Race to Recovery: Designing Advanced Safety Systems for Autonomous Driving via Learning Autonomous Racing

Summary

Abstract Summary

Vehicles that lose control at the handling limit through icing, hydroplaning, or an abrupt evasive maneuver fall outside the operating envelope of production safety systems such as electronic stability control, which focus on preventing instability rather than recovering from it. Expert drivers regain authority in these conditions by drifting. Existing autonomous recovery approaches are validated on idealized scenarios, define "recovered" states empirically and inconsistently, or rely on offline-planned trajectories rather than acting online. We address these gaps by first training a racing policy with reinforcement learning that learns drifting as a time-optimal maneuver, then adapting it to recovery through continued training with a minimum-time reward. We define recovery relative to a phase-plane-grounded stable equilibrium and introduce Gym-Khana for controller training and evaluation. Across 294 initial loss-of-control states, the transferred policy improves recovery by 186.8% over a Stanley path tracker and outperforms both a nonlinear model predictive controller and a recovery-only policy trained from scratch, while also recovering faster on states the baseline can already handle. An ablation shows that racing pretraining, rather than broader initial-state exposure alone, drives this gain. Deployed on a physical 1:10-scale F1TENTH vehicle using system identification, actuator-lag modelling, and domain randomization, the transferred policy outperforms Stanley on every tested loss-of-control state, including recovering 50% of the time from a hard state the baseline never recovers from.

Key Points

Vehicles that lose control at the handling limit through icing, hydroplaning, or an abrupt evasive maneuver fall outside the operating envelope of production safety systems such as electronic stability control, which focus on preventing instability rather than recovering from it.
Expert drivers regain authority in these conditions by drifting
Existing autonomous recovery approaches are validated on idealized scenarios, define "recovered" states empirically and inconsistently, or rely on offline-planned trajectories rather than acting online.
We address these gaps by first training a racing policy with reinforcement learning that learns drifting as a time-optimal maneuver, then adapting it to recovery through continued training with a minimum-time reward.
We define recovery relative to a phase-plane-grounded stable equilibrium and introduce Gym-Khana for controller training and evaluation.

Problem Formulation

Our goal is to solve the control task of returning a vehicle that has lost control while tracking a straight reference path, such as a driving lane, to a safe operating regime. Formulating this task requires two components: a vehicle and tire model, which we describe in Section III-A , and a rigorous definition of the recovered state, described in Section III-B .

The recovery task requires a dynamics model that represents the vehicle at a suitable level of complexity.

Problem Formulation — Race to Recovery: Designing Advanced Safety Systems for Autonomous Driving via Learning Autonomous Racing — Fig. 2: Sideslip vs. yaw-rate phase plane of Hindiyeh’s two-state single-track model [ 2 ] .

Recovery Controller Design

1. Racing pretraining 120 M steps, $\times$64 envs 50 M steps, $\times$64 envs 3.

Recovery fine-tuning Actor $\pi_{\text{race}}$ Critic $V_{\phi}$ $\mathbf{o}_{t}$ $\mathbf{a}_{t}$ $r_{t}$ progress $\hat{A}_{t}$ $\mathcal{U}$ $\mathcal{R}$ $\mathbf{z}_{0}\in\mathcal{U}$ $\mathbf{z}_{T}\in\mathcal{R}$ Actor $\pi_{\text{race}\to\text{rec}}$ Critic $V_{\phi^{\prime}}$ $\mathbf{o}_{t}$ $\mathbf{a}_{t}$ $r_{t}$ reach $\mathcal{R}$ $\hat{A}_{t}$ 2.

Recovery Controller Design — Race to Recovery: Designing Advanced Safety Systems for Autonomous Driving via Learning Autonomous Racing — Fig. 3: Overview of the approach. 1. A policy is trained with proximal policy optimization (PPO) to race on the Drift track and its mirror image, where drifting emerges as the time-optimal technique. 2. Its actor $\pi_{\text{race}}$ is transferred unchanged to the recovery task, and its critic is reinitialized. 3. Training continues under the recovery reward, which drives the vehicle from an unrecovered state in $\mathcal{U}$ into the recovered set $\mathcal{R}$; the two tasks share one vehicle model, observation and action space, so only the reward changes between them. 4. The resulting $\pi_{\text{race}\to\text{rec}}$ is deployed on the physical F1TENTH vehicle. Before deployment, system identification, actuator-lag modelling and domain randomization adapt the simulator to the vehicle, and the controller is retrained on it from racing onwards (Sections IV-D and VI ). Every image is taken from our experiments: the racing and recovery panels are rollouts of the trained policies in simulation, the bottom-left plot is the loss ( 6 ) of the identification run across four parallel covariance matrix adaptation evolution strategy (CMA-ES) workers, and the bottom-right photo overlays frames of a recovery run on the physical vehicle. In both recovery panels time runs downwards: the shading marks $\mathcal{U}$ (red) and its complement $\mathcal{R}$ (green), the dotted line the initial state $\mathbf{z}_{0}$ where the policy takes over, and the solid line the first recovered state $\mathbf{z}_{T}$.

Simulation Experiments

This section evaluates the recovery controllers in simulation, first establishing the evaluation metrics and experimental protocol, and then comparing the proposed controller against classical baselines and alternative training strategies. We choose two classical control methods as baselines: a geometric path-tracking Stanley controller and a nonlinear MPC formulation.

Hardware Validation

Deploying the recovery controller of Section IV-C on a physical vehicle is the most demanding validation of the approach, as physical testing exposes limitations that simulation does not: vehicle parameter mismatch, actuator delays, and state observation noise.

The results of Section V use the nominal vehicle parameters of Section IV-B ; here they are replaced by parameters identified on the physical vehicle as in Section IV-D , and the controller is retrained on them.

Hardware Validation — Race to Recovery: Designing Advanced Safety Systems for Autonomous Driving via Learning Autonomous Racing — Fig. 5: The modified F1TENTH hardware platform from varying angles, showing custom tire covers, lower ride height, harder shock absorbers, and stock F1TENTH hardware components.

Sources and Demonstrations

Figures are reproduced from Ilie et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.