely important to waste collection time and costs). The

gap in the literature is that no design was centered around the human aspect to engage the community. Anuardo et al.

[47]

employed a combined research methodology integrating literature review and content analysis to examine waste

management research. The literature review facilitated the identification of research gaps, while content analysis

enabled the detection of publication trends, thereby supporting the qualitative development of policies, initiatives, and

a conceptual framework for advancing waste management research. Sahu et al.

[48]

reviewed 15 studies examining the

application of emerging industrial technologies for waste sorting in urban systems in India. Using content analysis of

scientific articles and technical reports, the authors identified several significant technological innovations in waste

sorting practices. However, the study was geographically limited to Indian metropolitan areas, which the authors

acknowledged as a key limitation, restricting cross-country comparison and broader generalization of findings. Akram

et al.

[49]

provided a review of ICT applications in waste management with a focus on communication protocols and

energy-efficient IoT deployments. The authors highlighted the significance of selecting the appropriate wireless

communication technology in order to optimize the operational life of smart bins, while also recognizing blockchain

as a significant enabler of integrating various stakeholders in a waste-management network. Despite these

contributions, it still seems that there is a gap in the research about how well these ICT have been integrated in practice

from a real-world implementation perspective. Rajeb et al.

[50]

conducted a taxonomy-driven review of Internet of

Things (IoT) applications in smart cities by retrieving peer-reviewed journal articles from the Scopus database, selected

for its extensive coverage and reliable indexing of high-impact international publishers. To maintain methodological

rigor and ensure the quality of the synthesized evidence, the study deliberately limited its scope to journal articles,

notwithstanding ongoing debates in meta-analysis literature regarding publication type selection, as this strategy was

considered most appropriate for developing a robust and comprehensive taxonomy of IoT-based smart city research.

Ramirez et al.

[51]

included a section related to innovative waste systems in their review of articles related to IoT in

smart cities. They conducted a review of 22 articles related to the emergence of IoT for smart bins. This review

provided a broad overview of IoT in the smart city ecosystem, but did not provide much technical detail related to

innovative waste systems. The gap in research was that there are no technical specifications for in depth comparisons

to facilitate use in practice Concari et al.

[52]

provided a bibliometric and text-mining analysis of 2061 publications

assessing citizen recycling behaviors. They employed data mining software to identify emerging trends and thematic

associations, and concluded that local city innovative policies were a major influence on citizen recycling behaviors.

The research gap noted in the study was the lack of connections between behavioral evidence and practical areas of

technology in innovative waste systems. D'Amico et al.

[53]

provides a review that looks at the digitalization of resource

loops in smart cities, focusing specifically on "urban metabolism circularity." The authors reviewed ICT-based tools

that digitalize the circulation of materials from consumption to waste and provided case studies for illustration. The

authors found that ICT can be helpful in hastening the adoption of circular economy practices, although the authors

mentioned a lack of empirical evidence to support their assertions. The gap in the study is a (very) limited number of

operational examples that have shown any measurable environmental impact, specifically referencing the need for

operational implementations to verify the outcomes of the urban metabolism framework. Zoumpoulis et al.

[54]

presented a comprehensive review of waste collection bins with smart capabilities, highlighting their critical role in

modern urban environments and sustainable waste management systems. The study systematically analyzed 79

selected articles from an initial pool of more than 1,400 publications, focusing on state-of-the-art smart bin

technologies and advanced functionalities such as automated material separation and integrated control mechanisms.

Although a broadly accepted definition of smart bins exists—characterizing them as waste containers equipped with

features such as fill-level monitoring and IoT connectivity—the review identified substantial gaps in the existing

literature. In particular, limitations were observed in material separation practices, including automated waste

segregation, as well as in the maturity and consistency of conceptual frameworks, which collectively hinder efficient

resource recovery and the realization of circular economy models. Furthermore, the analysis revealed a lack of

standardization and uniformity in automation approaches, with existing studies proposing diverse solutions that exhibit

varying strengths and limitations. The absence of a unified and scalable framework underscores the need for

consolidated design principles to advance smart bin technologies and address sustainability challenges in future smart

city deployments.

2.2 IoT architectures & smart-bin designs

Idwan et al.

[55]

proposed a waste management system based on IoT technology to enhance the scheduling and routing

of waste collection vehicles within a metropolitan area. The study implemented a two-phase metaheuristic approach

that utilized a Genetic Algorithm (GA) to reduce collection distance and the number of trucks. The study conducted

two trials, an IoT trial and a conventional trial, using real geographical data collected from Islamabad Pakistan. The

results showed that the IoT-based system exhibited a considerably lower total travel distance and total travel time.

However, there is still a gap in existing research regarding extending the system to multi-vehicle and multi-objective

optimization, as well as testing robustness in larger datasets. Antora et al.

[56]

reported an IoT-enabled smart waste

management system that employs sensor data and image-based machine learning algorithms to classify and segregate

waste into multiple compartments, while enabling real-time monitoring through cloud connectivity. Juwariyah et al.

[57]

reported the design of an integrated monitoring system for multiple IoT-based smart bins in the context of waste

management under the Industrial Revolution 4.0 paradigm. The proposed system utilized a Wemos D1 Mini Pro

microcontroller in conjunction with an HC-SR04 ultrasonic sensor and a DHT22 temperature–humidity sensor to

monitor waste fill levels and environmental conditions. An integrated real-time monitoring platform was developed

using the Blynk application and Arduino IDE, enabling visualization of garbage height, temperature, and humidity

data on smartphones through virtual indicators and graphical displays. Experimental evaluation was conducted using

two smart bin units, demonstrating the feasibility of centralized real-time waste monitoring. Pebriad et al.

[58]

reported

the design and development of an IoT-based Smart Waste Bin aimed at automated waste monitoring and management.

The proposed system employed barcode sensors for waste type identification, an ESP32 microcontroller as the primary

control unit, and an IoT cloud platform for real-time data visualization via a web-based dashboard. The study followed

an engineering approach based on the waterfall model, encompassing requirement analysis, system design,

implementation, and testing phases. Experimental results demonstrated a waste detection accuracy of 95% and an

average data transmission delay of less than three seconds, indicating improved efficiency and responsiveness in waste

management. The findings support the feasibility of smart, environmentally sustainable waste management systems.

Abba et al.

[59]

presented an IoT-based smart garbage monitoring system employing an Arduino Uno microcontroller,

ultrasonic sensors, and Wi-Fi communication to detect and classify bin fill levels as empty, half-filled, or filled. The

system periodically displays bin status on an LCD and transmits real-time data to a centralized web server for graphical

visualization. The prototype was developed using Arduino IDE with embedded C, while server-side data processing

was implemented using PHP and simulated in Proteus 8.0. Experimental evaluations confirmed the system’s

effectiveness under real-world conditions, demonstrating its potential to support automated waste monitoring and

smart city waste management.Jun-Ho Huh et al.

[60]

reported the limitations of the standard trash bag–based waste

disposal system implemented in the Republic of Korea since 1995, particularly highlighting persistent issues of illegal

dumping by households and businesses attempting to avoid disposal costs. Efforts by the Seoul Metropolitan

Government to mitigate the problem by removing street trash bins proved ineffective, as illegal dumping continued to

cause environmental, hygienic, and odor-related concerns. To address these challenges while reducing manpower and

maintenance costs, the authors proposed an IoT-based smart trash separation bin model. The study presented three

alternative system designs incorporating sensor-based detection, image processing, and spectroscope technologies,

demonstrating the potential of IoT-enabled solutions to reduce labor requirements and administrative costs in urban

waste management. Khan et al.

