Safe Human-to-Humanoid Motion Imitation Using Control Barrier Functions

TL;DR

This paper introduces a vision-based, real-time motion imitation framework for humanoid robots that ensures safety by preventing collisions through a Control Barrier Function layer, validated in simulations.

Contribution

It combines vision-based human motion capture with a CBF-based safety layer to enable collision-free, real-time human-to-humanoid motion imitation.

Findings

Effective collision avoidance demonstrated in simulations

Real-time motion imitation achieved with safety guarantees

Framework successfully filters imitation commands to prevent collisions

Abstract

Ensuring operational safety is critical for human-to-humanoid motion imitation. This paper presents a vision-based framework that enables a humanoid robot to imitate human movements while avoiding collisions. Human skeletal keypoints are captured by a single camera and converted into joint angles for motion retargeting. Safety is enforced through a Control Barrier Function (CBF) layer formulated as a Quadratic Program (QP), which filters imitation commands to prevent both self-collisions and human-robot collisions. Simulation results validate the effectiveness of the proposed framework for real-time collision-aware motion imitation.