# TakeAD: Preference-based Post-optimization for End-to-end Autonomous Driving with Expert Takeover Data arXiv: https://arxiv.org/abs/2512.17370 ยท HTML: https://mlsanity.com/paper/2512.17370/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving. - Builds on 25 of its 29 references that are in the map. - First posted on arXiv 19 Dec 2025. ## Placed in - End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/) - LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/) - Offline RL and imitation learning from data / [Imitation and offline RL for driving](https://mlsanity.com/offlinerl/imitation-and-offline-rl-for-driving/) ## Builds on (most cited first, 25 of 25) - [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023) - [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022) - [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024) - [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023) - [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023) - [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022) - [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019) - [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023) - [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024) - [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025) - [Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving](https://mlsanity.com/paper/2406.03877/) (2024) - [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022) - [Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes](https://mlsanity.com/paper/2305.10430/) (2023) - [Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving](https://mlsanity.com/paper/2305.06242/) (2023) - [DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving](https://mlsanity.com/paper/2308.00398/) (2023) - [DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving](https://mlsanity.com/paper/2503.07656/) (2025) - [World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model](https://mlsanity.com/paper/2507.00603/) (2025) - [ReasonNet: End-to-End Driving with Temporal and Global Reasoning](https://mlsanity.com/paper/2305.10507/) (2023) - [Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Driving](https://mlsanity.com/paper/2503.03125/) (2025) - [RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning](https://mlsanity.com/paper/2502.13144/) (2025) - [Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning](https://mlsanity.com/paper/2506.18234/) (2025) - [TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous Driving](https://mlsanity.com/paper/2203.16792/) (2022) - [ReasonPlan: Unified Scene Prediction and Decision Reasoning for Closed-loop Autonomous Driving](https://mlsanity.com/paper/2505.20024/) (2025) - [UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty](https://mlsanity.com/paper/2504.12826/) (2025) - [Dream to Drive with Predictive Individual World Model](https://mlsanity.com/paper/2501.16733/) (2025) ## Built on by (most cited first, 8 of 8) - [SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model](https://mlsanity.com/paper/2604.19710/) (2026) - [Learning from Mistakes: Post-Training for Driving VLA with Takeover Data](https://mlsanity.com/paper/2603.14972/) (2026) - [Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives](https://mlsanity.com/paper/2605.19771/) (2026) - [Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention](https://mlsanity.com/paper/2605.15157/) (2026) - [Post-Training in End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.08072/) (2026) - [PerlAD: Towards Enhanced Closed-loop End-to-end Autonomous Driving with Pseudo-simulation-based Reinforcement Learning](https://mlsanity.com/paper/2603.14908/) (2026) - [GSDrive: Reinforcing Driving Policies by Multi-mode Future Trajectory Probing with 3D Gaussian Splatting Environment](https://mlsanity.com/paper/2604.28111/) (2026) - [Plug-and-Play Traffic Element Awareness for End-to-End Autonomous Driving](https://mlsanity.com/paper/2608.18035/) (2026) ## Abstract (arXiv) Existing end-to-end autonomous driving methods typically rely on imitation learning (IL) but face a key challenge: the misalignment between open-loop training and closed-loop deployment. This misalignment often triggers driver-initiated takeovers and system disengagements during closed-loop execution. How to leverage those expert takeover data from disengagement scenarios and effectively expand the IL policy's capability presents a valuable yet unexplored challenge. In this paper, we propose TakeAD, a novel preference-based post-optimization framework that fine-tunes the pre-trained IL policy with this disengagement data to enhance the closed-loop driving performance. First, we design an efficient expert takeover data collection pipeline inspired by human takeover mechanisms in real-world autonomous driving systems. Then, this post optimization framework integrates iterative Dataset Aggregation (DAgger) for imitation learning with Direct Preference Optimization (DPO) for preference alignment. The DAgger stage equips the policy with fundamental capabilities to handle disengagement states through direct imitation of expert interventions. Subsequently, the DPO stage refines the policy's behavior to better align with expert preferences in disengagement scenarios. Through multiple iterations, the policy progressively learns recovery strategies for disengagement states, thereby mitigating the open-loop gap. Experiments on the closed-loop Bench2Drive benchmark demonstrate our method's effectiveness compared with pure IL methods, with comprehensive ablations confirming the contribution of each component.