Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
Authors: Hongzhi Ruan, Pei Liu, Weiliang Ma, Zhengning Li, Xueyang Zhang, Jun Ma, Dan Xu, Kun Zhan
Organizations: Li Auto · HKUST (GZ) · HKUST
Abstract
Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training with near-infinite synthetic data a promising direction. However, naively incorporating all available synthetic data is inefficient and leads to distribution shifts, and optimizing data mixture under practical training budgets remains a critical yet under-explored problem. In this sense, we claim that the mixture of training data requires clear guidance in terms of scene types and quantities. Particularly in this work, we conceptualize the data mixture approximately as a dynamic optimization process that iteratively adjusts the training data mixture to maximize model performance, guided by closed-loop evaluation feedback, and propose AutoScale, a fully automated closed-loop data engine unifying scene representation, data mixture optimization and retrieval, as well as model training and evaluation. Specifically, we propose Graph Regularized AutoEncoder (Graph-RAE) for driving scene representations, introduce Cluster-aware Gradient Ascent (Cluster-GA) for cluster-wise importance estimation and reweighting, and perform cluster-guided vector retrieval to select high-value samples. Experiments on NavSim demonstrate that AutoScale outperforms vanilla co-training and cross-domain baselines, achieving better performance with fewer synthetic samples under constrained budgets.
As scaling pre-training data alone yields diminishing returns, post-training is becoming increasingly important across physical AI domains such as autonomous driving. End-to-end driving policies are pre-trained in open loop with behavior cloning on human demonstrations. However, compounding errors during closed-loop deployment can take the vehicle outside the training data distribution, increasing the risk of safety-critical incidents. Closed-loop post-training can mitigate this risk but requires costly simulation for sensor-based policies. We propose OPTED (on-policy fine-tuning for end-to-end driving) which decouples reinforcement learning from the post-training of the end-to-end policy: a privileged teacher is trained using RL on vectorized inputs (HD-map and bounding boxes). This teacher then provides supervision to the pre-trained student during closed-loop post-training. We apply OPTED to two camera-based models, TransFuser and VaVAM, and fine-tune them in AlpaSim, using neural reconstructions (3DGS) of real driving logs. Driving scores increase by factors of 1.6× and 9.5×, respectively. In controlled experiments OPTED matches closed-loop performance with approximately three orders of magnitude fewer simulator interactions than direct RL post-training, while staying closer to the human prior. Project page: https://01dami23.github.io/opted/
Synthetic data mitigates the data scarcity problem in autonomous driving perception. However, the synthetic-to-real gap leads to performance degradation, hindering real-world model generalization. Although current methods leverage diffusion models for photorealistic style transfer to bridge this gap, they critically ignore a practical asymmetry: while synthetic data possesses perfect pixel-level annotations, real-world style reference images generally lack corresponding labels. Consequently, existing methods relying on symmetric semantic guidance suffer from either prohibitive annotation costs or severe semantic misalignment. To address this dilemma, we formally propose a novel task: Asymmetric Style Transfer for Autonomous Driving (ASTAD), which requires semantically consistent transfer using only labeled synthetic content and unlabeled real-world references. We further introduce the ASTModel, a training-free two-stage framework designed to bridge this domain gap under asymmetric constraints. ASTModel first extracts a coarse semantic prior from the unlabeled target, followed by dynamic prior refinement and class-consistent style injection during the denoising process. Extensive experiments demonstrate that ASTModel significantly outperforms existing methods in downstream perception utility and structural fidelity, while offering a 3.2× inference speedup. This work aligns synthetic-to-real adaptation with practical constraints, holding the potential to accelerate the scalable deployment of robust autonomous driving systems. Code: https://github.com/Dingyi-Yao/ASTAD.
Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale simulations to substitute expensive, large-scale human driving demonstrations. A key limitation of this approach is that policies trained through pure self-play can learn effective but alien driving conventions incompatible with people. Previous works attempt to mitigate such behavioral misalignments through extensive reward engineering and domain randomization, which are brittle and labor-intensive. Instead of completely discarding human demonstrations, our method treats them as a regularization objective on top of a minimal safe goal-reaching reward. Like the spice in a good stew, we find that a little human data goes a long way: our method uses only 30 minutes of human demonstrations, 2500x fewer than comparable imitation learning approaches. Resulting policies coordinate with held-out human trajectories and complete training in 15 hours on a single consumer-grade GPU. Videos and full source code are available at https://spiced-self-play.com/.