[61]

proposed a novel IoT-enabled, knapsack-based optimization framework for waste

collection that leverages sensor data on waste quantity and toxicity to optimally load collection trucks while prioritizing

high-toxicity waste. The model was implemented and evaluated using MATLAB simulations, where it outperformed

conventional waste collection strategies. Experimental results demonstrated an improvement of up to 47% in high-

priority toxic waste collection and a reduction in the number of collection trips, leading to equipment cost recovery

within one year Lu et al.

[62]

introduces an ICT-based novel waste collection system that uses a hybrid bi-objective

metaheuristic based OEGA, mixing a Whale Optimization Algorithm and Genetic Algorithm for balancing total cost

and workload across multiple disposal centers. The proposed method was tested using real data from the Pudong

community in Shanghai and the resulting multi-objective compound had better multi-objective optimization ability

compared to the NSGA-II and MOEA/D. However, there was no implementation of a real-life case to substantiate the

findings of this study. This demonstrates a gap in future research examining operational feasibility and cost of

maintenance for the proposed waste collection system models. Aleyadeh et al.

[63]

proposed an IoT-based architecture

that addresses two key components of smart waste management. The first component focuses on monitoring the waste

volume and composition within bins, as well as environmental conditions in their surrounding areas. The second

component enables dynamic scheduling and optimized routing of waste collection vehicles based on real-time data

transmitted from the bins. The proposed smart bin design is capable of detecting obstacles and identifying illegal

dumping activities in the vicinity. Furthermore, the routing protocol computes optimal collection paths for servicing

filled bins in high-density residential areas while minimizing travel distance. The integration of these components

enhances overall waste collection efficiency and contributes to a reduction in operational costs and carbon footprint.

3. AI/ML for prediction, classification & decision support

Namoun et al.

[64]

offers a thorough overview of machine learning (ML) applications in solid waste management for

smart cities, specifically through optimizing waste flows organization. The authors reviewed 23 articles, which used

artificial neural networks (ANNs) for predicting waste generation and waste disposal behaviors. The comparative

approach, reviewing ML models and algorithms for waste forecasting was the method. Overall, the study results

conclude that ANNs provide the most viable modelling processes for predicting trends in waste generation, due to its

applicability to nonlinear patterns. Namoun et al. noted limited standardized and recently curated datasets for waste,

as well as a lack of benchmark case studies, therefore highlighting a gap in research to support the development of

robust and transferable models to explore datasets for comparisons. Alsabt et al.

[65]

explored the application of artificial

intelligence (AI) and machine learning (ML) techniques to optimize waste management strategies with an emphasis

on economic efficiency and environmental sustainability. Using the World Bank’s comprehensive waste management

dataset, the study conducted extensive data preprocessing, including cleaning and feature selection, to improve model

performance. Several ML models, such as regression techniques, Support Vector Machines (SVM), Random Forest

(RF), and Extreme Gradient Boosting (XGBoost), were employed to forecast waste generation trends and evaluate

waste management alternatives. Additionally, optimization methods, including linear programming, were used to

enhance resource allocation and operational efficiency. The proposed framework achieved an accuracy of 85 % in

waste generation prediction, attributed to the incorporation of diverse socio-economic variables. Moreover, the

optimization model resulted in a 15 % improvement in operational efficiency, demonstrating the potential of ML-

driven approaches for sustainable and cost-effective waste management. Ali et al.

[66]

introduced an optimization

framework that integrates machine learning and regression to improve economic and environmental performance in

waste management systems. Synthetic datasets simulating the performance of different waste materials, and conversion

technologies as configured and practiced in Malaysia were created to develop linear regression, multilayer perceptron

(MLP), and sequential minimal optimization regression models. The authors identified the MLP as having the strongest

correlation coefficient (0.7169), which was useful to predict the outputs of waste conversion. However, the authors did

not validate the models against real-world, municipal waste data or analyze their generalizability, representing a

notable research gap in using and testing this method in changing urban waste management processes.

Huang et al.

[67]

conducted a systematic review on the application of machine learning (ML) in the aerobic composting

of organic solid waste (OSW). Although aerobic composting is widely used for producing organic fertilizers, its

complex non-linear biochemical reactions and heterogeneous material properties limit accurate process simulation and

optimization. The review examined ML-based approaches for predicting and controlling compost maturity,

environmental pollutants, nutrients, moisture, heat loss, and microbial activity. The results showed that ML

applications primarily focus on compost maturity and pollutant prediction, with artificial neural networks (47%) and

genetic algorithms (10%) being the most commonly used techniques. Moreover, deep neural networks and ensemble

learning models demonstrated enhanced predictive performance and effective feature selection, contributing to

improved efficiency in organic waste composting. Boudanga et al.

[68]

offer an explainable artificial intelligence (XAI)

framework for medical waste management. The framework consists of IoT sensors, GPS-enabled vehicles, and data

analysis via AI model application, such as Decision Trees and Random Forests (RF) models to predict the fill level of

medical waste and make routing decisions. The authors used experimental analysis of operational efficiency and

resource optimization and collected data in real-world environments in Casablanca, Morocco. XAI enhanced

interpretation of findings, but the researchers did not benchmark the frameworks performance with comparative model

findings in existing literature. The research gap is in benchmarks for performance on explainable AI in medical waste

management logistics with real-time expandability testing. Gupta et al.

[69]

reviewed a wide range of data-driven

modeling techniques for organic waste treatment technologies, highlighting their potential contribution toward

achieving net-zero targets. The study discussed advanced machine learning (ML) methods, including neural networks

(NN), physics-informed neural networks (PINN), support vector machines (SVM), decision trees (DT), random forests

(RF), XGBoost, k-nearest neighbors (KNN), and Gaussian process regression (GPR), applied to the modeling,

optimization, and control of both high- and low-temperature waste treatment processes. Emphasis was placed on model

explainability techniques to interpret black-box ML models and enhance transparency. The integration of ML with

physical governing laws through PINNs was identified as a promising approach to improving model reliability and

robustness. Additionally, the study highlighted the importance of combining ML models with control algorithms,

heuristic optimization methods, life cycle assessment frameworks, and natural language processing techniques to

support holistic and circular organic waste management strategies

Fig. 3: Overview of thermochemical and biochemical organic waste treatment technologies. Reproduced from [69].

3. Circular Economy, Policy, Citizen Engagement & Systems Integration

The circular economy (CE) is currently an integral part of sustainability. Bandh et al.

[70]

examined the interrelationship

between waste management and the circular economy as complementary frameworks for achieving environmental

sustainability. The study emphasized that effective waste management-through recycling, reuse, and proper disposal-

plays a critical role in minimizing environmental risks and reducing waste generation. Within a circular economy,

principles such as designing out waste and pollution, maintaining materials in continuous use, and regenerating natural

systems enable the development of closed-loop systems that convert waste into valuable resources. The authors

highlighted the importance of the three core principles of the circular economy-reduce, reuse, and recycle-in lowering

environmental impact, conserving resources, and supporting eco-friendly industries. Overall, the study underscored

that integrating waste management practices within circular economy models can promote sustainable development

while delivering environmental, economic, and social benefits. Mridu Kulwant et al.

