Force-Based Robotic Imitation Learning: A Two-Phase Approach for Construction Assembly Tasks

2025-01-24

AI Summary

Existing vision- or pose-based imitation learning methods struggle to generalize to contact-sensitive tasks in construction assembly—such as welding and pipe insertion—that demand high-precision force control. To address this, we propose a two-stage force-based imitation learning framework. In the first stage, real-time human–robot force feedback is acquired via ROS-Sharp, and high-fidelity force interaction data are generated through virtual–physical co-simulation. In the second stage, a generative model maps raw force signals to robust motion commands. This work introduces the first “force-perception → force-driven” generative imitation paradigm, overcoming the fundamental limitation of conventional approaches that neglect explicit force modeling. Experiments demonstrate significant improvements in task success rate and execution speed, alongside enhanced generalization and reliability of learned policies under real-world force interactions.

Technology Category

• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The drive for efficiency and safety in construction has boosted the role of robotics and automation. However, complex tasks like welding and pipe insertion pose challenges due to their need for precise adaptive force control, which complicates robotic training. This paper proposes a two-phase system to improve robot learning, integrating human-derived force feedback. The first phase captures real-time data from operators using a robot arm linked with a virtual simulator via ROS-Sharp. In the second phase, this feedback is converted into robotic motion instructions, using a generative approach to incorporate force feedback into the learning process. This method's effectiveness is demonstrated through improved task completion times and success rates. The framework simulates realistic force-based interactions, enhancing the training data's quality for precise robotic manipulation in construction tasks.

Problem

• Robotics
• Force Control
• Assembly Tasks

Innovation

• Force Imitation Learning
• Fine-grained Assembly Tasks
• Robot Precision Enhancement