Learning-based Autonomous Oversteer Control and Collision Avoidance
On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic
Abstract (arXiv)
Oversteer, wherein a vehicle's rear tires lose traction and induce unintentional excessive yaw, poses critical safety challenges. Failing to control oversteer often leads to severe traffic accidents. Although recent autonomous driving efforts have attempted to handle oversteer through stabilizing maneuvers, the majority rely on expert-defined trajectories or assume obstacle-free environments, limiting real-world applicability. This paper introduces a novel end-to-end (E2E) autonomous driving approach that tackles oversteer control and collision avoidance simultaneously. Existing E2E techniques, including Imitation Learning (IL), Reinforcement Learning (RL), and Hybrid Learning (HL), generally require near-optimal demonstrations or extensive experience. Yet even skilled human drivers struggle to provide perfect demonstrations under oversteer, and high transition variance hinders accumulating sufficient data. Hence, we present Q-Compared Soft Actor-Critic (QC-SAC), a new HL algorithm that effectively learns from suboptimal demonstration data and adapts rapidly to new conditions. To evaluate QC-SAC, we introduce a benchmark inspired by real-world driver training: a vehicle encounters sudden oversteer on a slippery surface and must avoid randomly placed obstacles ahead. Experimental results show QC-SAC attains near-optimal driving policies, significantly surpassing state-of-the-art IL, RL, and HL baselines. Our method demonstrates the world's first safe autonomous oversteer control with obstacle avoidance.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 34 references that are in the map. First posted on arXiv 21 May 2025.
Builds on
13 of 34 references.
References · 13
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
- 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
- 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 715
- 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 129
- 2023Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Surveycited by 103
- 2018Reinforcement Learning from Imperfect Demonstrationscited by 75
- 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 61
- 2023Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priorscited by 36
- 2021Residual Reinforcement Learning from Demonstrationscited by 31
- 2020High-speed Autonomous Drifting with Deep Reinforcement Learningcited by 24
- 2021Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learningcited by 21
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2020Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving
- 2021Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving
- 2023Boosting Offline Reinforcement Learning for Autonomous Driving with Hierarchical Latent Skills
- 2025Bootstrapping Reinforcement Learning with Sub-optimal Policies for Autonomous Driving
- 2023Learning Realistic Traffic Agents in Closed-loop
- 2025Advanced Longitudinal Control and Collision Avoidance for High-Risk Edge Cases in Autonomous Driving
- 2025RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies
- 2024Efficient and Generalized end-to-end Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations