Receiver-Centered Robot-to-Human Handover with Grasp-Aware Object Orientation

2026-07-20

AI Summary

This work addresses the limitations of conventional static handover strategies, which often result in awkward grasping postures when delivering asymmetric industrial tools, thereby compromising the fluency and safety of human–robot interaction. To overcome this, the authors propose a receiver-centric, voice-driven adaptive handover system implemented on a Franka collaborative robot. By integrating a large language model (LLM) for parsing user intent with real-time 3D hand tracking via MediaPipe, the system dynamically adjusts the tool’s end-effector orientation to ensure ergonomic handle alignment. This approach uniquely combines the receiver’s grasping intention with the geometric properties of the tool to enable real-time, pose-adaptive delivery of asymmetric objects. User studies demonstrate that, compared to static baselines, the proposed system significantly reduces grasping latency, enhances interaction fluency, and improves users’ perception of the robot’s motion predictability and task simplicity.

Abstract

Collaborative robots are increasingly sharing workspaces with human operators, making tool handover a frequent and safety-critical micro-interaction. However, traditional static handovers often lead to awkward grasps when handling asymmetric industrial tools. This paper presents a receiver-centered voice-driven adaptive handover system for mechanical tools, built on a Franka cobot. Using an LLM for intention recognition and MediaPipe for real-time 3D hand tracking, the framework dynamically adjusts the end-effector's orientation to present tools in an ergonomically optimal, handle-first pose. A within-subjects study compared this adaptive approach with an object-agnostic static baseline. The results demonstrate that the adaptive system reduces the grasp delay for asymmetric tools, improving the fluency of the interaction. Furthermore, the adaptive strategy improved specific trust-related perceptions, particularly motion predictability and perceived task simplicity.

Problem

• robot-to-human handover
• asymmetric tools
• grasp ergonomics
• human-robot collaboration
• object orientation

Innovation

• adaptive handover
• grasp-aware orientation
• receiver-centered interaction
• LLM-based intention recognition
• real-time hand tracking