[71]

examined the role of waste

management within the framework of a circular economy, contrasting it with the traditional linear “take–make–

dispose” economic model and its associated environmental challenges. The chapter highlighted the growing shift

toward circular economy principles that emphasize resource efficiency, waste reduction, and sustainable consumption

patterns. Key strategies and principles were discussed, focusing on waste minimization and value creation through

sustainable practices. The authors also reviewed innovative technologies and approaches that are transforming waste

management systems and facilitating the transition to circular models. Through real-world examples and case studies,

the chapter demonstrated how circular economy adoption can reduce environmental impacts and support the

development of a sustainable and resilient future. Rashmi Paliwal et al.

[72]

discussed the escalating pressure on natural

resources caused by industrialization and population growth, which has resulted in increased waste generation and

environmental contamination. The study contrasted natural ecosystem cycling, where waste does not exist, with

anthropogenic linear economic models that introduce waste through “take–make–dispose” practices. Highlighting

World Bank projections of a nearly 70 % increase in global waste generation by 2050 if unmanaged, the authors

emphasized the urgency of adopting alternative models. The chapter positioned the circular economy as a

transformative approach for sustainable production and consumption, enabling recycling and the creation of “wealth

from waste” through strategies such as the 3R principles, eco-design, and energy-efficient products. Additionally, it

examined the challenges associated with multiple material cycles and downcycling, offering insights into achieving a

zero-waste economy. Salman Shooshtarian et al.

[73]

examined the role of circular economy (CE) principles in improving

construction and demolition (C&D) waste management within the built environment sector. The chapter emphasized

that enforcement, alongside encouragement and education, plays a critical role in advancing resource circularity

through effective policy interventions. Eight key policy measures-such as landfill taxation, penalties for illegal

dumping, extended producer responsibility, sustainable procurement, and recycled product certification-were analyzed

for their impact on waste recovery and resource efficiency. Using Australia as a case study, the authors combined

literature and policy analysis with stakeholder surveys and interviews conducted between 2018 and 2021. The findings

provide both conceptual and practical insights to support the development of evidence-based waste management

policies aimed at enhancing circularity in the built environment. Josephine Treacy et al.

[74]

examined the role of waste

management policy and stakeholder engagement in achieving the United Nations Sustainable Development Goals

(SDGs). The chapter emphasized that effective policy implementation, supported by strong engagement across civil

society and institutional stakeholders, is essential for embedding the SDGs into national and regional strategies.

Focusing on solid and liquid waste management, the study analyzed challenges related to water quality, sanitation, air

quality, and soil degradation arising from weak policy execution and limited stakeholder involvement. From a

European perspective, with particular emphasis on Ireland, the authors identified best practices, implementation gaps,

and consequences of ineffective waste management policies. The chapter highlighted SDG 17 as a critical enabler,

underscoring the importance of integrated bottom-up and top-down communication approaches for achieving

sustainable waste management and public health outcomes. Hashim Zameer et al.

[75]

explored the role of environmental

economics in shaping effective waste management policies by examining the social costs associated with waste

generation, including pollution, health risks, and resource scarcity. Using a content analysis approach, the study

developed a theoretical framework emphasizing the “polluter pays” principle to encourage waste reduction and

sustainable production practices. The authors highlighted the use of fiscal policy instruments such as taxes, fines,

subsidies, landfill taxes, and pay-as-you-throw schemes as effective economic incentives for reducing waste and

promoting recycling. Additionally, the study emphasized the importance of developing recycling markets through

waste-to-energy initiatives, deposit-refund systems, and support for recycling enterprises. Overall, the chapter

demonstrated how environmental economics can guide policy design to reduce waste disposal, stimulate economic

activity, and conserve natural resources. Berger et al.

[76]

developed an economic model of packaging waste management

to examine government policy options under the framework of Extended Producer Responsibility (EPR). The model

explicitly incorporated packaging design, consumer sorting behavior, and producers’ output decisions as joint

determinants of total waste generation. The findings revealed that policies achieving first-best outcomes may lack

public acceptability and that constrained policy instruments can lead to sub-optimal production and consumption

levels, even when optimal allocations are theoretically attainable. Moreover, the study showed that landfill taxation

may unintentionally increase landfill waste when combined with tradable recycling credits. These results highlight

critical limitations in existing regulatory schemes, including the UK’s Producer Responsibility Obligations for

packaging waste.

Chikkahanumaiah et al.

[77]

examined citizen engagement strategies and waste management challenges in Varamballi

Gram Panchayat, located in Brahmavara Taluk of Udupi district. The study identified key issues, including low public

awareness, weak Panchayat administration, and unscientific and illegal waste disposal practices. These challenges

were largely attributed to population growth and rapid development activities such as real estate expansion, small-

scale industries, and the growth of commercial establishments. Using qualitative research methods, data were collected

through unstructured, in-depth interviews with ten adult respondents. Interpretive phenomenological analysis (IPA)

was employed to analyze the findings, providing insights into community-level waste management dynamics and

engagement barriers. Tembo et al.

[78]

addressed growing waste management challenges in urban areas by proposing a

comprehensive, citizen-centered waste management system implemented through a user-friendly web application. The

platform enables residents to report, track, and provide feedback on waste-related issues, supported by geolocation

services to improve reporting accuracy. Municipal authorities can respond to reported issues and update their status,

thereby enhancing transparency and accountability. Data security is ensured through the use of hashing algorithms

such as Bcrypt to protect user information. The proposed system aligns with Sustainable Development Goals SDG 11

and SDG 12, promoting sustainable urban development through improved resource efficiency and waste reduction.

Mishra et al.

[79]

investigated the role of machine learning in enhancing public participation and environmental

awareness to support sustainable waste management. The study evaluated classification models, including logistic

regression, random forest, k-nearest neighbors (KNN), and decision trees, using waste composition and treatment

datasets. Model performance was assessed through multiple metrics, such as accuracy, precision, recall, and F1-score.

The Random Forest model achieved the best performance, with 89 % accuracy and an F1-score of 86 %, demonstrating

strong capability in forecasting citizen engagement behavior, while decision tree models also showed promising

potential. The findings highlight how ML-driven civic engagement strategies can improve recycling rates, reduce open

dumping, and enable collaborative waste management planning between governments and local communities.

4. Research gaps

Despite significant advances in smart waste management, IoT integration, and robotic automation, most of the studies

indicates that the development of fully autonomous, intelligent, and adaptable robotic systems for waste collection and

sorting in public environments remains an emerging and underexplored research area. Most existing studies primarily

focus on smart bin designs, IoT-based monitoring systems, and data-driven route optimization.

[80]

Consequently, there

is a notable lack of fully integrated systems capable of autonomously managing the entire waste handling process,

including waste detection, collection, classification, and final disposal. A key limitation identified across the reviewed

studies is the insufficient integration of artificial intelligence (AI), robotics, and IoT into a unified framework. While

several works incorporate IoT-enabled smart bins for monitoring and alerting, they often rely on human-operated

vehicles for physical waste collection.

[54,56,57]

Conversely, robotic arms and mobile platforms-largely evaluated in

laboratory or controlled environments may support autonomous collection and sorting but frequently lack IoT-based

communication and system-level coordination.

