Improvement of visual servo system of industrial robot based on sliding mode control and deep reinforcement learning

Abstract

Visual servo system is more and more widely used in the field of industrial robots because it allows robots to sense external signals through sensors to convey control commands to themselves and complete tasks. However, the traditional visual servo has many limitations in the design of controller and image feature extraction, such as insufficient robustness and image extraction accuracy. This research focuses on the optimization of controller and image feature extraction, which can improve the overall performance and autonomy of the system by combining sliding mode control and Convolutional Neural Network (CNN). Sliding mode control performs well in terms of robustness and response speed, while CNN has excellent ability for image feature extraction. The research results show that the combination of the two and the visual servo has better performance in a variety of application scenarios, so this is also the development direction that industrial robots can adopt in the future.