IoT-Enabled Smart Reverse Vending Machine with Digital Reward System

Abstract

The alarming rate at which plastics and metals such as bottles are discarded as waste is a serious environmental sustainability issue across the globe. Conventional waste management systems are not equipped with automatic material detection and classification mechanisms, as well as any incentives for users to participate in recycling efforts. This paper describes the development of a Smart Reverse Vending Machine (RVM) using Internet of Things technology to sort collected plastic and metal bottles based on the analysis of information obtained from inductive and capacitive proximity sensors along with a load cell sensor. The sorting process is controlled by a Raspberry Pi 4 Model B, which processes information gathered by the sensors and initiates the movement of the material sorting system actuated using a servo motor. After the completion of the sorting process, users are rewarded with digital currencies through the use of a Universal Payments Interface.

Introduction

The text proposes an IoT-based Smart Reverse Vending Machine (RVM) designed to improve plastic and metal bottle recycling by combining automatic material detection, sorting, weight measurement, and digital rewards through UPI.

Problem

The rapid increase in plastic and metal beverage containers is contributing to pollution and landfill growth. Although RVMs have achieved high recycling rates of 89–98% in countries such as Norway, Germany, Sweden, Finland, and Denmark, their adoption in India remains limited.

Existing systems have two major limitations:

• Low-cost RVMs generally use basic microcontrollers and sensors, offering limited detection and integration capabilities.
• AI-based RVMs can achieve very high accuracy, sometimes above 99%, but require expensive hardware and significant computational resources.

In addition, people may be reluctant to recycle because existing systems often provide little or no financial incentive.

Proposed Solution

The paper proposes an IoT-enabled Smart RVM that combines affordable sensors with a Raspberry Pi 4 and a UPI-based reward system.

The main components are:

• Inductive proximity sensor: Detects metallic containers such as aluminum or steel.
• Capacitive proximity sensor: Detects plastic containers.
• Load cell + HX711: Measures the weight of the deposited item.
• Raspberry Pi 4 Model B: Processes sensor data and controls the overall system.
• SG90 servo motor: Automatically directs the container into the appropriate plastic or metal compartment.
• LCD display: Provides users with information about detection, sorting, and rewards.
• UPI reward system: Provides a digital payment incentive to the user's registered UPI account.

System Operation

The proposed process is:

Insert bottle → Detect material → Measure weight → Classify → Sort automatically → Display result → Provide UPI reward

The Raspberry Pi acts as the central controller, receiving information from the sensors and activating the servo-based sorting mechanism. Once the item is successfully classified and sorted, the system generates a digital reward.

Literature Review

Previous research demonstrates that different RVM technologies have achieved promising results:

• Deep-learning systems have reported 99–100% classification accuracy, but they are expensive and computationally demanding.
• Sensor-based systems using inductive and capacitive sensors have achieved approximately 96–100% accuracy under certain conditions.
• One study reported 99% material-detection accuracy with an average response time of about 2.66 seconds using inductive and capacitive sensors.
• Some systems provide rewards through coupons, RFID, or cloud-based points, but generally lack UPI integration and automatic multi-material sorting.

The paper identifies a research gap: affordable systems tend to have limited material detection and reward capabilities, while high-accuracy AI systems are often too expensive for widespread deployment in developing countries.

Objectives

The proposed research aims to:

1. Develop an RVM for collecting plastic and metallic bottles.
2. Detect metals using an inductive proximity sensor and plastics using a capacitive proximity sensor.
3. Measure deposited items using a load cell and HX711.
4. Automatically sort materials into separate compartments.
5. Provide users with digital UPI-based rewards for recycling.

Key Advantages

The proposed system seeks to provide:

• Affordable hardware
• Automatic plastic/metal identification
• Automatic sorting
• Weight-based measurement
• IoT connectivity
• Immediate user feedback
• Digital financial incentives through UPI
• A solution particularly suited to the Indian recycling environment

Conclusion

In this research paper, we have designed and developed an IoT-powered Smart Reverse Vending Machine that is capable of detecting and classifying plastic and metallic bottles without any manual intervention through a low-cost sensor-based arrangement. The metallic bottles can be sensed by using the inductive proximity sensor (LJ12A3-4-Z/BX), and the plastic bottles can be detected by the capacitive sensor (LJC18A3-B-Z/BX). The processing of the data from both sensors is performed by Raspberry Pi 4 Model B. The system, as proposed, not only takes into account the need for automation of waste sorting but also the aspect of encouraging users. Both these aspects have been found to be lacking in RVM systems time and again [4][6][10]. It is a recycling program based on digital incentives and hence very relevant in the Indian context. The system enables efficient sorting without using AI-based techniques, which are costly. Further research will concentrate on enhancing materials recognition to include glass, enabling IoT monitoring via the cloud, examining the ideal positioning for installation based on sustainable positioning models, and carrying out extensive tests to determine the system’s effectiveness and user engagement levels.

