iTrash: Incentivized Token Rewards for Automated Sorting and Handling

TL;DR

This paper introduces iTrash, a smart trashcan addon that fuses computer-vision-based waste sorting with blockchain-based incentives to improve recycling in small office-like spaces. The system uses a modular 3D-printed mechanical design, four proximity sensors, a camera, and a Raspberry Pi to guide users with LED cues, while a GPT-4o-mini classifier determines the appropriate bin. Rewards are issued via the XRP Testnet, with a data-logging pipeline that records predictions, user actions, and timings for future optimization. In a 5-day field test, iTrash achieved about 82% sorting accuracy, substantially outperforming a control trashcan at 47%, though reward participation was low, indicating a need for more seamless reward delivery (e.g., NFC). Overall, the work demonstrates the feasibility of integrating automated waste sorting with token-based incentives to enhance recycling in compact environments and provides a data-rich platform for further optimization and urban-scale deployment.

Abstract

As robotic systems (RS) become more autonomous, they are becoming increasingly used in small spaces and offices to automate tasks such as cleaning, infrastructure maintenance, or resource management. In this paper, we propose iTrash, an intelligent trashcan that aims to improve recycling rates in small office spaces. For that, we ran a 5 day experiment and found that iTrash can produce an efficiency increase of more than 30% compared to traditional trashcans. The findings derived from this work, point to the fact that using iTrash not only increase recyclying rates, but also provides valuable data such as users behaviour or bin usage patterns, which cannot be taken from a normal trashcan. This information can be used to predict and optimize some tasks in these spaces. Finally, we explored the potential of using blockchain technology to create economic incentives for recycling, following a Save-as-you-Throw (SAYT) model.

Figures (7)

• Figure 1: iTrash concept: Diagram showing the incentive mechanism of iTrash. When users recycle properly (1), they earn a reward from iTrash (2). Then, they are able to purchase products or services (3) with the rewards (4) received with iTrash.
• Figure 2: High-level vision of system's workflow. 1) User shows a disposal item to a camera within the iTrash system. 2) The camera detects the waste and determines the color of the bin in which to dispose the item. 3) Light displayed from an LED strip with the correct bin color is emitted to inform the user. 4) User throws the item to the corresponding bin. 5) Feedback about this action is sent to a blockchain network. 6) In case the recycle process was successful, the user receives a reward in the shape of a crypto token (i.e., XRP).
• Figure 3: Overview of iTrash design and components. A) 3D mechanical components, exploded-axonometric view. B) Hardware components and connections, side and top views. C) Installation on a real trashcan.
• Figure 4: State machine diagram for the iTrash software controller. The diagram shows the information flow of the system when a person interacts with iTrash.
• Figure 5: Environmental setup for the proposed system. A) Panoramic view of the area where the experiments were performed, in the right-hand side an iTrash is located, opposite to it, the control trashcan can be seen. The separation between these two devices was 25 meters. B) iTrash together with an additional display screen where the instructions to use the device were shown.