arXiv:2606. 31106v1 Announce Type: cross Abstract: Large-scale datasets and fast simulators have enabled improvements in driving policies that appear safe and robust, yet strong performance in nominal scenarios can still mask flawed reasoning and unsafe heuristics.
arXiv:2609.39995v2 Announce Type: new Abstract: Diffusion planners exhibit strong capabilities in generating multimodal trajectories. However, existing methods primarily rely on expert demonstrations...
arXiv:2607. 18637v1 Announce Type: cross Abstract: Generating closed-loop traffic scenarios that are both realistic and controllable is crucial for evaluating autonomous driving systems, especially under rare safety-critical interactions.
The paper introduces Endpoint-Constrained Optimization (ECO), a lightweight postprocessing layer that corrects intermediate waypoints of end-to-end driving policies while preserving the predicted endpoint. ECO does not require maps, privileged simulator state, or additional training, and can be applied to a wide range of waypoint-emitting policies. Experiments on two closed-loop simulators show that ECO significantly improves closed-loop performance, achieving top results in the HUGSIM Closed-Loop Driving Challenge and boosting scene scores on AlpaSim.
arXiv:2607. 13028v1 Announce Type: cross Abstract: Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long tail that logged data rarely contains.
arXiv:2608. 10403v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient exposure to safety-critical driving scenes.
arXiv:2607. 07844v1 Announce Type: cross Abstract: While closed-loop motion planners trained on large-scale, object-level datasets, e.
SCAPE is a scenario‑conditioned simulation‑augmented policy evaluation framework that predicts real‑world policy performance for specific scenarios using limited paired simulation‑and‑real samples and extensive simulation rollouts. It corrects sim‑to‑real bias in simulation labels before training the prediction model and calibrates prediction uncertainty via conformal prediction. Experiments on autonomous driving and quadruped velocity tracking show SCAPE reduces scenario‑level prediction error, improves testing sample efficiency, narrows calibrated prediction intervals, and generalizes better to out‑of‑distribution scenarios, enabling fine‑grained deployment strategies.
arXiv:2608.22549v1 Announce Type: new Abstract: Batched simulators for autonomous driving have recently enabled training reinforcement learning (RL) agents at scale, encompassing thousands of traffic...
CAR‑VLA is a Vision‑Language‑Action model for autonomous driving that jointly considers scene complexity and dynamic risk to determine reasoning depth, urgency, and focus. It maps four complexity‑risk categories to three reasoning modes—Fast Intuition, Slow Thinking, and Reflex Response—each tailored to different driving scenarios. The model is trained via progressive supervised learning and reinforcement learning, achieving competitive performance on NAVSIM and Navhard benchmarks and demonstrating risk‑aware reasoning in high‑risk scenarios.
OPTED is a method for on‑policy fine‑tuning of end‑to‑end driving models that separates reinforcement learning from the policy update. A privileged teacher trained with RL on vectorized inputs (HD‑maps and bounding boxes) supervises the pre‑trained student during closed‑loop post‑training. Applied to the camera‑based models TransFuser and VaVAM in AlpaSim, OPTED boosts driving scores by 1.6× and 9.5×, respectively, while requiring roughly three orders of magnitude fewer simulator interactions than direct RL post‑training.
arXiv:2607. 10630v1 Announce Type: cross Abstract: Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data.
arXiv:2608. 19425v1 Announce Type: cross Abstract: Reliable performance evaluation is a central bottleneck for deploying robot-learning policies in real-world conditions.