LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving

• URL: http://arxiv.org/abs/2512.20563v1
• Date: Tue, 23 Dec 2025 18:07:43 GMT
• Title: LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
• Abstract summary: We study how misalignment between privileged expert demonstrations and sensor-based student observations can limit the effectiveness of imitation learning.<n>Our TransFuser v6 (TFv6) student policy achieves a new state of the art on all major publicly available CARLA closed-loop benchmarks.
• Score: 29.34610793694948
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Simulators can generate virtually unlimited driving data, yet imitation learning policies in simulation still struggle to achieve robust closed-loop performance. Motivated by this gap, we empirically study how misalignment between privileged expert demonstrations and sensor-based student observations can limit the effectiveness of imitation learning. More precisely, experts have significantly higher visibility (e.g., ignoring occlusions) and far lower uncertainty (e.g., knowing other vehicles' actions), making them difficult to imitate reliably. Furthermore, navigational intent (i.e., the route to follow) is under-specified in student models at test time via only a single target point. We demonstrate that these asymmetries can measurably limit driving performance in CARLA and offer practical interventions to address them. After careful modifications to narrow the gaps between expert and student, our TransFuser v6 (TFv6) student policy achieves a new state of the art on all major publicly available CARLA closed-loop benchmarks, reaching 95 DS on Bench2Drive and more than doubling prior performances on Longest6~v2 and Town13. Additionally, by integrating perception supervision from our dataset into a shared sim-to-real pipeline, we show consistent gains on the NAVSIM and Waymo Vision-Based End-to-End driving benchmarks. Our code, data, and models are publicly available at https://github.com/autonomousvision/lead.

Related papers

• SimWAM: A Simple World Action Model for End-to-End Autonomous Driving [66.93548079427477]
  We present SimWAM, a simple yet effective WAM that leverages future-video prediction as a training-time supervision signal.<n>An isolated attention mask keeps action prediction independent of future frames, allowing trajectory prediction without explicit future-frame generation at inference.<n>Our SimWAM achieves 91.5 PDMS on NAVSIM, surpasses state-of-the-art WAM-based planners with substantially lower latency, and transfers zero-shot to nuScenes.
  arXiv  Detail & Related papers  (2026-08-07T17:59:09Z)
• CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving [66.77752555295355]
  We present CLEAR, a system that enables closed-loop training using Reinforcement Learning (RL) at scale for E2E-AD.<n>We show that with a simple reward, CLEAR significantly outperforms previous methods and sets new state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-07-03T00:34:50Z)
• Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives [18.838887346129916]
  We propose BeyondDrive, a failure-aware imitation learning framework that jointly learns from successful and failed driving behaviors.<n>First, we introduce a flow matching-based negative trajectory generator that synthesizes safety-critical yet expert-proximate trajectories.<n>Second, we develop a diversity-aware sampling strategy that mitigates mode collapse and improves coverage of diverse failure modes.<n>Third, we propose a Repulsive Distance Loss that simultaneously attracts predictions toward expert demonstrations while repelling them from hard negative trajectories.
  arXiv  Detail & Related papers  (2026-05-19T12:41:47Z)
• What Matters for Scalable and Robust Learning in End-to-End Driving Planners? [45.17722693412255]
  We re-examine the impact of architectural patterns on closed-loop performance.<n>We introduce BevAD, a novel lightweight and highly scalable end-to-end driving architecture.
  arXiv  Detail & Related papers  (2026-03-16T12:20:34Z)
• Learning to Drive by Imitating Surrounding Vehicles [0.8902959815221526]
  We study a data augmentation strategy that leverages the observed trajectories of nearby vehicles as additional demonstrations.<n>We introduce a simple vehicle-selection sampling and filtering strategy that prioritizes informative and diverse driving behaviors.<n>Specifically, the approach reduces collision rates and improves safety metrics compared to the baseline.
  arXiv  Detail & Related papers  (2025-03-08T00:40:47Z)
• MetaFollower: Adaptable Personalized Autonomous Car Following [63.90050686330677]
  We propose an adaptable personalized car-following framework - MetaFollower. We first utilize Model-Agnostic Meta-Learning (MAML) to extract common driving knowledge from various CF events. We additionally combine Long Short-Term Memory (LSTM) and Intelligent Driver Model (IDM) to reflect temporal heterogeneity with high interpretability.
  arXiv  Detail & Related papers  (2024-06-23T15:30:40Z)
• NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking [65.24988062003096]
  We present NAVSIM, a framework for benchmarking vision-based driving policies. Our simulation is non-reactive, i.e., the evaluated policy and environment do not influence each other. NAVSIM enabled a new competition held at CVPR 2024, where 143 teams submitted 463 entries, resulting in several new insights.
  arXiv  Detail & Related papers  (2024-06-21T17:59:02Z)
• Enhancing End-to-End Autonomous Driving with Latent World Model [78.22157677787239]
  We propose a novel self-supervised learning approach using the LAtent World model (LAW) for end-to-end driving.<n> LAW predicts future scene features based on current features and ego trajectories.<n>This self-supervised task can be seamlessly integrated into perception-free and perception-based frameworks.
  arXiv  Detail & Related papers  (2024-06-12T17:59:21Z)
• Guiding Attention in End-to-End Driving Models [49.762868784033785]
  Vision-based end-to-end driving models trained by imitation learning can lead to affordable solutions for autonomous driving. We study how to guide the attention of these models to improve their driving quality by adding a loss term during training. In contrast to previous work, our method does not require these salient semantic maps to be available during testing time.
  arXiv  Detail & Related papers  (2024-04-30T23:18:51Z)
• Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning [13.699336307578488]
  Deep imitative reinforcement learning approach (DIRL) achieves agile autonomous racing using visual inputs. We validate our algorithm both in a high-fidelity driving simulation and on a real-world 1/20-scale RC-car with limited onboard computation.
  arXiv  Detail & Related papers  (2021-07-18T00:00:48Z)
• PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning [84.30765628008207]
  We propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning. Our method outperforms the current state-of-the-art methods by a large margin on both benchmarks.
  arXiv  Detail & Related papers  (2021-06-08T07:37:37Z)
• Multi-task Learning with Attention for End-to-end Autonomous Driving [5.612688040565424]
  We propose a novel multi-task attention-aware network in the conditional imitation learning framework. This does not only improve the success rate of standard benchmarks, but also the ability to react to traffic lights.
  arXiv  Detail & Related papers  (2021-04-21T20:34:57Z)
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors [82.91398970736391]
  Vehicle trajectory prediction tasks have been commonly tackled from two perspectives: knowledge-driven or data-driven. In this paper, we propose to learn a "Realistic Residual Block" (RRB) which effectively connects these two perspectives. Our proposed method outputs realistic predictions by confining the residual range and taking into account its uncertainty.
  arXiv  Detail & Related papers  (2021-03-08T16:03:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.