The paper applies mechanistic interpretability to end‑to‑end autonomous driving by training Sparse Autoencoders on a single‑camera path‑planning model’s internal activations. Unsupervised clustering of the autoencoder’s latent space uncovers interpretable features linked to route intent, vehicle speed, and braking, achieving 98.3% accuracy in recovering route intent without supervision. Visual counterfactual edits confirm that specific latent features correspond to scene changes such as traffic lights and stop signs, and manipulating these latents yields predictable changes in planner outputs; a lightweight adapter trained on these latents reduces trajectory selection error by 3.44% compared to one that ignores them.
arXiv:2607. 16938v1 Announce Type: cross Abstract: End-to-end autonomous driving models are now able to navigate complex road scenarios, mapping raw sensor observations directly to observed paths for open-loop evaluation and often effective driving in closed-loop evaluation.
arXiv:2606. 17362v1 Announce Type: cross Abstract: Autonomous driving has shifted towards end-to-end policy learning, where reliable, interpretable policy evaluation is a fundamental challenge as driving quality is highly context-dependent.
End-to-end autonomous driving models are now able to navigate complex road scenarios, mapping raw sensor observations directly to observed paths for open-loop evaluation and often effective driving in closed-loop evaluation. Yet the internal logic of these safety-critical systems remains largely opaque, due to the complexity of traffic scenes.
arXiv:2607. 06328v1 Announce Type: new Abstract: The increasing adoption of end-to-end learning for autonomous driving introduces increased model complexity and opacity, raising the risk of learning undesired or erroneous behavior.
arXiv:2607. 29031v1 Announce Type: cross Abstract: Existing autonomous-driving world models typically perform dense prediction of future videos, occupancy states, BEV representations, or agent motion.
arXiv:2611.06007v1 Announce Type: new Abstract: Motorized Two-Wheelers (MTWs) dominate personal transport across much of the Global South, yet remain largely overlooked in predictive perception resea...
arXiv:2610.35032v1 Announce Type: cross Abstract: Self-supervised learning has emerged as a powerful paradigm for Path Representation Learning (PRL) in road networks. PRL aims to learn informative re...
arXiv:2610.09695v1 Announce Type: cross Abstract: Visual foundation models (VFMs) are increasingly integrated into end-to-end autonomous driving for their powerful representations, yet it remains unc...
ForeDrive introduces a planning-relevant latent world model that is asymmetrically coupled to a Diffusion Transformer planner. The model learns multi‑horizon latent futures with a JEPA‑style world model, while planning gradients update the shared encoder and stop‑gradient routing trains the predictor with forecasting losses only. Gated visual fusion, future‑status injection, and Trajectory‑Adaptive Bias are used to guide trajectory generation without overriding current observations, achieving high performance on NAVSIM benchmarks using only front‑view images and pure imitation learning.
arXiv:2606. 29879v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) provide powerful semantic understanding and commonsense reasoning for End-to-End Autonomous Driving (E2E-AD) planning.
The paper introduces a plug‑and‑play method that injects traffic‑element signals—such as traffic lights and road signs—into end‑to‑end autonomous driving models with minimal architectural changes. By augmenting several public datasets with comprehensive traffic‑element annotations, the authors evaluate this integration across diverse driving paradigms, consistently improving performance on nuScenes, NAVSIM‑v1, NAVSIM‑v2, and Bench2Drive. The approach achieves a new state‑of‑the‑art result on the challenging NAVSIM‑v2 benchmark, demonstrating the broad utility of traffic‑element awareness.
arXiv:2607. 20988v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models augmented with world modeling represent a promising paradigm for end-to-end autonomous driving.