AI-Based River Cleaning Robot for Plastic Waste: Design, Development, and Implementation

Abstract

Plastic waste contamination of rivers and other water bodies has become a pressing global environmental challenge. Conventional waste management techniques, which often rely on manual labour, are inefficient and struggle to handle the vast scale of pollution. This study introduces an AI-powered river-cleaning robot designed to autonomously identify, collect, and manage floating plastic waste to address this issue. The system enhances detection and waste retrieval efficiency by incorporating Artificial Intelligence (AI), the Internet of Things (IoT), and computer vision. The robot utilizes advanced technologies such as Convolutional Neural Networks (CNN) and the YOLO (You Only Look Once) algorithm for real-time waste identification, while a conveyor belt mechanism facilitates efficient collection. Additionally, IoT-enabled monitoring ensures real-time data transmission and performance tracking. The robot uses a dual-energy system, combining a rechargeable battery with solar power to enhance sustainability. This innovative approach aims to minimize reliance on manual labour, improve the effectiveness of waste removal, and promote environmentally responsible waste management. Experimental evaluations confirm the system’s high accuracy in detecting and collecting plastic debris, demonstrating its potential as a scalable and efficient solution for river pollution control.

Introduction

Problem Overview:
Water, essential for life, is increasingly threatened by pollution and overuse. Urbanization, industrial growth, and human activities have reduced clean water availability. Plastic pollution severely harms aquatic ecosystems, water quality, and human health. Traditional river-cleaning methods, reliant on manual labor, are inefficient, hazardous, and unsustainable.

Proposed Solution:
To address these challenges, the study introduces an AI-powered river-cleaning robot. This autonomous system uses AI, computer vision, IoT, and robotics to detect, collect, segregate, and manage plastic waste in water bodies. It aims to reduce human involvement, improve waste collection efficiency, and enable real-time monitoring and sustainability through solar energy and battery power.

System Overview:

1. Hardware Components:

• Central Unit: Raspberry Pi 4 Model B processes AI algorithms and controls sensors/motors.

• Vision System: High-resolution camera with CNNs, YOLO, and Mask R-CNN for object detection.

• Sensors: Ultrasonic and IR for obstacle avoidance; plastic ID via infrared spectroscopy; DHT11 for temperature/humidity; GPS for location tracking.

• Mobility & Manipulation: DC/servo motors for movement; robotic arm and gripper for waste collection.

• Connectivity: Wi-Fi, Bluetooth, LoRa/Zigbee for real-time and remote monitoring.

• Power: Li-ion/Li-Po batteries with solar panel support for sustainable energy.

2. Software & Algorithms:

• Detection & Classification: Uses CNN, YOLO, Mask R-CNN, K-Means, SVM for waste identification and sorting.

• Navigation & Mapping: Employs SLAM, A*, and RRT for path planning.

• Robotic Control: Inverse Kinematics and force control for precise collection.

• Optimization: Reinforcement Learning and Genetic Algorithms for performance improvement.

• Energy Management: Dynamic Power Management ensures efficiency.

• Communication: MQTT protocol for IoT-based remote control and Edge AI for low-latency decisions.

3. Workflow:

• Initialization → Environment mapping → Waste detection → Navigation → Collection → Segregation → Real-time monitoring → Energy optimization → Task completion.

Results & Comparisons:

Traditional Methods:

• Labor-intensive, time-consuming, limited in scale.

• Prone to errors and ecological disruption.

• Lack of monitoring tools.

AI-Based Systems:

• Autonomous, scalable, and efficient.

• Real-time detection and operation in diverse environments.

• Eco-friendly and cost-effective in the long term.

• Supports data-driven decision-making.

Conclusion

This paper presents the design and development of an AI-based river-cleaning robot that integrates AI, IoT, and robotics technologies to autonomously detect, collect, and segregate plastic waste from water bodies. The proposed system offers a cost-effective, energy-efficient, and scalable solution for river cleaning, reducing the reliance on manual labour and minimising environmental impact. Experimental results demonstrate the robot\'s ability to efficiently clean water surfaces, with an average waste detection accuracy of 96%. Future work will focus on improving the robot\'s battery life, scalability, and real-world deployment.

