TS-MAMP: A Remanufactured Agricultural Robot Powered by Second-Life EV Components and NMS-Free On-Device Weed Detection

2026-08-03

AI Summary

This study addresses the high cost of Agriculture 4.0 robotics, which limits accessibility for smallholder farmers, and the environmentally detrimental disposal of retired low-speed electric vehicle powertrains. To tackle these challenges, the authors propose a novel, low-cost, reconfigurable agricultural mobile platform developed under the 3R (Reduce, Reuse, Recycle) circular economy framework. The platform repurposes screened 48V brushless DC hub motors and lead-acid battery modules with 60%–80% state-of-health. It integrates a lightweight YOLOv10n weed detection model that eliminates non-maximum suppression, employs back-EMF-based motor pairing, active battery balancing, an adjustable-gauge truss chassis, and FP16 TensorRT deployment for edge inference. The resulting system achieves a bill-of-materials cost below $450—approximately 60% lower than conventional alternatives—and attains 80.87% mAP@0.5 on the Wanxi dataset, demonstrating the feasibility and practicality of real-time autonomous field operations.

Abstract

Agriculture 4.0 robotic systems improve field efficiency yet remain too capital-intensive for the fragmented smallholdings that dominate global agriculture. Meanwhile, a growing number of retired low-speed electric-vehicle (LSEV) powertrains retain functional electromechanical value but are destructively recycled. This paper presents TS-MAMP (Telescopic-Sleeve Modular Agricultural Mobile Platform), a remanufactured robot built under 3R (reduce, reuse, recycle) circular-economy principles. Retired 48 V brushless-DC (BLDC) hub motors are paired via back-EMF matching, and lead-acid battery modules screened at 60%-80% state of health are actively balanced within a 100 mV inter-module voltage deviation. Together, these reused components reduce the powertrain-and-chassis BOM cost by approximately 60%, to below USD 450 (perception and weeding modules excluded). The truss chassis provides >=200 kg static load, continuously adjustable track width from 1200 mm to 2000 mm, and <=5-minute module changeover. An NMS-free (non-maximum-suppression-free) YOLOv10n detector with consistent dual-assignment training and negative-sample learning achieves 80.87% mean average precision (mAP)@0.5 (58.41% mAP@0.5:0.95) on the Wanxi Crop-Weed dataset, and is deployed via FP16 TensorRT on a Jetson Nano, confirming on-device inference feasibility. TS-MAMP demonstrates that retired EV components, under modest screening, can be re-engineered into affordable, AI-enabled agricultural robots--opening a remanufacturing pathway for the smallholder fields that commercial automation leaves unserved.

Problem

• Agriculture 4.0
• smallholder farming
• second-life EV components
• circular economy
• affordable agricultural robotics

Innovation

• remanufacturing
• second-life EV components
• NMS-free object detection
• circular economy
• on-device AI