Contrastive Forward Prediction Reinforcement Learning for Adaptive Fault-Tolerant Legged Robots

Yangqing Fu, Yang Zhang, Qiyue Yang, Liyun Yan, Zhanxiang Cao, Yue Gao

Keywords: Legged robot locomotion, Fault tolerance control, Deep Reinforcement learning

TL;DR: This work proposes a reinforcement learning framework that enhances fault-tolerant control in legged robots by integrating forward prediction and error-based feedback, enabling robust and adaptive locomotion under joint damage.

Abstract: In complex environments, adaptive and fault-tolerant capabilities are essential for legged robot locomotion. To address this challenge, this study proposes a reinforcement learning framework that integrates contrastive learning with forward prediction to achieve fault-tolerant locomotion for legged robots. This framework constructs a forward prediction model with contrastive learning, incorporating a comparator and a forward model. The forward model predicts the robot's subsequent state, and the comparator compares these predictions with actual states to generate critical prediction errors. These errors are systematically integrated into the controller, facilitating the continuous adjustment and refinement of control signals.Experiments on quadruped robots across different terrains and various joint damage scenarios have verified the effectiveness of our method, especially the functions of the comparator and the forward model. Furthermore, robots can adapt to locked joints without prior training, demonstrating zero-shot transfer capability. Finally, the proposed method demonstrates universal applicability to both quadruped and hexapod robots, highlighting its potential for broader applications in legged robotics.

Submission Number: 495