Learning-based Autonomous Oversteer Control and Collision Avoidance
Organizations: CCS Graduate School of Mobility, Korea Advanced Institute of Science and Technology, Daejeon, Korea, 34051
Abstract
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 the accumulation of sufficient data. Hence, we present Q-Compared Soft Actor-Critic (QC-SAC), a new HL algorithm that effectively learns from immature 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 that QC-SAC attains near-optimal driving policies, significantly surpassing state-of-the-art IL, RL, and HL baselines. Hardware-in-the-loop simulation (HILS) validation with physical steering hardware further demonstrates that QC-SAC can operate beyond a software-only simulation, providing an intermediate validation step toward real-vehicle implementation. To the best of our knowledge, this is the first work that achieves safe autonomous control of vehicles in oversteer while simultaneously avoiding obstacles.
Figures & tables
| Method | Success Rate | Success | Fail |
|---|---|---|---|
| QC-SAC (Proposed) | 81.8% | 409 | 91 |
| BC-SAC [ 22 ] | 34.6% | 173 | 327 |
| SAC [ 35 ] | 19.0% | 95 | 405 |
| AMP [ 24 ] | 8.6% | 43 | 457 |
| BC | 0.4% | 2 | 498 |
| Parameter | Symbol | Value | Unit |
| Vehicle mass | 1600.0 | kg | |
| Center of gravity position | m | ||
| Inertia tensor about CG | kg m 2 | ||
| Gyration radius | m | ||
| Front/rear axle load | kg | ||
| Wheelbase | 2.975 | m |
| Parameter | Success Rate | Deviation from Nominal |
|---|---|---|
| ( ) | 81% | |
| ( ) | 74% | |
| ( ) | 37% | |
| ( ) | 82% | |
| ( ) | 86% | |
| ( ) | 69% |
| Setting | Success Rate | Deviation from Nominal | |||
|---|---|---|---|---|---|
| low | 0.4 | 0.2 | 0.2 | 78% | |
| high | 1.2 | 0.2 | 0.2 | 65% | |
| low | 0.8 | 0.1 | 0.2 | 59% | |
| high | 0.8 | 0.3 | 0.2 | 73% | |
| low | 0.8 | 0.2 | 0.1 | 38% | |
| high | 0.8 | 0.2 | 0.3 | 66% |
End-to-End Autonomous Driving
End-to-end autonomous driving learns to turn sensor observations and driving context into vehicle actions or trajectories.
See all 246 papers