Abstract
<p class="Abstract">The present study focused on vision-based end-to-end reinforcement learning in relation to<strong> </strong>vehicle control problems such as lane following and collision avoidance. The controller policy presented in this paper is able to control a small-scale robot to follow the right-hand lane of a real two-lane road, although its training has only been carried out in a simulation. This model, realised by a simple, convolutional network, relies on images of a forward-facing monocular camera and generates continuous actions that directly control the vehicle. To train this policy, proximal policy optimization was used, and to achieve the generalisation capability required for real performance, domain randomisation was used. A thorough analysis of the trained policy was conducted by measuring multiple performance metrics and comparing these to baselines that rely on other methods. To assess the quality of the simulation-to-reality transfer learning process and the performance of the controller in the real world, simple metrics were measured on a real track and compared with results from a matching simulation. Further analysis was carried out by visualising salient object maps.</p>
Highlights
Reinforcement learning has been used to solve many control and robotics tasks
Bridging the gap between simulation and the real world is an important transfer-learning problem related to reinforcement learning, and it is an unresolved task for researchers
Almási et al [7] used reinforcement learning to solve lane following in the Duckietown environment, but their work differs from the present study in the use of an off-policy reinforcement learning algorithm (deep Q-networks (DQNs) [8]); in this study an on-policy algorithm is used, which achieves significantly better sample efficiency and shorter training times
Summary
Reinforcement learning has been used to solve many control and robotics tasks. only a handful of papers have been published that apply this technique to end-to-end driving [1]-[7], and even fewer studies have focused on reinforcement learningbased driving, trained only in simulations and applied to real-world problems. Almási et al [7] used reinforcement learning to solve lane following in the Duckietown environment, but their work differs from the present study in the use of an off-policy reinforcement learning algorithm (deep Q-networks (DQNs) [8]); in this study an on-policy algorithm (proximal policy optimization [9]) is used, which achieves significantly better sample efficiency and shorter training times Another important difference is that Almási et al applied hand-crafted colour threshold-based segmentation to the input images, whereas the method presented here takes the ‘raw’ images as inputs, which allows for a more robust real performance
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.
