Identification of Effective Motion Primitives for Ground Vehicles

Understanding the kinematics of a ground robotis essential for efficient navigation. Based on the kinematicmodel of a robot, its full motion capabilities can be repre-sented by theoretical motion primitives. However, dependingon the environment and/or human preferences, not all of thosetheoretical motion primitives are desirable and/or achievable.This work presents a method to identify effective motionprimitives (eMP) from continuous trajectories for autonomousground robots. The pipeline efficiently performs segmentation,representation and reconstruction of the motion primitives,using initial human-driving behaviour as a guide to createa motion primitive library. Hence, this strategy incorporateshow the environment affects the robot operation regardingaccelerations, speed, braking, and steering behaviours.The method is thoroughly tested on an autonomous car-likeelectric vehicle, and the results show excellent generalisationof the theoretical motion primitive distribution to real vehicle.The experiments are carried out on large site with very diversecharacteristics, illustrating the applicability of the method