Toward Context-Aware Exoskeleton Assistance: Integrating Computer Vision Payload Estimation with a User-Centric Optimization Space

TL;DR

This paper presents a novel, integrated approach combining computer vision and user-centric optimization to improve the effectiveness of back-support exoskeletons in industrial tasks, enhancing assistance precision and user comfort.

Contribution

It introduces a multi-metric optimization space and a vision transformer-based payload estimation method for adaptive exoskeleton control, advancing context-aware assistance.

Findings

Payload estimation accuracy over 82%

Peak back muscle activation reduced by up to 23%

Enhanced user comfort and assistance precision

Abstract

Back-support exoskeletons (BSEs) mitigate musculoskeletal strain, yet their efficacy depends on precise, context-aware modulation. This paper introduces a user-centric optimization framework and a vision-based adaptive control strategy for industrial BSEs. First, we constructed a multi-metric optimization space, integrating electromyography reduction, perceived discomfort, and user preference, through baseline experiments with 12 subjects. This revealed a non-linear relationship between optimal assistance and payload. Second, we developed a predictive computer vision pipeline using a Vision Transformer (DINOv2) to estimate payloads before lifting, effectively overcoming actuation latency. Validation with 12 subjects confirmed the system's robustness, achieving over 82% estimation accuracy. Crucially, the adaptive controller reduced peak back muscle activation by up to 23% compared to static baselines while optimizing user comfort. These results validate the proposed framework, demonstrating that pre-lift environmental perception and user-centric optimization significantly enhance physical assistance and human-robot interaction in industrial settings.