Computer Vision-based Adaptive Control for Back Exoskeleton Performance Optimization

--Back exoskeletons can reduce musculoskeletal strain, but their effectiveness depends on support modulation and adaptive control. This study addresses two challenges: defining optimal support strategies and developing adaptive control based on payload estimation. We introduce an optimization space based on muscle activity reduction, perceived discomfort, and user preference, constructing functions to identify optimal strategies. Experiments with 12 subjects revealed optimal operating regions, highlighting the need for dynamic modulation. Based on these insights, we developed a vision-based adaptive control pipeline that estimates payloads in real-time by enhancing exoskeleton contextual understanding, minimising latency and enabling support adaptation within the defined optimisation space. V alidation with 12 more subjects showed over 80% accuracy and improvements across all metrics. Compared to static control, adaptive modulation reduced peak back muscle activation by up to 23% while preserving user preference and minimising discomfort. These findings validate the proposed framework and highlight the potential of intelligent, context-aware control in industrial exoskeletons. Musculoskeletal disorders are a growing concern in industrial workplaces, where workers in construction sites, production, logistics, and others who regularly lift heavy loads face significant risks. To address these issues, back support exoskeletons (BEs) have been developed, aiming to reduce muscular activation and spinal loadskey contributors to back impairment [1]-[4]. Over the past few decades, advancements in the design of active BEs have improved their kinematic compatibility, reduced their weight, enhanced their acceptability, and proposed innovative designs [5]-[9].