Human-Robot Shared Visual Servoing Based on Game Theory

Abstract

Human-robot shared visual servoing systems can combine the precise control ability of the robot and the human decision-making ability. However, integrating human input into such systems remains a challenging endeavor. This work studies the robot visual servoing control system in the human-robot shared environment and proposes a human-robot shared visual servoing framework based on game theory. Game theory is used to model the relationship between humans and robots. According to the observation of human input, the human intention is adaptively estimated using a radial basis function neural network (RBFNN), and the robot control objective is dynamically adjusted to realize human-robot coordination. The Lyapunov theory is used to prove the stability of the system. Experiments are conducted to verify the effectiveness of the proposed method.