Research on Sensor Switching and Path Optimization of Disinfection Robots Based on Reinforcement Learning

This study proposes a reinforcement learning-based system for intelligent sensor switching and path optimization to enhance the performance of disinfection robots in dynamic environments. By combining camera and radar sensors, the system adaptively selects the optimal sensor based on factors like lighting, weather, and obstacles, optimizing the robot's path for efficient task completion. Using Q-learning for sensor selection and reinforcement learning for path optimization, the robot autonomously adjusts to environmental changes, improving perception, reducing energy consumption, and increasing execution efficiency. The experimental results indicate that this method provides certain value for the development of intelligent decision-making systems for robots.