References

[1] S. Lata and N. Siddharth, “Sustainable and eco-friendly approach for controlling industrial wastewater quality imparting succour in water-energy nexus system,” Energy Nexus, vol. 3, p. 100020, Nov. 2021, doi: 10.1016/j.nexus.2021.100020. [2] S. M. Popescu et al., “Artificial intelligence and IoT driven technologies for environmental pollution monitoring and management,” Frontiers in Environmental Science, vol. 12, Feb. 2024, doi: 10.3389/fenvs.2024.1336088. [3] Y. Y. F. Panduman, N. Funabiki, E. D. Fajrianti, S. Fang, and S. Sukaridhoto, “A Survey of AI Techniques in IoT Applications with Use Case Investigations in the Smart Environmental Monitoring and Analytics in Real-Time IoT Platform,” Information, vol. 15, no. 3, p. 153, Mar. 2024, doi: 10.3390/info15030153. [4] G. T. Braulik, U. Noureen, M. Arshad, and R. R. Reeves, “Review of status, threats, and conservation management options for the endangered Indus River blind dolphin,” Biological Conservation, vol. 192, pp. 30–41, Sep. 2015, doi: 10.1016/j.biocon.2015.09.008. [5] J. Walsh and K. K. Zin, “Achieving sustainable Community-Based tourism in Rural Myanmar: The case of River Ayeyarwaddy Dolphin Tourism,” Zagreb International Review of Economics and Business/Zagreb International Review of Economics & Business, vol. 22, no. 2, pp. 95–109, Nov. 2019, doi: 10.2478/zireb-2019-0022. [6] K. N. A. Maulud, A. Fitri, W. H. M. W. Mohtar, W. S. W. M. Jaafar, N. Z. Zuhairi, and M. K. A. Kamarudin, “A study of spatial and water quality index during dry and rainy seasons at Kelantan River Basin, Peninsular Malaysia,” Arabian Journal of Geosciences, vol. 14, no. 2, Jan. 2021, doi: 10.1007/s12517-020-06382-8. [7] B. Koki, “Development of water quality index of Ex-Mining ponds in Malaysia - ProQuest.” https://www.proquest.com/openview/1d9da7f610c41a298438a0af94217813/1?pqorigsite=gscholar&cbl=2026366&diss=y [8] Sinha, P. Bhardwaj, B. Vaibhav, and N. Mohommad, “Research and development of Ro-boat: an autonomous river cleaning robot,” Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE, Jan. 2014, doi: 10.1117/12.2037898. [9] G. S. Khekare, U. T. Dhanre, G. T. Dhanre, and S. S. Yede, “Design of optimized and innovative remotely operated machine for water surface garbage assortment,” International Journal of Computer Sciences and Engineering, vol. 7, no. 1, pp. 113–117, Jan. 2019, doi: 10.26438/ijcse/v7i1.113117. [10] J. B. Fernandes, K. R. Krishnamoorthi, N. S. Reddy, S. S. B, S. L. S, and T. J. Reddy, A Survey on Solar Powered Automatic Drainage Cleaning Systems. 2024, pp. 627–631. doi: 10.1109/icicnis64247.2024.10823245. [11] L. Yang, S. H. Yang, and L. Plotnick, “How the internet of things technology enhances emergency response operations,” Technological Forecasting and Social Change, vol. 80, no. 9, pp. 1854–1867, Aug. 2012, doi: 10.1016/j.techfore.2012.07.011. [12] G. M. Owusu, J. K. F. Okyere, S. K. Armah, and P. L. Kwao, A Low-Cost Autonomous Surface Vehicle (ASV) for Plastic Waste Collection on Water Bodies. 2024, pp. 41–46. doi: 10.1109/iccma63715.2024.10843900. [13] S. Krishnan, A. J. Anand, and R. Kumar, Sustainable development goals. 2024. doi: 10.1201/9781003468257. [14] P. K. R. Maddikunta et al., “Unmanned aerial vehicles in smart agriculture: Applications, requirements, and challenges,” IEEE Sensors Journal, vol. 21, no. 16, pp. 17608–17619, Jan. 2021, doi: 10.1109/jsen.2021.3049471. [15] M. A. Alloghani, “Artificial Intelligence for Ocean Conservation: Sustainable computer vision techniques in marine debris detection and classification,” in Signals and communication technology, 2023, pp. 99–136. doi: 10.1007/978-3-031-45214-7_6. [16] F. R. Sayem et al., “Enhancing waste sorting and recycling efficiency: robust deep learning-based approach for classification and detection,” Neural Computing and Applications, Dec. 2024, doi: 10.1007/s00521-024-10855-2. [17] M. Dudek, P. Tomczyk, P. Wygonik, M. Korkosz, P. Bogusz, and B. Lis, “Hybrid fuel cell – battery system as a main power unit for small unmanned aerial vehicles (UAV),” International Journal of Electrochemical Science, vol. 8, no. 6, pp. 8442–8463, Jun. 2013, doi: 10.1016/s1452-3981(23)12901-4. [18] Prasad, K. Chaudhary, B. Sharma, and A. S. Ali, “Robot Path Planning and Motion Control: A Systematic review,” Engineered Science, Jan. 2024, doi: 10.30919/es1354. [19] T. Khan, S. Li, S. Kadry, and Y. Nam, “Control framework for trajectory planning of soft manipulator using optimized RRT algorithm,” IEEE Access, vol. 8, pp. 171730–171743, Jan. 2020, doi: 10.1109/access.2020.3024630. [20] S. P. Gundupalli, S. Hait, and A. Thakur, “A review on automated sorting of source-separated municipal solid waste for recycling,” Waste Management, vol. 60, pp. 56–74, Sep. 2016, doi: 10.1016/j.wasman.2016.09.015. [21] J. Bobulski and M. Kubanek, “Deep learning for plastic Waste Classification system,” Applied Computational Intelligence and Soft Computing, vol. 2021, pp. 1–7, May 2021, doi: 10.1155/2021/6626948. [22] G. Krishna, R. Singh, A. Gehlot, S. V. Akram, N. Priyadarshi, and B. Twala, “Digital Technology Implementation in Battery-Management Systems for Sustainable Energy Storage: review, challenges, and recommendations,” Electronics, vol. 11, no. 17, p. 2695, Aug. 2022, doi: 10.3390/electronics11172695. [23] O. Olayiwola, M. Elsden, and M. Dhimish, “Robotics, Artificial Intelligence, and Drones in Solar Photovoltaic Energy Applications—Safe Autonomy Perspective,” Safety, vol. 10, no. 1, p. 32, Mar. 2024, doi: 10.3390/safety10010032. [24] Sahay, S., Banoudha, A., & Sharma, R. (2012). On the use of ANFIS for Ground Water Level Forecasting in an Alluvium Area. International Journal of Research and Development in Applied Science and Engineering, 2(1).2012 [25] Sahay, S., Banoudha, A., & Sharma, R. On the use of ANFIS for Predicting Groundwater Levels in Hard Rock Area. . International Journal of Research and Development in Applied Science and Engineering, 6(1). 2014.

Copyright

Copyright © 2025 Mahfooz Ahmad, Tasleem Jamal, Mohammad Aqib. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.