Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

• URL: http://arxiv.org/abs/2509.20109v1
• Date: Wed, 24 Sep 2025 13:35:15 GMT
• Title: Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
• Authors: Pengxiang Li, Yinan Zheng, Yue Wang, Huimin Wang, Hang Zhao, Jingjing Liu, Xianyuan Zhan, Kun Zhan, Xianpeng Lang,
• Abstract summary: 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.
• Score: 55.13109926181247
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages pre-trained multimodal knowledge from Vision-Language Models (VLMs) to interpret and interact with complex real-world environments. However, these methods remain constrained by the limitations of imitation learning, which struggles to inherently encode physical rules during training. Existing approaches often rely on complex rule-based post-refinement, employ reinforcement learning that remains largely limited to simulation, or utilize diffusion guidance that requires computationally expensive gradient calculations. To address these challenges, we introduce ReflectDrive, a novel learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion. We first discretize the two-dimensional driving space to construct an action codebook, enabling the use of pre-trained Diffusion Language Models for planning tasks through fine-tuning. Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient computation. Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors. Based on this, we apply local search methods to identify unsafe tokens and determine feasible solutions, which then serve as safe anchors for inpainting-based regeneration. Evaluated on the NAVSIM benchmark, ReflectDrive demonstrates significant advantages in safety-critical trajectory generation, offering a scalable and reliable solution for autonomous driving systems.

Related papers

• MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning [51.20229133553804]
  Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL)<n>Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning.<n>We propose MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters.<n>By feeding trajectory-level rewards back into the reasoning space, MindDrive enables trial-and-error learning over a finite set of discrete linguistic driving decisions.
  arXiv  Detail & Related papers  (2025-12-15T18:31:32Z)
• WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving [9.719456684859606]
  WAM-Diff is a framework that employs masked diffusion to refine a discrete sequence representing future ego-trajectories.<n>Our model achieves 91.0 PDMS on NAVSIM-v1 and 89.7S on NAVSIM-v2, demonstrating the effectiveness of masked diffusion for autonomous driving.
  arXiv  Detail & Related papers  (2025-12-06T10:51:53Z)
• BLIP-FusePPO: A Vision-Language Deep Reinforcement Learning Framework for Lane Keeping in Autonomous Vehicles [0.0]
  We propose a novel framework for multimodal reinforcement learning (RL) for autonomous lane-keeping (LK)<n>The proposed method lets the agent learn driving rules that are aware of their surroundings and easy to understand.<n>A hybrid reward function that includes semantic alignment, LK accuracy, obstacle avoidance, and speed regulation helps learning to be more efficient and generalizable.
  arXiv  Detail & Related papers  (2025-10-25T17:27:08Z)
• AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving [37.260140808367716]
  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.
  arXiv  Detail & Related papers  (2025-09-02T04:32:24Z)
• 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)
• Breaking Imitation Bottlenecks: Reinforced Diffusion Powers Diverse Trajectory Generation [20.106116218594266]
  DIVER is an end-to-end autonomous driving framework that integrates reinforcement learning and diffusion-based generation.<n>We show that DIVER significantly improves trajectory diversity, effectively addressing the mode collapse problem inherent in imitation learning.
  arXiv  Detail & Related papers  (2025-07-05T14:19:19Z)
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving [35.493857028919685]
  We propose ReCogDrive, an autonomous driving system that integrates Vision-Language Models with diffusion planner.<n>In this paper, we use a large-scale driving question-answering datasets to train the VLMs, mitigating the domain discrepancy between generic content and real-world driving scenarios.<n>In the second stage, we employ a diffusion-based planner to perform imitation learning, mapping representations from the latent language space to continuous driving actions.
  arXiv  Detail & Related papers  (2025-06-09T03:14:04Z)
• SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models [63.71984266104757]
  We propose SafeAuto, a framework that enhances MLLM-based autonomous driving by incorporating both unstructured and structured knowledge.<n>To explicitly integrate safety knowledge, we develop a reasoning component that translates traffic rules into first-order logic.<n>Our Multimodal Retrieval-Augmented Generation model leverages video, control signals, and environmental attributes to learn from past driving experiences.
  arXiv  Detail & Related papers  (2025-02-28T21:53:47Z)
• Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert Trajectories [16.666811573117613]
  The primary goal of motion planning is to generate safe and efficient trajectories for vehicles.<n>Traditionally, motion planning models are trained using imitation learning to mimic the behavior of human experts.<n>We propose a method that integrates constraint learning into imitation learning by extracting driving constraints from expert trajectories.
  arXiv  Detail & Related papers  (2024-12-07T18:29:28Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Empowering Autonomous Driving with Large Language Models: A Safety Perspective [82.90376711290808]
  This paper explores the integration of Large Language Models (LLMs) into Autonomous Driving systems. LLMs are intelligent decision-makers in behavioral planning, augmented with a safety verifier shield for contextual safety learning. We present two key studies in a simulated environment: an adaptive LLM-conditioned Model Predictive Control (MPC) and an LLM-enabled interactive behavior planning scheme with a state machine.
  arXiv  Detail & Related papers  (2023-11-28T03:13:09Z)

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.