Adaptive Compensation for Robotic Joint Failures Using Partially Observable Reinforcement Learning

TL;DR

This paper presents a reinforcement learning framework that enables a robotic manipulator to adaptively compensate for joint failures, significantly improving task success rates in unpredictable failure scenarios.

Contribution

It introduces a novel RL-based approach formulated as a POMDP to handle joint malfunctions, outperforming traditional control methods in robustness and adaptability.

Findings

Achieved a 93.6% success rate in tasks with joint failures.

Demonstrated effectiveness in both seen and unseen failure scenarios.

Outperformed inverse kinematics-based control methods.

Abstract

Robotic manipulators are widely used in various industries for complex and repetitive tasks. However, they remain vulnerable to unexpected hardware failures. In this study, we address the challenge of enabling a robotic manipulator to complete tasks despite joint malfunctions. Specifically, we develop a reinforcement learning (RL) framework to adaptively compensate for a non-functional joint during task execution. Our experimental platform is the Franka robot with 7 degrees of freedom (DOFs). We formulate the problem as a partially observable Markov decision process (POMDP), where the robot is trained under various joint failure conditions and tested in both seen and unseen scenarios. We consider scenarios where a joint is permanently broken and where it functions intermittently. Additionally, we demonstrate the effectiveness of our approach by comparing it with traditional inverse kinematics-based control methods. The results show that the RL algorithm enables the robot to successfully complete tasks even with joint failures, achieving a high success rate with an average rate of 93.6%. This showcases its robustness and adaptability. Our findings highlight the potential of RL to enhance the resilience and reliability of robotic systems, making them better suited for unpredictable environments. All related codes and models are published online.