[20,21,40]

This separation between cyber (IoT) and physical (robotic)

components restricts scalability and coordinated operation across large public spaces. Waste classification represents

another critical research gap. Many current systems depend on basic sensor-based segregation using moisture or

inductive sensors, limiting classification to coarse categories such as dry, wet, or metallic waste. Although vision-

based approaches using deep learning techniques (e.g., CNNs and YOLO) have shown promising results in controlled

environments, their robustness in real-world outdoor settings remains limited due to challenges such as variable

lighting, occlusion, and irregular waste shapes.

[23,33]

This highlights the need for robust, sensor-fused AI models capable

of reliable real-time waste classification in dynamic environments. Furthermore, the majority of reviewed systems

operate within simulated or semi-controlled settings, constraining their applicability to real-world scenarios. Limited

attention has been given to practical deployment challenges, including dynamic obstacle avoidance, uneven terrain,

battery constraints, and changing weather conditions. Autonomous navigation, energy efficiency, and adaptive

decision-making under uncertain outdoor conditions remain insufficiently addressed in existing research.

Finally, the communication and fleet management aspects of autonomous waste collection robots are relatively under-

researched. Few studies explore multi-robot coordination, cloud synchronization, real-time analytics, or predictive

maintenance. Emerging technologies such as edge computing, low-power IoT protocols, and 5G connectivity offer

significant potential to improve scalability, reliability, and operational efficiency, yet remain largely unexplored in this

domain. Future research should focus on developing holistic AI–IoT–robotics frameworks for autonomous waste

management, robust vision-assisted classification systems for outdoor environments, energy-efficient and adaptive

navigation strategies, and scalable multi-robot coordination architectures to support sustainable smart city waste

management.

4. Discussion

The survey of current research on intelligent waste management systems reveals a rapidly evolving yet fragmented

research landscape. While there is broad consensus that future waste management solutions will increasingly integrate

robotics, the Internet of Things (IoT), and artificial intelligence (AI), most existing studies address these components

in isolation.

[50,58,65,66]

The integration of these technologies into a seamless and fully autonomous system remains a

significant challenge for both researchers and practitioners. This section discusses key insights, comparisons, and

technological implications derived from the reviewed literature, particularly in the context of comprehensive robotic

waste management systems. One major finding is that the majority of existing systems emphasize monitoring rather

than physical action. IoT-based waste management solutions primarily rely on smart bins equipped with sensors, GSM

modules,

[37]

and cloud dashboards to monitor fill levels and notify authorities. Although such systems improve

awareness and scheduling efficiency, they continue to depend on human-operated vehicles for waste collection. In

contrast, robotic systems such as autonomous sweepers or manipulators focus on physical waste collection but often

lack real-time data connectivity and centralized monitoring. This separation highlights the need to integrate IoT-

enabled data intelligence with robotic actuation to enable truly autonomous waste collection.

Another critical issue concerns the autonomy and adaptability of existing systems. Most reported prototypes operate

in structured or semi-structured environments, such as indoor facilities or controlled testbeds. However, real-world

public environments are highly unstructured and dynamic, characterized by pedestrian movement, uneven terrain,

weather variability, and irregular waste distribution. Current systems based on ultrasonic or infrared sensing exhibit

limited adaptability under such conditions. Emerging approaches, including LiDAR-based mapping, stereo vision, and

deep reinforcement learning for adaptive navigation, demonstrate strong potential but remain underexplored in waste

management applications. Future systems must evolve beyond preprogrammed routes toward adaptive, learning-based

navigation strategies. From an AI perspective, waste classification and segregation remains a complex yet impactful

challenge. Basic sensor-based methods using inductive or moisture sensors enable only coarse classification into

categories such as metallic, dry, or wet waste. Although computer vision and convolutional neural networks (CNNs)

have achieved high accuracy in laboratory settings for identifying recyclable materials, their deployment on outdoor

mobile robots is constrained by computational requirements, energy consumption, and environmental variability.

Lightweight deep learning models (e.g., MobileNet, Tiny-YOLO) combined with edge computing platforms offer

promising directions for achieving efficient and robust real-time classification in field conditions.

[23]

System sustainability and energy efficiency also emerge as critical considerations. Most robotic platforms rely on

battery-powered motors without advanced power optimization strategies, limiting operational duration in large public

spaces.

[41]

Integrating solar-assisted charging, low-power microcontrollers, and intelligent power management

algorithms could significantly enhance system autonomy. Additionally, the deployment of autonomous docking or

wireless charging stations within urban infrastructure could enable continuous, unattended operation, supporting long-

term sustainability goals. The communication and data management architecture further influences system scalability.

While GSM and Wi-Fi are commonly used, they may suffer from latency and reliability issues in open urban

environments. Alternative communication technologies such as LoRaWAN, NB-IoT, and 5G offer improved range,

reliability, and energy efficiency. Hybrid data architectures that combine local edge processing with cloud-based

analytics can support both real-time responsiveness and long-term optimization, enabling large-scale institutional

deployment. Finally, multi-robot collaboration represents a promising yet underexplored research direction. Most

current systems operate as standalone units within limited areas. Coordinated fleets of autonomous waste robots,

managed through centralized IoT platforms, could dynamically allocate cleaning tasks based on real-time waste density

and geographic data. Techniques such as swarm intelligence and multi-agent reinforcement learning (MARL) may

enable efficient cooperation, route negotiation, and resource optimization across large urban environments.

5. WasteXpert Auto: a conceptual advanced and integrated waste management system

The WasteXpert Auto is advanced and integrated waste management system fill these gaps by creating a fully

autonomous waste collection robot capable of operating autonomously and safely in public environments. The

WasteXpert Auto system includes several integrated modules: a perception module for detecting waste or obstacles, a

navigation module for the robot to autonomously navigate the space, a manipulator to collect the waste, a sorting

module to sort the waste, and a communication system that transmits this data on-demand. The perception module

uses ultrasonic and infrared sensors to obtain distance measurements, a vision camera to detect objects, and additional

sensors to measure the presence of water, and humans in the environment to ensure safe operation. The navigation

module relies on GPS, IMU, and encoder data for accurate localization and efficient path planning. The robot arm

mechanically collects waste it detects and places it into a dedicated internal sorting unit that automatically categorizes

the waste as dry, wet, or metallic with inductive and moisture sensors. This on-board sorting process will reduce the

need for manual segregation of waste further on in the recycling process, thereby improving the overall recycling

efficiency. Once the internal bins are full, the robot will navigate to the closest dustbin or waste disposal point,

recognized through a combination of GPS data and IoT-based mapping, and will deposit its waste back into the dustbin

before returning to its designated area to continue operation.

The communication system based on Internet of Things (IoT) is the most important part of WasteXpert Auto. The robot

is then able to send telemetry data which include the hotels of the bin, battery life, and location back to either the cloud

server or from an Android application interface using any of the protocols either the GSM or MQTT. The municipalities

or operators using the interface can monitor multiple robots at that time, schedule servicing of their robots in house

and notified of emergency situations for example low battery or bin overflows. The Android application has a feature

a human operator can take manual control to start, stop, or re-route the robot as required. A communication system of

this nature easily aligns with the objectives of smart city initiatives such as the Swachh Abhiyan initiative in India,

which utilizes technology to promote cleanliness and sustainability. The use of automation in waste management is

not only about increasing operational efficiency; it has many indirect potential benefits for public health, environmental

protection, and urban sustainability. Automation here could facilitate less human exposure to waste and, therefore,

reduce the risk of a disease propagating, while also enhancing a city's visual feel. Intelligent sorting at the source could

improve recycling rates, decrease landfill needs, and protect our resources. It is not unreasonable to see that in the

future this may be extended to robots interfacing with a centralized IoT platform to form a smart waste ecosystem,

allowing for coordination and data sharing from multiple robots and smart bins to streamline routes for increased

efficiency, and predict and classify waste generation while allocating resources dynamically.

