Feature selection based on reinforcement learning and hazard state classiffcation for magnetic adhesion wall-climbing robots

摘要

Abstract Magnetic adhesion tracked wall-climbing robots face potential risks of overturning during high-altitude operations, making their stability crucial for ensuring safety. This study presents a dynamic feature selection method based on reinforcement learning of Proximal Policy Optimization (PPO), combined with typical machine learning models, aimed at improving the classification accuracy of hazardous states under complex operating conditions. Firstly, this work innovatively employs a fiber rod-based MEMS attitude sensor to collect vibration data from the robot and extract high-dimensional feature vectors in both the time and frequency domains. Then a reinforcement learning model is used to dynamically select the optimal subset of characteristics, reducing redundancy of characteristics, and improving classification accuracy. Finally, a CNN-LSTM deep learning model is employed for classification and recognition. Experimental results demonstrate that the proposed method significantly improves the robot’s ability to assess hazardous states across various operational scenarios, providing reliable technical support for robotic safety monitoring.