cs.ROOct 30, 2026

Mechanistic Interpretability for End-to-End Self-Driving

Authors: Manav Gagvani, Benjamin Namikas, Sivamurugan Velmurugan, Nysa Kumar, Shrey Sharma, Thomas Peterson, Pratyush Mathur, Hyunseo Chang, 

Organizations: Department of Electrical & Computer Engineering, Purdue University · Department of Computer Science, Purdue University

Abstract

End-to-end (E2E) autonomous driving models achieve strong planning performance but remain largely opaque, limiting observability and trust. We apply mechanistic interpretability to E2E driving by training Sparse Autoencoders (SAEs) on the internal activations of a simple, single-camera end-to-end path planning model. Unsupervised clustering of SAE latents reveals interpretable structure aligned with route intent, vehicle speed, and braking behavior, recovering route intent with 98.3% accuracy without supervision. Through paired counterfactual image edits, we further show that specific SAE features are visually grounded and systematically respond to scene changes such as traffic light state and stop sign presence. Steering individual SAE latents produces predictable, monotonic changes in planner outputs including lateral displacement, curvature, and braking. Finally, we demonstrate a practical application of these representations: we build a lightweight adapter trained on SAE latents that reduces trajectory selection error by 3.44%, outperforming an equivalent adapter that omits SAE latents, confirming that the sparse representation captures useful information for interpretability. Code and visualizations are available at https://mgagvani.github.io/mechanistic-interpretability-for-e2e-driving/

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jul 7, 2026

Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models

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. In this work, we integrate unsupervised dictionary learning as a post hoc interpretability module within state-of-the-art driving models to decompose driving behavior into semantically meaningful concepts while demonstrating their causal influence on the model's driving decisions. We propose a stepwise framework for extracting and interpreting meaningful concepts from the end-to-end model and connecting them to the multifaceted model outputs, thereby revealing the underlying decision-making logic for the prediction of future trajectories. Furthermore, targeted interventions at the concept level allow us to manipulate and correct driving decisions, resulting in measurable improvements in overall driving performance. We thus demonstrate how interpretability can effectively be used to reduce model opacity, uncover erroneous behavior, and enable targeted mitigation, ultimately boosting model performance.
Jun 4, 2026

Vault: One-Step Latent Generation with Positive-Anchored Rewards for Autonomous Driving

End-to-end autonomous driving must balance multimodal maneuver generation against real-time inference constraints. Diffusion planners capture diverse behaviors, but their iterative denoising incurs considerable inference cost in safety-critical deployment, while one-step alternatives still imitate only the single expert demonstration, so neither family certifies both the diversity and the quality of its outputs. To address this, we propose Vault, a framework that couples one-step latent generation with sample-based reinforcement learning guidance. Built on a V-JEPA 2.1 visual representation pretrained on the full NAVSIM training imagery, Vault generates trajectory candidates in a single forward pass by drifting in a VAE latent space. During training, a reward-gated positive pool collects the maximum-scoring trajectories that the model itself discovers under the official evaluator and anchors the drift targets to these certified samples. This closes a reinforcement-learning loop purely through sample-based target construction, without policy gradients, learned reward models, or extra interaction: the generator imitates the frontier of its own certified successes, so quality and multimodality improve together under a single fixed sampling configuration. A learned scorer that predicts the official score and its sub-metrics then selects the executed trajectory, and all training-only modules are discarded at inference. On the NAVSIM benchmarks, Vault achieves state-of-the-art performance at real-time inference cost, reaching 94.6 PDMS on v1 and 91.2 EPDMS on v2.
Aug 2, 2026

PRISM: Privileged Probabilistic Latent Supervision for End-to-End Autonomous Driving Motion Planning

End-to-end autonomous driving (E2E AD) systems integrate perception, prediction, and planning into a single differentiable architecture. While these models show great promise, their standard training often relies on output-only supervision, which can lead to weak gradients for the hidden layers of increasingly complex models. Recent works have integrated vision-language model (VLM) supervision for latent features to address this, yielding substantial empirical gains, yet leaving the underlying theoretical mechanisms poorly understood. Our investigation into this methodology reveals that the resulting performance gains stem not from VLM reasoning capabilities, as previously assumed, but rather from the latent connections forged between the E2E AD model and ground-truth (GT) data during training. Building on this insight, we propose a probabilistic deep supervision framework that regularizes intermediate latent representations directly from GT data. By treating model latents as reparameterizable distributions, we optimize the architecture via the Evidence Lower Bound (ELBO). Our evaluations conducted on the nuScenes dataset demonstrate that supervising trajectory-related latents with future GT paths consistently improves planning performance. Using identical training data and E2E architectures, our method achieves an 8% reduction in planning L2 error and a 3% decrease in collision rates compared to competitive vectorized baselines, all while incurring negligible computational overhead.