J Zhao, T Qu, F Xu - IFAC-PapersOnLine, 2020 - Elsevier
… Abstract: Autonomous driving has been the trend. In this paper, a DeepReinforcement … making and interaction between vehicles on highwaydriving. To avoid the overestimate action …
… deepreinforcement learning system for automated driving. … safety rule based on common driving practice that ensure a … that learns safety patterns from driving data. Specifically, the …
H Wang, S Yuan, M Guo, X Li… - Proceedings of the …, 2021 - journals.sagepub.com
… We propose a DeepReinforcement Learning-based approach in this work for merging decisions of AV with dynamic constraints and reasoning in moderate traffic through highway …
J Liao, T Liu, X Tang, X Mu, B Huang, D Cao - IEEE Access, 2020 - ieeexplore.ieee.org
… This following organization of this article is given as follows: the highwaydriving environment and the control modules of the ego and surrounding vehicles are described in Section II. …
… [21] present a framework to learn costmaps for autonomous driving using IRL directly from sensor data. [22] present an IRL approach in a simple highwaydriving scenario on a custom …
DC Selvaraj, S Hegde, N Amati, F Deflorio… - Applied Sciences, 2023 - mdpi.com
… , we focus on DeepReinforcement Learning (DRL), which incorporates deep neural networks in … We have divided our scenarios into two distinct traffic conditions: highway and urban. In …
S Aradi, T Becsi, P Gaspar - 2018 IEEE Conference on Control …, 2018 - ieeexplore.ieee.org
… The fully automated highwaydriving (AHD) has been researched by the control engineers … Chan, “Formulation of deepreinforcement learning architecture toward autonomous driving …
… for self-driving cars in a multi-lane, single-agent setting. The proposed approach utilizes deepreinforcement … Simulations from a wellknown self-driving car simulator demonstrate the …
L Schester, LE Ortiz - 2021 IEEE Intelligent Vehicles …, 2021 - ieeexplore.ieee.org
… multi-agent reinforcement-learning (MARL) approach to study the problem of highway on-ramp … We exploit recent advances on deepreinforcement learning (deep RL) to train controllers …