Impact of Static Friction on Sim2Real in Robotic Reinforcement Learning

2025-03-03

AI Summary

In Sim2Real transfer, static friction is often neglected in domain randomization, leading to severe performance degradation in real-world deployment. This work first systematically identifies anomalously high static friction torques at robotic joints—a previously underappreciated factor. To address this, we propose a static-friction-aware domain randomization framework: leveraging control-theoretic joint modeling and parameter identification, we integrate Actuator Net with Rapid Motor Adaptation (RMA) to construct a learnable static friction model, and design an enhanced randomization strategy that reduces learning complexity. Experiments demonstrate that our method significantly outperforms conventional domain randomization and Actuator Net on challenging terrains such as stairs. Post-transfer, robots achieve faster adaptation and superior overall locomotion performance. This work establishes a new paradigm for robust Sim2Real transfer in friction-sensitive scenarios.

Technology Category

• Intelligent Robots: Manipulation
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

In robotic reinforcement learning, the Sim2Real gap remains a critical challenge. However, the impact of Static friction on Sim2Real has been underexplored. Conventional domain randomization methods typically exclude Static friction from their parameter space. In our robotic reinforcement learning task, such conventional domain randomization approaches resulted in significantly underperforming real-world models. To address this Sim2Real challenge, we employed Actuator Net as an alternative to conventional domain randomization. While this method enabled successful transfer to flat-ground locomotion, it failed on complex terrains like stairs. To further investigate physical parameters affecting Sim2Real in robotic joints, we developed a control-theoretic joint model and performed systematic parameter identification. Our analysis revealed unexpectedly high friction-torque ratios in our robotic joints. To mitigate its impact, we implemented Static friction-aware domain randomization for Sim2Real. Recognizing the increased training difficulty introduced by friction modeling, we proposed a simple and novel solution to reduce learning complexity. To validate this approach, we conducted comprehensive Sim2Sim and Sim2Real experiments comparing three methods: conventional domain randomization (without Static friction), Actuator Net, and our Static friction-aware domain randomization. All experiments utilized the Rapid Motor Adaptation (RMA) algorithm. Results demonstrated that our method achieved superior adaptive capabilities and overall performance.

Problem

• Impact of static friction on Sim2Real transfer in robotics.
• Conventional domain randomization excludes static friction, reducing real-world performance.
• Proposed static friction-aware domain randomization improves adaptive capabilities and performance.

Innovation

• Implemented Static friction-aware domain randomization
• Developed control-theoretic joint model for parameter identification
• Proposed novel solution to reduce learning complexity