Motion Planning for Nonholonomic Vehicles with Space Exploration Guided Heuristic Search

摘要

The development of the modern sensing, actuation, communication, and computation technology unfolds a promising future of mobile robots, especially for intelligent automobiles.Motion planning is one of the most important software components in these autonomous systems.It is responsible for a motion strategy or trajectory while considering the robot kinematic model, the prior knowledge of the environment, the real-time perception, and domain specific rules.Particularly, a motion planning problem for an autonomous vehicle is beyond a theoretical problem of finding an executable collision-free trajectory.An intelligent vehicle should behave rationally in traffic, which includes following a global route from the navigation, adapting local behaviors according to the circumstances, obeying traffic rules, and respecting the convenience of the human traffic participants.Furthermore, the driving tasks are highly diverse, so specific motion planning methods are required for different maneuver types.In this case, an intelligent agent should be able to process all kinds of information with domain knowledge, select the most efficient algorithm for a specific task, and integrate them seamlessly in a system.In this dissertation, a Space Exploration Guided Heuristic Search (SEHS) method is introduced as a base framework for mobile robot motion planning.Several extensions of SEHS such as Orientation-Aware Space Exploration Guided Heuristic Search (OS-EHS) and Space Time Exploration Guided Heuristic Search (STEHS) are developed for specific autonomous driving scenarios.They can be integrated in a hierarchical planning architecture with a high-level task planning in order to process information in different layers and achieve online motion planning for mobile robots, especially autonomous vehicles.The major part of the research work in this thesis is done in fortiss from 2012 to 2015, where is a nice place to work as it provides close links to the university as well as the practical world.The mission of transferring the innovative technology from academic to industry gives me a great chance to apply my research result.First of all, I would like to thank Prof. Dr. Alois Knoll for the precious opportunity to study the exciting topic of robot motion planning.His vision gave much valuable advice to my research work.