This is the official implementation of IROS2025 papaer "Human-Robot Shared Visual Servoing Based on Game Theory" created by Zitai Fang, Chong Cao, and Lijun Han.
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.
The original paper can be found in "paper/paper.pdf" in this repository.
The supplementary item includes a video, which can be found in "video/video.mp4" in this repository. This Mp4 video file an overview of the experimental setup, the outline of our proposed method, and the experimental results. The entire video is divided into two experiments. In Experiment I, we show the visual servoing results under three control modes. We also analyze our method in detail. In Experiment II, we show the comparative results of our proposed "dynamic role adaptation" control mode and "fixed role" control mode. Player Information: Any Mp4 player (VLC, Windows Media Player, etc.) is sufficient for viewing.
All rights under copyright has been assigned to The Institute of Electrical and Electronics Engineers, Incorporated (the "IEEE") including:
- Paper
- Supplemental Items