Abstract
Reinforcement learning-based approaches are widely studied in the literature for solving different control tasks for Connected and Autonomous Vehicles, from which this paper deals with the problem of lateral control of a dynamic nonlinear vehicle model, performing the task of lane-keeping. In this area, the appropriate formulation of the goals and environment information is crucial, for which the research outlines the importance of lookahead information, enabling to accomplish maneuvers with complex trajectories. Another critical part is the real-time manner of the problem. On the one hand, optimization or search based methods, such as the presented Monte Carlo Tree Search method, can solve the problem with the trade-off of high numerical complexity. On the other hand, single Reinforcement Learning agents struggle to learn these tasks with high performance, though they have the advantage that after the training process, they can operate in a real-time manner. Two planning agent structures are proposed in the paper to resolve this duality, where the machine learning agents aid the tree search algorithm. As a result, the combined solution provides high performance and low computational needs.
Highlights
Deep Learning (DL) has gained tremendous interest in the field of vehicle control and motion planning in general thanks to the success of DL in other fields where the advantages of ConvolutionNeural Networks (CNN) are heavily utilized such as semantic segmentation, scene understanding, object detection, and recognition [1,2]
The results showed that the steering signal created by the neural network is noisy, which suggests the use of Recurrent Neural Networks that has a memory of earlier inputs
The trained network is tested in simulation and the results show that it can keep the required time distance accurately, but the control signal always oscillates, which is uncomfortable for the passengers
Summary
Deep Learning (DL) has gained tremendous interest in the field of vehicle control and motion planning in general thanks to the success of DL in other fields where the advantages of ConvolutionNeural Networks (CNN) are heavily utilized such as semantic segmentation, scene understanding, object detection, and recognition [1,2]. The early concepts for designing autonomous functions used rule-based systems where the parameters of the conditions are tuned over tests. This type of system has limitations because it is hard to cover all the rare events in tests that can happen in the real world. Deep Learning techniques feature adaptation and self-tuning. These techniques are able to generalize behaviors for unseen cases. These characteristics make DL an obvious choice for solving vehicle control problems. The second is a longitudinal motion control, which is dedicated to managing the brake and throttle pedals to hold speed, maintaining
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
