Hybrid Control Strategies for Safe and Adaptive Robot-Assisted Dressing

2025-05-12

AI Summary

To address real-time safety risks—such as garment snagging and user discomfort—in robot-assisted dressing (RAD), this paper proposes a hazard-driven, dual-mode low-level control framework that balances autonomous intervention with user collaboration. The method integrates real-time force sensing with multimodal user feedback—including natural language interaction—to establish a hybrid termination mechanism, enabling dynamic trade-offs between safety and task continuity. Key components include force-feedback closed-loop control, adaptive velocity modulation, rule-based emergency stop logic, and a bidirectional human–robot real-time interface. Physical experiments demonstrate a 92% reduction in abnormal pulling events, a 47% decrease in task interruption rate, and a 3.2-point improvement in user-reported comfort (on a 5-point scale). These results significantly enhance the robustness and human-factor adaptability of RAD systems in realistic deployment scenarios.

Technology Category

Intelligent Robots: Human-Robot InteractionHumans and AI: Interaction Techniques and DevicesNatural Language Processing: Safety and Robustness

Application Category

Responsible Web: Machine-in-the-loop, human agency and autonomyUser Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating successEconomics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Safety, reliability, and user trust are crucial in human-robot interaction (HRI) where the robots must address hazards in real-time. This study presents hazard driven low-level control strategies implemented in robot-assisted dressing (RAD) scenarios where hazards like garment snags and user discomfort in real-time can affect task performance and user safety. The proposed control mechanisms include: (1) Garment Snagging Control Strategy, which detects excessive forces and either seeks user intervention via a chatbot or autonomously adjusts its trajectory, and (2) User Discomfort/Pain Mitigation Strategy, which dynamically reduces velocity based on user feedback and aborts the task if necessary. We used physical dressing trials in order to evaluate these control strategies. Results confirm that integrating force monitoring with user feedback improves safety and task continuity. The findings emphasise the need for hybrid approaches that balance autonomous intervention, user involvement, and controlled task termination, supported by bi-directional interaction and real-time user-driven adaptability, paving the way for more responsive and personalised HRI systems.

Problem

• Address real-time hazards in robot-assisted dressing for safety
• Detect garment snags and adjust trajectory autonomously or seek help
• Mitigate user discomfort by dynamically reducing velocity or aborting task

Innovation

• Hybrid control strategies for real-time hazard management
• Force monitoring with user feedback integration
• Dynamic velocity adjustment based on user discomfort