Collision-free trajectory generation on assistive robot Neptune

This work demonstrates the integration of existing open source robotics tools to develop a collision free trajectory generation system for assistive environments and evaluates its performance. Trajectory generation and obstacle avoidance abilities were applied in the Neptune assistive robot developed in our lab. Such abilities are essential for safe operation of the robot in an assistive living environment. The Robot Operating System (ROS) is used as the software framework within which collision-free algorithms are executed. Prior to deploying the code on the Neptune hardware, the kinematics was modeled and simulated. Furthermore, a Kinect sensor was used to gain information about the environment and detect obstacles. Experiments were then performed on the robotic system to demonstrate the obstacle avoidance behavior during trajectory generation between randomly generated and selected end effector poses.