There are multiple facets of the engineering profession because of the interdisciplinary characteristic of having a robot

that can autonomously manage waste. This can be accomplished by integrating robotics, embedded systems, artificial

intelligence algorithms, power management, and environmental sensing. For example, a robot that has to navigate

through an outdoor public space should be able to avoid obstacles, conserve power, and respond to dynamic conditions

such as pedestrians and uneven surfaces. When developing a manipulator to remove waste, the designer has to consider

the manipulator has to meet more degrees of freedom and accuracy when it is manipulating irregularly shaped objects.

The waste classification task will require the robot to correctly calibrate sensors and process the information in real-

time. The communications module will need to remain connected in areas with low signal so that communications can

remain ongoing. All of these components just to name a few will contribute to the overall performance and reliability

of the system. In the case of WasteXpert Auto, the primary contribution of the proposed system is that it combines full

autonomy and advanced intelligence from a sorting and IoT-based monitoring platform in a single system. It not only

automates waste collection, but incorporates decision-making, communications, and safety and has been designed to

operate continuously in public spaces. It is modular as well, meaning further developments will offer continuous

scalability (across vast zones, multiple robots can combine their operation, all monitored through a central platform).

These developments will be a monumental development toward cleaner, safer, more intelligent cities. The growing

complexity of urban waste management necessitates a transition from conventional manual practices to intelligent,

automated, and sustainable solutions. This review analyzed 37 representative studies addressing smart waste

management through IoT-based monitoring, machine learning-driven prediction, route optimization, and robotic

automation. The analysis reveals that, although significant progress has been made in individual subsystems, most

existing efforts remain fragmented and do not yet realize fully autonomous, end-to-end waste management systems.

The review highlights that current solutions largely focus on isolated components such as smart bins, sensor-based

monitoring, or optimization algorithms, while comprehensive integration of artificial intelligence, robotics, and IoT

within a unified operational framework remains limited. Challenges related to scalability, energy efficiency,

environmental adaptability, and multi-robot coordination continue to restrict real-world deployment in dynamic public

environments. Despite notable advancements in sensing technologies, navigation strategies, and machine learning

models, further research is required to address system-level integration, energy-aware operation, robustness in outdoor

environments, and coordinated fleet management. Future research should prioritize unified AI–IoT–robotic

architectures, edge-enabled intelligence, renewable energy integration, and collaborative robotic systems to enable

scalable and sustainable urban waste management. Within this context, the conceptual framework of WasteXpert Auto

is positioned as a representative direction toward next-generation autonomous waste management. By integrating real-

time sensing, autonomous navigation, intelligent waste classification, and IoT-enabled monitoring, such systems

demonstrate the potential to reduce human intervention, improve operational safety, enhance recycling efficiency, and

support smart city objectives. Overall, this review provides a structured understanding of the current research

landscape, identifies critical gaps, and outlines future directions that can accelerate the development of fully

autonomous, intelligent, and sustainable waste management systems for smarter cities.

6. Conclusion

The increasing complexity of urban waste management demands a decisive transition from conventional manual

practices toward intelligent, automated, and sustainable solutions. This review critically examined 37 representative

studies addressing smart waste management through IoT-based monitoring, machine learning–driven prediction, route

optimization, and robotic automation. The analysis indicates that, while notable progress has been achieved across

individual subsystems, most existing approaches remain fragmented and fall short of delivering fully autonomous,

end-to-end waste management solutions. The findings reveal that current research predominantly emphasizes isolated

components—such as smart bins, sensor-based monitoring, or optimization algorithms—rather than holistic system

integration. Limited coordination between artificial intelligence, robotics, and IoT frameworks continues to constrain

real-world deployment, particularly in dynamic and unstructured urban environments. Persistent challenges related to

scalability, energy efficiency, terrain adaptability, robustness, and multi-robot coordination further hinder large-scale

adoption. Within this context, the conceptual framework of WasteXpert Auto represents a promising direction for next-

generation autonomous waste management systems. By integrating real-time sensing, autonomous navigation,

intelligent waste classification, and IoT-enabled monitoring within a unified architecture, such systems highlight the

potential to reduce human intervention, enhance operational safety, improve waste segregation efficiency, and align

with smart city sustainability objectives. Despite advances in sensing technologies, navigation strategies, and machine

learning models, further research is required to address system-level integration, energy-aware operation, resilience in

outdoor environments, and coordinated fleet management. Future work should prioritize unified AI–IoT–robotic

architectures, edge-enabled intelligence, renewable energy integration, and collaborative multi-robot systems to enable

scalable and sustainable urban waste management. Overall, this review provides a structured understanding of the

current research landscape, identifies critical gaps, and outlines clear future directions that can accelerate the

development of fully autonomous, intelligent, and sustainable waste management systems for smarter cities.

Conflict of Interest

There is no conflict of interest.

Supporting Information

Not applicable

Use of artificial intelligence (AI)-assisted technology for manuscript preparation

The authors confirm that there was no use of artificial intelligence (AI)-assisted technology for assisting in the writing

or editing of the manuscript and no images were manipulated using AI.

References

[1] C. Arteaga, J. Silva, C. Yarasca-Aybar, Solid waste management and urban environmental quality of public space

in Chiclayo, Peru, City and Environment Interactions, 2023, 20, 2023, 100112, doi: 10.1016/j.cacint.2023.100112.

[2] I. R. Abubakar, K. M. Maniruzzaman, U. L. Dano, F. S. AlShihri, M. S. AlShammari, S. M. S. Ahmed, W. A. G.

Al-Gehlani, T. I. Alrawaf, Environmental sustainability impacts of solid waste management practices in the global

south, International Journal of Environmental Research and Public Health, 2022, 19, 12717, doi:

10.3390/ijerph191912717.

[3] K. M. O. Landim, D. Ceglia, E. P. Lopes Júnior, S. H. de Oliveira Lima, A systematic review of urban solid waste

management to mitigate greenhouse gas emissions: a quantitative and qualitative approach, Sustainable Development,

2025, 33, 7474-7512, doi: 10.1002/sd.3510.

[4] P. Awasthi, G. Chataut, R. Khatri, Solid waste composition and its management: A case study of Kirtipur

Municipality-10, Heliyon, 2023, 9, e21360, doi: 10.1016/j.heliyon. 2023.e21360.

[5] S. Shahab, M. Anjum, Solid waste management scenario in India and illegal dump detection using deep learning:

an ai approach towards the sustainable waste management, Sustainability, 2022, 14, 15896, doi: 10.3390/su142315896

[6] R. T. Wasai, M. A. Yohannis, Internet of things-based smart waste segregation system for sustainable waste

management in Nairobi’s residential estates, Journal of Information and Technology, 2025, 5, 68–96, doi:

10.70619/vol5iss10pp68-96

[7] J. N. Jebaranjitham, J. D. S. Christyraj, A. Prasannan, K. Rajagopalan, K. S. Chelladurai, J. K. J. Samuel Gnanaraja,

Current scenario of solid waste management techniques and challenges in Covid-19 – A review, Heliyon, 2022, 8,

e09855, doi: 10.1016/j.heliyon.2022.e09855.

