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

2026-04-13

AI Summary

This work addresses the challenge of self-collisions and human–robot collisions in vision-driven motion imitation for humanoid robots by proposing a real-time safety-aware control framework that integrates Control Barrier Functions (CBFs) with Quadratic Programming (QP). The approach estimates human joint positions from monocular vision, generates target joint commands via motion retargeting, and dynamically adjusts control inputs through an online CBF-QP optimization mechanism to rigorously enforce safety constraints while preserving motion fidelity. Simulation experiments demonstrate that the proposed framework enables high-fidelity, collision-free motion imitation under real-time conditions. To the best of our knowledge, this is the first study to combine CBFs and QP for dynamic obstacle avoidance and safety-critical control in humanoid robot imitation learning.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Vision for Robotics & Autonomous Driving

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

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.

Problem

• motion imitation
• humanoid robot
• collision avoidance
• operational safety
• human-robot interaction

Innovation

• Control Barrier Function
• Humanoid Motion Imitation
• Collision Avoidance
• Quadratic Program
• Vision-based Retargeting