Abstract
In automatic parking motion planning, multi-objective optimization including safety, comfort, parking efficiency, and final parking performance should be considered. Most of the current research relies on the parking data from expert drivers or prior knowledge of humans. However, it is challenging to obtain a large amount of high-quality expert drivers’ data. Furthermore, expert drivers’ data or prior knowledge of humans does not guarantee an optimal multi-objective parking performance. In this article, we propose a model-based reinforcement learning method that learns parking policy of the data, by executing the data generation, data evaluation, and training network, iteratively. The trained network is used to guide the data generation cycle in the subsequent iteration. Based on this proposed method, we can get rid of human experience largely and learn parking strategies autonomously and quickly. The learned strategies ensure the multi-objective optimality of above requirements in the parking process. First, an environment model that approximates the actual environment is established, and the learning efficiency is accelerated through the simulated interaction between the agent and the environment model. To make the system independent of expert data or prior knowledge, a data generation algorithm combining Monte Carlo Tree Search (MCTS) and longitudinal and lateral policies is proposed. Then, to meet the multi-objective optimal demands mentioned above, a reward function is constructed to evaluate and filter the parking data. Finally, a neural network is used to learn the parking strategy from the filtered data. From the real vehicle test benchmarked with a mass-produced parking system, the proposed method is found to achieve better parking efficiency and lower requirements for start parking posture, thereby verifying the algorithm’s superiority.
Highlights
The growth of mobile travel demand and the shortage of road capacity have caused severe traffic and environmental problems due to the continuous increase of car ownership
Comprehensive consideration of safety, comfort, parking efficiency, and final parking posture to achieve parking motion planning is of great significance for the future development of shared vehicles
Current research on parking motion planning can be divided into several methods, such as expert drivers’ parking data-based method, human prior knowledge-based method, and reinforcement learning-based method
Summary
The growth of mobile travel demand and the shortage of road capacity have caused severe traffic and environmental problems due to the continuous increase of car ownership. The demand for the time-sharing electric vehicle is increasing, as it is eco-friendly, intensive, and efficient. The need for wireless charging after shared electric vehicle parking increases the requirements concerning the vehicle’s final parking posture. Comprehensive consideration of safety, comfort, parking efficiency, and final parking posture to achieve parking motion planning is of great significance for the future development of shared vehicles. A typical automatic parking system, as shown, includes key technologies such as parking slot detection, motion planning (or path planning and tracking), ego-vehicle’s posture estimation, and chassis control. Motion planning is an intermediate module for environment perception and chassis control, which plans vehicle control commands based on real-time vehicle information and parking space information. J. Zhang et al.: Reinforcement Learning-Based Motion Planning for Automatic Parking System chassis control module for execution. Current research on parking motion planning can be divided into several methods, such as expert drivers’ parking data-based method, human prior knowledge-based method, and reinforcement learning-based method
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.