[8] H. I. Abdel-Shafy, M. S. M. Mansour, Solid waste issue: Sources, composition, disposal, recycling, and

valorization, Egyptian Journal of Petroleum, 2018, 27, 1275-1290, doi: 10.1016/j.ejpe.2018.07.003.

[9] R. Tlou, M. Nelisiwe, E. Mariana, The impact of improper waste disposal on human health and the environment:

a case of Umgungundlovu District in KwaZulu Natal Province, South Africa, Frontiers in Sustainability, 2024, 5, doi:

10.3389/frsus.2024.1386047.

[10] R. Mahajan Environment and health impact of solid waste management in developing countries: a review-Current

World Environment, 2023, 18, doi: 10.12944/CWE.18.1.3.

[11] F. A. Kitole, T. O. Ojo, C. U. Emenike, N. Z. Khumalo, K. M. Elhindi, H. S. Kassem, The impact of poor waste

management on public health initiatives in shanty towns in Tanzania, Sustainability, 2024, 16, 10873, doi:

10.3390/su162410873

[12] E. O. Atofarati, V. O. Adogbeji, C. C. Enweremadu, Sustainable smart waste management solutions for rapidly

urbanizing African Cities, Utilities Policy, 2025, 95, 101961, doi: 10.1016/j.jup.2025.101961.

[13] A. Lakhouit, Revolutionizing urban solid waste management with AI and IoT: A review of smart solutions for

waste collection, sorting, and recycling, Results in Engineering, 2025, 25, 104018, doi: 10.1016/j.rineng.2025.104018.

[14] T. M. Kanade, S. B. Sharma, T. K. Savale, A. A. Medhekar, Advancements and evolution of artificial intelligence

(ai) in enhancing robotics: innovations, applications, and future directions. Academy of Marketing Studies Journal,

2025, 29, 1-18.

[15] J. Krejčí, M. Babiuch, J. Suder, V. Krys, Z. Bobovský, Internet of robotic things: current technologies, challenges,

applications, and future research topics, Sensors, 2025, 25, 765, doi: 10.3390/s25030765.

[16] P. Das, G. Gargate, IOT for solid waste management in India: a road towards sustainability, 2024 Portland

International Conference on Management of Engineering and Technology (PICMET), Portland, OR, USA, 2024, 1-

15, doi: 10.23919/PICMET64035.2024.10653160.

[17] S. Neema, K. Gor, Smart waste management using IoT, International Journal of Scientific Research in Science,

Engineering and Technology, 2022, 9, doi: 10.32628/IJSRSET229529.

[18] B. Fang, J. Yu, Z. Chen, A. I. Osman, M. Farghali, I. Ihara, E. H. Hamza, D. W. Rooney, P-S. Yap, Artificial

intelligence for waste management in smart cities: a review, Environmental Chemistry Letters, 2023, 21, 1959–1989,

doi: 10.1007/s10311-023-01604-3.

[19] A. B. Rashid, MD A. K. Kausik, AI revolutionizing industries worldwide: A comprehensive overview of its

diverse applications, Hybrid Advances, 2024, 7, 100277, doi: 10.1016/j.hybadv.2024.100277.

[20] L. Li, L. Li, M. Li, K. Liang, AI-driven robotics: innovations in design, perception, and decision-making,

Machines, 2025, 13, 615, doi: 10.3390/machines13070615.

[21] B.G.M. Mwanza, Robotics in Waste Management: A Smart Technique to Segregate, Recycle, and Recover

Electronic Waste. In: Yatoo, A.M., Sillanpää, M. (eds) Smart Waste and Wastewater Management by Biotechnological

Approaches. Interdisciplinary Biotechnological Advances. Springer, Singapore. 2025, doi: 10.1007/978-981-97-8673-

2_4

[22] S. G. González, D. C. García, R. H. Pérez, A. Á. Sanchez, G. V. González, Autonomous waste classification using

multi-agent systems and blockchain: a low-cost intelligent approach, Sensors, 2025, 25, 4364, doi:

10.3390/s25144364.

[23] M. Kulshreshtha, S. S. Chandra, P. Randhawa, G. Tsaramirsis, A. Khadidos, A. O. Khadidos, OATCR: outdoor

autonomous trash-collecting robot design using YOLOv4-Tiny, Electronics, 2021, 10, 2292, doi:

10.3390/electronics10182292.

[24] S. Fuqaha, N. Nursetiawan, Artificial intelligence and IOT for smart waste management: challenges,

opportunities, and future directions, Journal of Future Artificial Intelligence and Technologies, 2025, 2, 24–46, doi:

10.62411/faith.3048-3719-85.

[25] K. S. Salem, K. Clayson, M. Salas, N. Haque, R. Rao, S. Agate, A. Singh, J. W. Levis, A. Mittal, J. M. Yarbrough,

R. Venditti, H. Jameel, L.Lucia, L. Pal, A critical review of existing and emerging technologies and systems to

optimize solid waste management for feedstocks and energy conversion, Matter, 2023, 6, 3348-3377, doi:

10.1016/j.matt.2023.08.003.

[26] N. Ferronato, V. Torretta, Waste mismanagement in developing countries: a review of global issues, International

Journal of Environmental Research and Public Health, 2019, 16, 1060, doi: 10.3390/ijerph16061060.

[27] M. Ngwira, M. M. Chitete, M. Sibande, Y. Ngwira, C. Damazio, Understanding solid waste collectors’ awareness

of occupational hazards and personal protective equipment practices in northern Malawi. Environmental Health

Insights, 2024, 18, doi:10.1177/11786302241303688

[28] J. Gutberlet, S. M. Nazim Uddin, Household waste and health risks affecting waste pickers and the environment

in low- and middle-income countries, International Journal of Occupational and Environmental Health, 2017, 23,

299–310, doi: 10.1080/10773525.2018.1484996

[29] I. Utip, A. Krayer, S. Williams, Waste handlers’ health and experiences of healthcare waste management in a

Lassa fever treatment centre in Nigeria, Global Health Journal, 2025, 9, 37-45, doi: 10.1016/j.glohj.2025.02.007.

[30] D. B. Olawade, O. Fapohunda, O. Z. Wada, S. O. Usman, A. O. Ige, O. Ajisafe, B. I. Oladapo, Smart waste

management: A paradigm shift enabled by artificial intelligence, Waste Management Bulletin, 2024, 2, 244-263, doi:

10.1016/j.wmb.2024.05.001.

[31] R. Anitha, A. Parthiban, AI-IoT-graph synergy for smart waste management: a scalable framework for predictive,

resilient, and sustainable urban systems, Frontiers in Sustainability, 2025, 6, 2025 10.3389/frsus.2025.1675021.

[32] N. Kumar, Prabhansu, Artificial intelligence and machine learning techniques for next-generation waste

management system: an overview, Cureus Journal of Computer Science, 2025, 2, es44389-025-04880-y, doi:

10.7759/s44389-025-04880-y.

[33] A. Rahmatulloh, I. Darmawan, A. P. Aldya, F. M. S. Nursuwars, WasteInNet: deep learning model for real‐time

identification of various types of waste, Cleaner Waste Systems, 2025, 10, 100198, doi: 10.1016/j.clwas.2024.100198.

