Compliant Blind Handover Control for Human-Robot Collaboration

TL;DR

This work tackles blind handovers in human–robot collaboration by proposing a compliant, force-driven handover architecture that operates without vision. It combines an admittance-controlled, safety-governed trajectory planner with a neural network that interprets force-load transfer patterns to time gripper release, all while adhering to ISO/TS 15066 safety constraints. Empirical validation against a non-compliant baseline shows improved user experience, reduced handover failures, and robust performance under disturbances. The approach advances practical HRC by enabling safe, autonomous, and natural handovers when the operator cannot visually monitor the robot, with potential extensions to vision-based perception and multi-channel communication.

Abstract

This paper presents a Human-Robot Blind Handover architecture within the context of Human-Robot Collaboration (HRC). The focus lies on a blind handover scenario where the operator is intentionally faced away, focused in a task, and requires an object from the robot. In this context, it is imperative for the robot to autonomously manage the entire handover process. Key considerations include ensuring safety while handing the object to the operator's hand, and detect the proper timing to release the object. The article explores strategies to navigate these challenges, emphasizing the need for a robot to operate safely and independently in facilitating blind handovers, thereby contributing to the advancement of HRC protocols and fostering a natural and efficient collaboration between humans and robots.

Figures (6)

• Figure 1: Proposed Architecture
• Figure 2: Load-Force Transfer Curve. $f_{GL}$, $f_{GG}$, $f_{RL}$, $f_{RG}$ represent load curve and grip force of the giver and receiver, respectively.
• Figure 3: LSTM Neural Network
• Figure 4: Questionnaire Results
• Figure 5: Setup of the Experiment