Collision-free Motion Planning for Human-Robot Collaborative Safety under Cartesian Constraints

• Main Authors: Chen, Jen-Hao, 陳人豪
• Other Authors: Song, Kai-Tai
• Format: Others
• Language: zh-TW
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/etvc43

碩士 === 國立交通大學 === 電控工程研究所 === 106 === This thesis presents a real-time motion planning and control design of a robot arm for human-robot collaborative safety. Multiple KinectV2 depth camera are utilized to model and track dynamic obstacles (e.g. Humans and objects) inside the robot workspace. Depth images are applied to generate the point cloud of segmented objects in the environment. A K-nearest neighbor (KNN) searching algorithm is used to cluster and find the closest point from the obstacle point cloud to the robot. Then, a Kalman filter is applied to estimate the obstacle position and velocity. For the collision avoidance behavior, the repulsive force is generated for the robot end effector by calculating the minimum distance between the robot and moving obstacles. Moreover, a novel collision-free motion planning method is proposed not only to keep robot body from colliding with objects but also to preserve the execution of robot’s original task under the Cartesian constraint of the environment. Practical experiments show that the 6-DOF robot arm can effectively avoid obstacles in a constrained environment and complete the original task.