[34] H. Nguyen, D. Nawara, R. Kashef, Connecting the indispensable roles of IoT and artificial intelligence in smart

cities: A survey, Journal of Information and Intelligence, 2024, 2, 261-285, doi: 10.1016/j.jiixd.2024.01.003.

[35] I. Rafiq, A. Mahmood, S. Razzaq, S.H.M. Jafri, I. Aziz, IoT applications and challenges in smart cities and

services, Journal of Engineering, 2023, 1–25, doi: 10.1049/tje2.12262.

[36] A. Hoque, M. Padhiary, K. Kumar, J. A. Barbhuiya, The role of robotics in sustainable agriculture and waste

management, In A. J. Obaid, Muthmainnah, S. Rajest, & M. Baron (Eds.), Multidisciplinary Advancements in Human-

AI Augmentation, IGI Global Scientific Publishing, 2026, 265-302, doi: 10.4018/979-8-3373-1987-2.ch012.

[37] P. S. Kumar, V. B. Sree, N. Ramanjaneyulu, S. Nagurvali, V. Rohith, R. S. Teja, Effective garbage monitoring

system using GSM module, 2024 Third International Conference on Intelligent Techniques in Control, Optimization

and Signal Processing (INCOS), Krishnankoil, Virudhunagar district, Tamil Nadu, India, 2024, 1-5, doi:

10.1109/INCOS59338.2024.10527614.

[38] S. Vishnu, S.R.J. Ramson, M. S. S. Rukmini, A. M. Abu-Mahfouz, Sensor-based solid waste handling systems:

a survey, Sensors, 2022, 22, 2340, doi: 10.3390/s22062340.

[39] A. Snoun, M. K. Mufida, A. A. El-Cadi, T. Delot, AI-Driven innovations in waste management: catalyzing the

circular economy, Engineering Proceedings, 2025, 97, 12, doi: 10.3390/engproc2025097012.

[40] G. Ferri, A. Manzi, P. Salvini, B. Mazzolai, C. Laschi, P. Dario, DustCart, an autonomous robot for door-to-door

garbage collection: From DustBot project to the experimentation in the small town of Peccioli, 2011 IEEE International

Conference on Robotics and Automation, Shanghai, China, 2011, 655-660, doi: 10.1109/ICRA.2011.5980254.

[41] H. Abdu, M. H. Mohd Noor, A survey on waste detection and classification using deep learning, IEEE Access,

2022, 10, 128151-128165, doi: 10.1109/ACCESS.2022.3226682.

[42] M. Maghsoudi, S. Shokouhyar, S. Khanizadeh, S. Shokoohyar, Towards a taxonomy of waste management

research: An application of community detection in keyword network, Journal of Cleaner Production, 2023, 401,

2023,136587, doi: 10.1016/j.jclepro.2023.136587.

[43] S. Nižeti´c, N. Djilali, A. Papadopoulos, J. Rodrigues, Smart technologies for promotion of energy efficiency,

utilization of sustainable resources and of the waste management, Journal of Cleaner Production, 2019, 231, 565–

591, doi: /10.1016/j.jclepro.2019.04.397.

[43] M.-J. Rodríguez-Guerreiro, V. Torrijos, M. Soto, A review of waste management in higher education institutions:

the road to zero waste and sustainability, Environments, 2024, 11, 293, doi: 10.3390/environments11120293.

[44] D. Hariyani, P. Hariyani, S. Mishra, M. Kumar Sharma, A literature review on waste management treatment and

control techniques, Sustainable Futures, 2025, 9, 100728, doi: 10.1016/j.sftr.2025.100728.

[45] I. Dawar, A. Srivastava, M. Singal, N. Dhyani, S. Rastogi, A systematic literature review on municipal solid waste

management using machine learning and deep learning, Artificial Intelligence Review, 2025, 58, 183 doi:

10.1007/s10462-025-11196-9

[46] K. Pardini, J. Rodrigues, S. Kozlov, N. Kumar, V. Furtado, IoT-based solid waste management solutions: A

survey, Journal of Sensor and Actuator Networks, 2019, 8, 5, doi: 10.3390/jsan8010005.

[47] R. G. Anuardo, M. Espuny, A. C. Ferreira Costa, O. José Oliveira, Toward a cleaner and more sustainable world:

A framework to develop and improve waste management through organizations, governments and academia, Heliyon,

2022, 8, e09225, doi: 10.1016/j.heliyon.2022.e09225.

[48] P. Sahu, S. Shelare, C. Sakhale, Smart cities waste management and disposal system by innovative system: A

review. International Journal of Scientific Research & Technology, 2020, 9, 4467–4470.

[49] S. Akram, R. Singh, A. Gehlot, M. Rashid, A. AlGhamdi, S. Alshamrani, D. Prashar, Role of wireless aided

technologies in the solid waste management: A comprehensive review, Sustainability, 2021, 13, 13104, doi:

10.3390/su132313104.

[50] A. Rejeb, K. Rejeb, S. Simske, H. Treiblmaier, S. Zailani, The big picture on the internet of things and the smart

city: a review of what we know and what we need to know, Internet of Things, 2022, 19, 2022, 100565, doi:

10.1016/j.iot.2022.100565.

[51] M. Ramírez, S. Keshtkar, D. Padilla, E. Ramos, M. García, M. Hernández, A. Mogro, J. Mahlknecht, J. Huertas,

R. Peimbert-García, R. A. Ramírez-Mendoza, A. M. Mangini, M. Roccotelli, B. L. Pérez-Henríquez, S. C.

Mukhopadhyay, J. de Jesús Lozoya-Santos, Sensors for sustainable smart cities: a review, Applied Science, 2021, 11,

8198, doi: 10.3390/app11178198.

[52] A. Concari, G. Kok, P. Martens, Recycling behaviour: Mapping knowledge domain through bibliometrics and

text mining, Journal of Environmental Management, 2022, 303, 114160, doi: 10.1016/j.jenvman.2021.114160.

[53] G. D’Amico, R. Arbolino, L. Shi, T. Yigitcanlar, G. Ioppolo, Digitalisation driven urban metabolism circularity:

A review and analysis of circular ci.ty initiatives, Land Use Policy, 2022, 112, 105819, doi:

10.1016/j.landusepol.2021.105819.

[54] Panagiotis Zoumpoulis, Fotios K. Konstantinidis, Georgios Tsimiklis, Angelos Amditis, Smart bins for enhanced

resource recovery and sustainable urban waste practices in smart cities: A systematic literature review, Cities, 2024,

152, 2024, 105150, doi: 10.1016/j.cities.2024.105150.

[55] S. Idwan, I. Mahmood, J. Zubairi, I. Matar, Optimal management of solid waste in smart cities using Internet of

Things, Wireless Personal Communications, 2020, 110, 485–501, doi: 10.1007/s11277-019-06738-8.

[56] N. A. Antora, M. A. Rahman, A. A. Mosharraf, M. Ibn Ehsan, M. Alve, M. M. Elahi, Design and implementation

of a smart bin using IOT for an efficient waste management system, 2022 25th International Conference on Computer

and Information Technology (ICCIT), Cox's Bazar, Bangladesh, 2022, 774-779, doi:

10.1109/ICCIT57492.2022.10055998.

