Receiver-Centered Robot-to-Human Handover with Grasp-Aware Object Orientation
2026-07-20 • Robotics
Robotics
AI summaryⓘ
The authors created a robot system that hands tools to people in a smarter way by listening to voice commands and tracking the person's hand in 3D. Instead of handing tools in a fixed position, the robot adjusts how it holds the tool so it's easier and faster for the person to grab. They tested this method against a normal, unchanging handover and found that the smart system made tool passing quicker and made people trust the robot more because its movements were easier to predict and the task felt simpler.
collaborative robotstool handoverintention recognitionLLM (large language model)3D hand trackingMediaPipeergonomicsend-effector orientationhuman-robot interactiontrust in robotics
Authors
Federico Biagi, Dario Onfiani, Simone Silenzi, Luigi Biagiotti
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.