AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
- URL: http://arxiv.org/abs/2509.01944v1
- Date: Tue, 02 Sep 2025 04:32:24 GMT
- Title: AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
- Authors: Zhenlong Yuan, Jing Tang, Jinguo Luo, Rui Chen, Chengxuan Qian, Lei Sun, Xiangxiang Chu, Yujun Cai, Dapeng Zhang, Shuo Li,
- Abstract summary: We propose AutoDrive-R$2$, a novel VLA framework that enhances both reasoning and self-reflection capabilities of autonomous driving systems.<n>We first propose an innovative CoT dataset named nuScenesR$2$-6K for supervised fine-tuning.<n>We then employ the Group Relative Policy Optimization (GRPO) algorithm within a physics-grounded reward framework to ensure reliable smoothness and realistic trajectory planning.
- Score: 37.260140808367716
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Vision-Language-Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimodal perception with decision-making capabilities. However, the interpretability and coherence of the decision process and the plausibility of action sequences remain largely underexplored. To address these issues, we propose AutoDrive-R$^2$, a novel VLA framework that enhances both reasoning and self-reflection capabilities of autonomous driving systems through chain-of-thought (CoT) processing and reinforcement learning (RL). Specifically, we first propose an innovative CoT dataset named nuScenesR$^2$-6K for supervised fine-tuning, which effectively builds cognitive bridges between input information and output trajectories through a four-step logical chain with self-reflection for validation. Moreover, to maximize both reasoning and self-reflection during the RL stage, we further employ the Group Relative Policy Optimization (GRPO) algorithm within a physics-grounded reward framework that incorporates spatial alignment, vehicle dynamic, and temporal smoothness criteria to ensure reliable and realistic trajectory planning. Extensive evaluation results across both nuScenes and Waymo datasets demonstrates the state-of-the-art performance and robust generalization capacity of our proposed method.
Related papers
- Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving [55.13109926181247]
We introduce ReflectDrive, a learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion.<n>Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient.<n>Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors.
arXiv Detail & Related papers (2025-09-24T13:35:15Z) - ViLaD: A Large Vision Language Diffusion Framework for End-to-End Autonomous Driving [14.486548540613791]
We introduce ViLaD, a novel Large Vision Language Diffusion framework for end-to-end autonomous driving.<n>ViLaD enables parallel generation of entire driving decision sequences, significantly reducing computational latency.<n>We conduct comprehensive experiments on the nuScenes dataset, where ViLaD outperforms state-of-the-art autoregressive VLM baselines in both planning accuracy and inference speed.
arXiv Detail & Related papers (2025-08-18T04:01:56Z) - ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving [64.12414815634847]
Vision-Language Models (VLMs) and Driving World Models (DWMs) have independently emerged as powerful recipes addressing different aspects of this challenge.<n>We propose ImagiDrive, a novel end-to-end autonomous driving framework that integrates a VLM-based driving agent with a DWM-based scene imaginer.
arXiv Detail & Related papers (2025-08-15T12:06:55Z) - ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving [49.07731497951963]
ReCogDrive is a novel Reinforced Cognitive framework for end-to-end autonomous driving.<n>We introduce a hierarchical data pipeline that mimics the sequential cognitive process of human drivers.<n>We then address the language-action mismatch by injecting the VLM's learned driving priors into a diffusion planner.
arXiv Detail & Related papers (2025-06-09T03:14:04Z) - SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving [51.47621083057114]
SOLVE is an innovative framework that synergizes Vision-Language Models with end-to-end (E2E) models to enhance autonomous vehicle planning.<n>Our approach emphasizes knowledge sharing at the feature level through a shared visual encoder, enabling comprehensive interaction between VLM and E2E components.
arXiv Detail & Related papers (2025-05-22T15:44:30Z) - RAD: Retrieval-Augmented Decision-Making of Meta-Actions with Vision-Language Models in Autonomous Driving [10.984203470464687]
Vision-language models (VLMs) often suffer from limitations such as inadequate spatial perception and hallucination.<n>We propose a retrieval-augmented decision-making (RAD) framework to enhance VLMs' capabilities to reliably generate meta-actions in autonomous driving scenes.<n>We fine-tune VLMs on a dataset derived from the NuScenes dataset to enhance their spatial perception and bird's-eye view image comprehension capabilities.
arXiv Detail & Related papers (2025-03-18T03:25:57Z) - TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning [61.33599727106222]
TeLL-Drive is a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.<n>A self-attention mechanism then fuses these strategies with the DRL agent's exploration, accelerating policy convergence and boosting robustness.
arXiv Detail & Related papers (2025-02-03T14:22:03Z) - DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving [55.53171248839489]
We propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving.<n>Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.<n>Experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
arXiv Detail & Related papers (2024-09-15T15:55:24Z) - Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving [38.28159034562901]
Reason2Drive is a benchmark dataset with over 600K video-text pairs.
We characterize the autonomous driving process as a sequential combination of perception, prediction, and reasoning steps.
We introduce a novel aggregated evaluation metric to assess chain-based reasoning performance in autonomous systems.
arXiv Detail & Related papers (2023-12-06T18:32:33Z)
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.