[57] T. Juwariyah, L. Krisnawati, S. Sulasminingsih, Design of IoT-based smart bins integrated monitoring system

using Blynk, IOP Conference Series: Materials Science and Engineering, Workshop on Environmental Science,

Society, and Technology (WESTECH 2020) 16-17 October 2020, Makassar, Indonesia, 2021, 1125, 012078, doi:

10.1088/1757-899X/1125/1/012078.

[58] F. M. S. Pebriadi, A. R.Windarsyah, A. Khalid, Design and build Internet of Things (IoT)-based smart waste bin

for waste management, Formosa Journal of Multidisciplinary Research, 2025, doi: 10.55927/fjmr.v4i10.597.

[59] S. Abba, C. I. Light, IoT-based framework for smart waste monitoring and control system: A case study for smart

cities, Engineering Proceedings, 2020, 2, 90, doi: 10.3390/ecsa-7-08224.

[56] J-H. Huh, J-H. Choi, K. Seo, Smart trash bin model design and future for smart city, Applied Sciences, 2021, 11,

4810, doi: 10.3390/app11114810

[61] S. Khan, B. Ali, A. A. K. Alharbi, S. Alotaibi, M. Alkhathami, Efficient IoT-assisted waste collection for urban

smart cities, Sensors, 2024, 24, 3167, doi: 10.3390/s24103167.

[62] X. Lu, X. Pu, X. Han, Sustainable smart waste classification and collection system: A bi-objective modeling and

optimization approach, Journal of Cleaner Production, 2020, 276, 124183, doi: 10.1016/j.jclepro.2020.124183.

[63] S. Aleyadeh, A. -E. M. Taha, An IoT-based architecture for waste management, 2018 IEEE International

Conference on Communications Workshops (ICC Workshops), Kansas City, MO, USA, 2018, 1-4, doi:

10.1109/ICCW.2018.8403750.

[64] A. Namoun, A. Tufail, M. Khan, A. Alrehaili, T. Syed, O. BenRhouma, Solid waste generation and disposal using

machine learning approaches: A survey of solutions and challenges, Sustainability 2022, 14, 13578, doi:

10.3390/su142013578.

[65] R. Alsabt, W. Alkhaldi, Y.A. Adenle, H. M. Alshuwaikhat, Optimizing waste management strategies through

artificial intelligence and machine learning - An economic and environmental impact study, Cleaner Waste Systems,

2024, 8, 2024, 100158, doi: 10.1016/j.clwas.2024.100158.

[66] S. Boovaneswari, I. Varalakshmi, S. Sarathi, P. Sriram, Artificial intelligence enhanced waste sorting and

classification system for urban recycling, Current Trends in Signal Processing, 2025, 15, 23-32.

[67] L. Huang, J. Hou, H. Liu, Machine-learning intervention progress in the field of organic waste composting:

Simulation, prediction, optimization, and challenges, Waste Management, 2024, 178, 2024, 155-167, doi:

10.1016/j.wasman.2024.02.022.

[68] Z. Boudanga, S. Benhadou, H. Medromi, An innovative medical waste management system in a smart city using

XAI and vehicle routing optimization, F1000 Research, 2023, 12, 1060, doi: 10.12688/f1000research.138867.2.

[69] R. Gupta, Z. H. Ouderji, Uzma, Z. Yu, W. T. Sloan, S. You, Machine learning for sustainable organic waste

treatment: a critical review, npj Materials Sustainability, 2024, 2, doi: 10.1038/s44296-024-00009-9

[70] S. A. Bandh, F. A. Malla, S. A. Wani, A. T. Hoang, Waste Management and Circular Economy. In: Bandh, S.A.,

Malla, F.A. (eds) Waste Management in the Circular Economy. Springer, 2023, Cham., doi: 10.1007/978-3-031-

42426-7_1.

[71] M. Kulwant, N. Rai, D. Patel, Circular economy and waste management: advancing sustainability through

integration and innovation. In: Mandpe, A., Paliya, S., Shah, M.P. (eds) A vision for environmental sustainability:

overcoming waste management challenges in developing countries, Environmental Science and Engineering, Springer,

Cham, doi: 10.1007/978-3-031-89230-1_12

[72] R. Paliwal, From waste to wealth: stepping toward sustainability through circular economy. In: Baskar, C.,

Ramakrishna, S., Baskar, S., Sharma, R., Chinnappan, A., Sehrawat, R. (eds) Handbook of Solid Waste Management.

Springer, Singapore. 2022, doi: 10.1007/978-981-16-4230-2_82.

[73] S. Shooshtarian, T. Maqsood, P. S. P. Wong, Policy intervention of waste management, In: Bandh, S.A., Malla,

F.A. (eds) Waste management in the circular economy, Springer, Cham. 2024, doi: 10.1007/978-3-031-42426-7_5.

[74] J. Treacy, Policy implementation on waste management and achievement of related SDGs. In: Leal Filho, W.,

Dinis, M.A.P., Moggi, S., Price, E., Hope, A. (eds) SDGs in the European Region, Implementing the UN Sustainable

Development Goals – Regional Perspectives. Springer, Cham. 2023, doi: 10.1007/978-3-030-91261-1_35-1

[75] H. Zameer, S. Irshad, S. Sarwar, Waste management policy formulation using environmental economics. In:

Shahbaz, M., Sharma, G.D., Gedikli, A., Erdoğan, S. (eds) Global Pathways for Efficient Waste Management and

Inclusive Economic Development. Springer, Singapore. 2025, doi: 10.1007/978-981-96-5569-4_5.

[76] W. Berger, Y. Nagase, Waste management regulation: policy solutions and policy shortcomings, Scottish Journal

of Political Economy, 2018, 65, 205-223, doi: 10.1111/sjpe.12137.

[77] Chikkahanumaiah, B. H. Anjanappa, A case study on strategies of citizen involvement in waste management,

IOSR Journal of Humanities and Social Science, 2023, 28, 45-49.

[78] K. Tembo, H. Vasudavan, U. Eaganathan, Citizen-powered waste management system for cleaner cities, 2025

International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC), Bhubaneswar, India,

2025, 1-6, doi: 10.1109/ASSIC64892.2025.11158334.

[79] D. Mishra, R. Kumar A. B. bin Abdul Hamid, Empowering sustainable waste management: a comparative study

of machine learning models for citizen engagement, 2025 3rd International Conference on Disruptive Technologies

(ICDT), Greater Noida, India, 2025, 633-638, doi: 10.1109/ICDT63985.2025.10986713.

[80] H. Mehta, V. Deriya, D. Sankhe, P. Kanani, G. Pandya, V. Shelke, Smart bins, smarter cities: IoT-driven waste

collection with real-time sensing and methane mapping, Mathematical Modelling of Engineering Problems, 2025, 12,

6, 2110-2122, doi: 10.18280/mmep.120626.

Publisher Note: The views, statements, and data in all publications solely belong to the authors and contributors. GR

Scholastic is not responsible for any injury resulting from the ideas, methods, or products mentioned. GR Scholastic

remains neutral regarding jurisdictional claims in published maps and institutional affiliations.

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which

permits the non-commercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long

as appropriate credit to the original author(s) and the source is given by providing a link to the Creative Commons

License and changes need to be indicated if there are any. The images or other third-party material in this article are

included in the article's Creative Commons License, unless indicated otherwise in a credit line to the material. If

material is not included in the article's Creative Commons License and your intended use is not permitted by statutory

regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view

a copy of this License, visit: https://creativecommons.org/licenses/by-nc/4.0/