From Vision to Assistance: Gaze and Vision-Enabled Adaptive Control for a Back-Support Exoskeleton

2026-02-04

AI Summary

Current back-support exoskeletons often lack contextual awareness, hindering timely and adaptive assistance and thereby compromising human–robot collaboration efficiency and user comfort. To address this limitation, this work proposes a vision-gated control framework that uniquely integrates first-person visual input with wearable eye-tracking data. By leveraging real-time object detection via YOLO, a task-driven finite state machine, and a variable admittance controller, the system proactively modulates assistive torque based on the user’s operational intent. User studies demonstrate that the proposed approach significantly reduces perceived physical workload while enhancing movement fluency, user trust, and comfort, with participants expressing a clear preference for this method over conventional strategies.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Interaction Techniques and Devices
• Computer Vision: Motion & Tracking

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Back-support exoskeletons have been proposed to mitigate spinal loading in industrial handling, yet their effectiveness critically depends on timely and context-aware assistance. Most existing approaches rely either on load-estimation techniques (e.g., EMG, IMU) or on vision systems that do not directly inform control. In this work, we present a vision-gated control framework for an active lumbar occupational exoskeleton that leverages egocentric vision with wearable gaze tracking. The proposed system integrates real-time grasp detection from a first-person YOLO-based perception system, a finite-state machine (FSM) for task progression, and a variable admittance controller to adapt torque delivery to both posture and object state. A user study with 15 participants performing stooping load lifting trials under three conditions (no exoskeleton, exoskeleton without vision, exoskeleton with vision) shows that vision-gated assistance significantly reduces perceived physical demand and improves fluency, trust, and comfort. Quantitative analysis reveals earlier and stronger assistance when vision is enabled, while questionnaire results confirm user preference for the vision-gated mode. These findings highlight the potential of egocentric vision to enhance the responsiveness, ergonomics, safety, and acceptance of back-support exoskeletons.

Problem

• back-support exoskeleton
• adaptive assistance
• context-aware control
• egocentric vision
• gaze tracking

Innovation

• vision-gated control
• egocentric vision
• gaze tracking
• adaptive admittance control
• back-support exoskeleton