我所李丹勇老师课题组完成的论文《Research on Motion Control Technology of Quadruped Robot Arm Based on Visual Analysis》于2025-04在《International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)》正式发表。论文摘要如下：
Abstract: To address the issues of limited working range, weak interactivity, and low safety in robotic arm, a collaborative quadruped robot with an attached robotic arm is designed and implemented. Using the door-opening task as an example, this system covers target recognition and measurement, kinematic modeling and path planning, collision detection, and collaborative control. The Mask-RCNN algorithm is employed for precise identification of the door handle, and a depth camera is used to measure the spatial distance to the door handle. A torque observer based on generalized momentum is designed for collision detection of the robotic arm. Based on the coordinates of the target object and the observed external torque, a motion control strategy for the robotic arm to open the door is planned. Finally, a collaborative control logic is established between the quadruped robot and the robotic arm, enabling them to work together to complete the door-opening task while ensuring safety.
引用信息：Shuaibing Yao, Danyong Li, Tong Zhang, Mingxuan Ma. Research on Motion Control Technology of Quadruped Robot Arm Based on Visual Analysis. International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI), 2025-04. DOI: 10.1109/ricai64321.2024.10911560