DiDrive introduces a risk‑aware hierarchical diffusion framework for offline reinforcement learning in autonomous driving. It combines a low‑level risk‑gated encoder with a high‑level contextual modulator to filter redundant state information, and a 3DICE policy optimization that reduces out‑of‑distribution overestimation and stabilizes gradients. On the CARLA benchmark, DiDrive outperforms baselines such as IQL, CQL, and Diffusion‑QL, achieving an 85% success rate and a 4295.68 average reward in dense traffic with 60 vehicles.
arXiv:2606. 27766v1 Announce Type: cross Abstract: Offline reinforcement learning enables policy learning from fixed datasets without additional environment interaction, making it appealing for safety-critical applications where online exploration is costly or unsafe.
arXiv:2606. 06423v1 Announce Type: cross Abstract: Safety-critical traffic scenario generation is essential for evaluating autonomous driving systems under rare but high-risk interactions.
The paper introduces WM‑RMoE, a World Model‑based Risk‑aware Mixture‑of‑Experts framework for autonomous overtaking. It uses a learned latent dynamics model to perform multi‑step rollouts, evaluating cumulative risk at the trajectory level, and employs a hierarchical gating mechanism to coordinate long‑, short‑horizon, and rule‑based safety experts. A Gaussian Mixture Model preserves multimodal maneuver branches, improving robustness and preventing behavioral averaging, leading to better safety compliance, decision stability, and generalization in experiments.
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. 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.
arXiv:2609.39995v2 Announce Type: new Abstract: Diffusion planners exhibit strong capabilities in generating multimodal trajectories. However, existing methods primarily rely on expert demonstrations...
The paper introduces Interaction-Constrained Drive Policy (ICDP), an offline reinforcement learning framework for autonomous driving that explicitly controls interaction-level distribution shift. ICDP decomposes joint-support degradation into ego-support and interaction-support components, estimating the latter via contrastive density-ratio estimation without requiring joint-density modeling or simulator rollouts. Experiments on nuPlan, Interplan, and real-world truck data demonstrate that ICDP reduces selection of high-value but interaction-unsupported trajectories and improves performance in interaction-critical driving scenarios.
arXiv:2601. 00898v3 Announce Type: replace Abstract: Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inference.
arXiv:2510. 09041v3 Announce Type: replace-cross Abstract: Deep reinforcement learning (DRL) has demonstrated remarkable success in developing autonomous driving policies.
arXiv:2603. 18315v2 Announce Type: replace-cross Abstract: Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse collision signals, which fail to capture the rich contextual understanding required for safe driving and make unsafe exploration unavoidable in real-world settings.
The paper presents a single pretrained diffusion traffic model that serves both as an ego motion planner and as a controllable generator of safety‑critical scenarios for autonomous driving. It introduces a Single‑Stream Dual‑Stream diffusion‑transformer decoder (SSDS) that fuses scene context via joint attention, improving closed‑loop performance on the nuPlan benchmark, and a training‑free guidance scheme called Decoupled Annealing Posterior Sampling with Energy (DAPSE) that injects arbitrary energy functions at inference time. Using the same model, the authors generate realistic long‑tail driving interactions—such as aggressive cut‑ins and lead‑vehicle braking—through inference‑time guidance, exposing failure modes in black‑box planners that standard benchmarks miss.
arXiv:2606. 16480v1 Announce Type: cross Abstract: Robots deployed in the real world must plan motions across diverse scenarios without per-scenario retuning.