Knowledge-Data-Dual-Driven Reinforcement Learning for Autonomous Vehicle Control in Mixed Traffic

• URL: http://arxiv.org/abs/2608.13878v1
• Date: Fri, 14 Aug 2026 02:07:13 GMT
• Title: Knowledge-Data-Dual-Driven Reinforcement Learning for Autonomous Vehicle Control in Mixed Traffic
• Abstract summary: In mixed traffic, decision-making for autonomous vehicles (AVs) confronts three interrelated challenges.<n>First, physics-based priors fail to capture latent interactive vehicle intentions and diverse driver behaviors.<n>Second, abrupt maneuvers by surrounding vehicles cause non-stationarity, leaving long-tail safety events under-explored.<n>Third, hybrid action spaces destabilize unified RL training due to the different temporal scales of continuous car-following and discrete lane-changing maneuvers.
• Score: 7.833666254318349
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In mixed traffic, decision-making for autonomous vehicles (AVs) confronts three interrelated challenges. First, physics-based priors incorporated into reinforcement learning (RL) models fail to capture latent interactive vehicle intentions and diverse driver behaviors, limiting the proactive reasoning capabilities. Second, abrupt maneuvers by surrounding vehicles cause non-stationarity, leaving long-tail safety events under-explored. Third, hybrid action spaces destabilize unified RL training due to the different temporal scales of continuous car-following and discrete lane-changing maneuvers. To address these issues, we propose Knowledge-Data Dual-driven Reinforcement Learning (KDDRL). First, a conditional deep generative model synthesizes intention-aware future trajectories, converting passive perception into proactive predictive states. Second, a knowledge-data dual-driven paradigm operates on these predictive states, fusing probabilistic data-driven insights with physical constraints to guide safe exploration through safety-critical scenarios. Third, a coupling module compresses both intention-aware trajectories and physical constraints into compact shared embeddings. This unified representation enables asynchronous multi-timescale optimization of continuous car-following and discrete lane-changing while preserving mutual information. Evaluations on dataset-calibrated simulations demonstrate that KDDRL effectively handles intention uncertainty, accelerates training convergence, and outperforms conventional baseline methods in terms of safety, efficiency, and comfort.

Related papers

• SIREN-Bench: Behavior-Driven Generation and Evaluation of Emergency-Vehicle Interactions [4.523530339704703]
  We present textbfSIREN, a behavior-driven SUMO--CARLA co-language platform for generating EMVsimulation--civilian interactions.<n>We instantiate the platform as textbfSIREN-v1, comprising seven parameterized interaction templates across emergency levels L1--L3 and three behavior families.<n>We demonstrate the benchmark through three representative tasks: 3D object detection, trajectory prediction, and vision-language risk understanding.
  arXiv  Detail & Related papers  (2026-08-25T05:41:34Z)
• End-to-end Conditional Diffusion for Realistic and Controllable Visual Traffic Scenario Generation [59.188006170485046]
  E2E-CDiff is an end-to-end conditional diffusion framework for controllable and realistic scenario generation.<n>Differentiable guidance regulates speed, enforces drivable-area compliance, and supports collision-avoidance or collision-seeking behaviors.<n>E2E-CDiff also performs competitively as a learning-based ego planner.
  arXiv  Detail & Related papers  (2026-07-21T02:13:25Z)
• 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)
• 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)
• AI2-Active Safety: AI-enabled Interaction-aware Active Safety Analysis with Vehicle Dynamics [8.557684007368046]
  This paper introduces an AI-enabled, interaction-aware active safety analysis framework.<n>The framework employs a bicycle model-augmented with road gradient considerations to accurately capture vehicle dynamics.<n>In parallel, a hypergraph-based AI model is developed to predict probabilistic trajectories of ambient traffic.
  arXiv  Detail & Related papers  (2025-05-01T05:46:34Z)
• Minds on the Move: Decoding Trajectory Prediction in Autonomous Driving with Cognitive Insights [18.92479778025183]
  In driving scenarios, a vehicle's trajectory is determined by the decision-making process of human drivers.<n>Previous models fail to capture the true intentions of human drivers, leading to suboptimal performance in long-term trajectory prediction.<n>We introduce a Cognitive-Informed Transformer (CITF) that incorporates a cognitive concept, Perceived Safety, to interpret drivers' decision-making mechanisms.
  arXiv  Detail & Related papers  (2025-02-27T13:43:17Z)
• 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)
• Deep Reinforcement Learning for Autonomous Vehicle Intersection Navigation [0.24578723416255746]
  Reinforcement learning algorithms have emerged as a promising approach to address these challenges. Here, we address the problem of efficiently and safely navigating T-intersections using a lower-cost, single-agent approach. Our results reveal that the proposed approach enables the AV to effectively navigate T-intersections, outperforming previous methods in terms of travel delays, collision minimization, and overall cost.
  arXiv  Detail & Related papers  (2023-09-30T10:54:02Z)
• Unsupervised Driving Event Discovery Based on Vehicle CAN-data [62.997667081978825]
  This work presents a simultaneous clustering and segmentation approach for vehicle CAN-data that identifies common driving events in an unsupervised manner. We evaluate our approach with a dataset of real Tesla Model 3 vehicle CAN-data and a two-hour driving session that we annotated with different driving events.
  arXiv  Detail & Related papers  (2023-01-12T13:10:47Z)
• Modeling driver's evasive behavior during safety-critical lane changes:Two-dimensional time-to-collision and deep reinforcement learning [19.649145869208617]
  This study aims to develop a lane-change-related evasive behavior model. It can facilitate the development of safety-aware traffic simulations and predictive collision avoidance systems.
  arXiv  Detail & Related papers  (2022-09-29T23:23:38Z)
• Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance [110.63037190641414]
  We propose to learn congestion patterns explicitly and devise a novel "Sense--Learn--Reason--Predict" framework. By decomposing the learning phases into two stages, a "student" can learn contextual cues from a "teacher" while generating collision-free trajectories. In experiments, we demonstrate that the proposed model is able to generate collision-free trajectory predictions in a synthetic dataset.
  arXiv  Detail & Related papers  (2021-03-26T02:42:33Z)

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.