References

[1] C. Gomes da Silva, M. E. Fernandes, and J. M. C. Costa, “Sustainable Location of Reverse Vending Machines,” Circular Economy and Sustainability, vol. 6, p. 106, 2026. DOI: 10.1007/s43615-026-00825-2. [2] A. Marzuki, A. Zaky, B. Handoko, D. Q. Mustieni, and N. Risyadi, “IoT-Based Reverse Vending Machine with Deep Learning for Bottle Waste Management,” 2025. [3] A. Subbiah and N. A. D. Mohd Muner, “Advancing Sustainable Waste Management on Campus through an Intelligent Reverse Vending Machine,” 2025. [4] M. E. Fernandes and J. M. C. Costa, “Reverse Vending Machines in the Circular Economy: A Bibliometric Analysis of an Underexplored Enabler (2003–2023),” Cleaner Waste Systems, vol. 12, p. 100404, 2025. DOI: 10.1016/j.clwas.2025.100404. [5] M. D. C. Mendoza and M. A. Ahmed, “Modeling and Comparative Scenario-Based Simulation of SmartBottle+: An AI-Powered Recycling Reward System versus Hungary’s Conventional Reverse Vending Machines,” Procedia Computer Science, vol. 274, pp. 711–720, 2025. DOI: 10.1016/j.procs.2025.12.069. [6] S. Sharma, “Reverse Vending Machine (RVM),” International Journal of Engineering in Computer Science, vol. 7, no. 1, pp. 60–66, 2025. DOI: 10.33545/26633582.2025.v7.i1a.199. [7] N. N. H. A. Shukor and A. K. A. Rahim, “Design of Feeding System in Recycle Vending Machine (RVM),” Research Progress in Mechanical and Manufacturing Engineering, vol. 4, no. 2, pp. 48–58, 2023. DOI: 10.30880/rpmme.2023.04.02.007. [8] N. Sangprasert, K. Inthavisas, K. Wattanakul, and N. Noorit, “Development of a Low-Cost Reverse Vending Machine for Clear Plastic Bottles and Aluminum Cans,” Science, Engineering and Health Studies, 2023. [9] H. Zia et al., “Plastic Waste Management through a Low-Cost Deep Learning-Based Reverse Vending Machine,” Recycling, vol. 7, no. 5, 2022. DOI: 10.3390/recycling7050070. [10] M. E. Rana, K. Shanmugam, and K. Q. Yi, “IoT Based Reverse Vending Machine to Identify Aluminium Material and Allocate Point Reward,” in Proc. 2022 Int. Conf. on Decision Aid Sciences and Applications (DASA), 2022, pp. 645–649. DOI: 10.1109/DASA54658.2022.9765296. [11] D. Kim et al., “Designing of Reverse Vending Machine to Improve Sorting Efficiency,” Journal of Air & Waste Management Association, vol. 71, no. 10, pp. 1312–1318, 2021. DOI: 10.1080/10962247.2021.1939811. [12] R. Tomari et al., “Reverse Vending Machine Item Verification Module using CNN,” 2021. [13] D. Mariya et al., “Plastic Bottle Reverse Vending Machine,” International Journal of Creative Research Thoughts (IJCRT), vol. 12, no. 3, pp. k221–k225, 2024. [14] E. Watanyulertsakul, “The Accuracy of Sorting Beverage Cans and Bottles for a Reverse Vending Machine,” 2019. [15] K. K. Wong et al., “Development of Reverse Vending Machine using Recycled Materials and Arduino,” 2019. [16] R. Tomari et al., “Development of Reverse Vending Machine Framework for Implementation to a Standard Recycle Bin,” Procedia Computer Science, vol. 105, pp. 75–80, 2017. DOI: 10.1016/j.procs.2017.01.202.

Copyright

Copyright © 2026 Prof. Dr. Yugendra Chincholkar, Atharva Gaikwad, Sakshi Pimpale, Rishika Singh, Aasim Shaikh. 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.