Research on Steel Pipe Recognition and Grasping Method for Humanoid Robots

Le résumé fourni par la source

Abstract With the advancement of technology, research on humanoid robots has rapidly expanded. To address the challenge of regular object grasping in assembly scenarios, this paper proposes a 6-degree-of-freedom (6DoF) grasping method for regular objects tailored to humanoid robots. The method integrates semantic segmentation, depth imaging, and position prediction to obtain the 3D position of a target object, which is then used to design an appropriate grasping posture for the dexterous hand. First, the YOLOv8n-seg model is employed to detect and segment a steel pipe, and the depth image is combined with this segmented image to estimate the object’s 3D position using the FoundationPose model. Second, based on hand-eye calibration results and internal coordinate transformations of the robot, the gripping position of the robotic arm is calculated, and corresponding control commands are issued to execute the grasping task. Several strategies, such as constraining the grasping axis to remain parallel to the horizontal plane, are implemented to enhance the stability of the grasping process. Experimental results demonstrate that the proposed method enables the robot to achieve stable and reliable grasping across various pipe positions and orientations.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.