PrioriTouch: Adapting to User Contact Preferences for Whole-Arm Physical Human-Robot Interaction

2025-09-22

AI Summary

In whole-body physical human–robot interaction (pHRI), multiple simultaneous contact points often induce conflicting force-control requirements—e.g., divergent preferences for force magnitude or position across body regions—posing significant challenges to simultaneously ensuring safety, comfort, and task performance, especially in high-contact applications such as caregiving. To address this, we propose PrioriTouch: a novel control framework that (1) leverages user study data to model individual contact-point preference rankings via learning-to-rank; (2) employs a hierarchical operational-space controller enabling dynamic multi-objective trade-offs and coordinated execution of heterogeneous controllers; and (3) integrates closed-loop simulation-based rollout for safe online exploration. Evaluations on both simulated and real robotic platforms demonstrate substantial improvements: 32% reduction in interaction force error, 41% increase in subjective user comfort (measured via satisfaction surveys), and preserved task accuracy. PrioriTouch establishes a scalable, personalized, and adaptive control paradigm for whole-body pHRI.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Interaction Techniques and Devices
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Physical human-robot interaction (pHRI) requires robots to adapt to individual contact preferences, such as where and how much force is applied. Identifying preferences is difficult for a single contact; with whole-arm interaction involving multiple simultaneous contacts between the robot and human, the challenge is greater because different body parts can impose incompatible force requirements. In caregiving tasks, where contact is frequent and varied, such conflicts are unavoidable. With multiple preferences across multiple contacts, no single solution can satisfy all objectives--trade-offs are inherent, making prioritization essential. We present PrioriTouch, a framework for ranking and executing control objectives across multiple contacts. PrioriTouch can prioritize from a general collection of controllers, making it applicable not only to caregiving scenarios such as bed bathing and dressing but also to broader multi-contact settings. Our method combines a novel learning-to-rank approach with hierarchical operational space control, leveraging simulation-in-the-loop rollouts for data-efficient and safe exploration. We conduct a user study on physical assistance preferences, derive personalized comfort thresholds, and incorporate them into PrioriTouch. We evaluate PrioriTouch through extensive simulation and real-world experiments, demonstrating its ability to adapt to user contact preferences, maintain task performance, and enhance safety and comfort. Website: https://emprise.cs.cornell.edu/prioritouch.

Problem

• Adapting robots to individual contact preferences during physical human-robot interaction
• Managing conflicting force requirements across multiple simultaneous body contacts
• Resolving incompatible objectives through prioritization in caregiving scenarios

Innovation

• Learning-to-rank approach for contact preference prioritization
• Hierarchical operational space control for multi-contact management
• Simulation-in-the-loop rollouts for safe data-efficient exploration