RoboAssist: Interactive Human-Humanoid Planning for Long-Horizon Surgical Assistance

2026-09-30

AI Summary

This study addresses the challenges of human-robot coordination and execution safety for humanoid robots during long-horizon surgical assistance. To this end, it proposes an agent-based interaction planning framework that introduces a novel asymmetric dual-track representation mechanism to decouple human states from robot tasks, combined with suffix-based local replanning for efficient online inference. Furthermore, a cross-layer safety architecture integrating preventive, reactive, and runtime supervision is constructed. Validated in simulated surgical scenarios using the Unitree G1 humanoid robot, the proposed approach demonstrates reliable execution of multi-stage tasks. It significantly reduces replanning latency and token consumption while effectively ensuring safety during navigation and instrument handover.

Abstract

Long-horizon surgical assistance requires humanoid robots to coordinate with evolving human activities while maintaining safety across planning and execution. We present RoboAssist, an agent-based framework for interactive human-humanoid planning that integrates workflow reasoning, task coordination, and cross-layer safety. At its core is an asymmetric dual-track representation that separates partially observed human process states from executable robot task sequences. By updating human-process estimates, scene context, and task dependencies online, RoboAssist revalidates the remaining task sequence and replans only the affected suffix when workflow requests change. A cross-layer safety architecture combines preventive navigation regulation, reactive regulation during close-range handover, and independent whole-body runtime supervision. This design couples online task coordination with safety constraints throughout execution. We demonstrate the framework on a Unitree G1 humanoid robot in long-horizon, multi-stage simulated surgical assistance scenarios encompassing multimodal interaction, instrument handling, medical material transport, navigation, and safe human-robot handover. Experiments show multi-stage task completion and adaptation to workflow-request changes. A targeted full-replanning ablation shows that residual replanning reduces plan-update latency and post-update token usage. Separate safety experiments demonstrate complementary protection across navigation, handover, and runtime supervision. Additional results and demonstrations are available online at https://roboassist.github.io.

Problem

• Long-horizon surgical assistance
• Humanoid robot
• Human-robot coordination
• Safety

Innovation

• Asymmetric Dual-track Representation
• Residual Replanning
• Cross-layer Safety Architecture
• Human-Humanoid Planning
• Long-horizon Surgical Assistance