Beyond Imitation: Constraint-Aware Trajectory Generation with Flow Matching For End-to-End Autonomous Driving

• URL: http://arxiv.org/abs/2510.26292v1
• Date: Thu, 30 Oct 2025 09:24:34 GMT
• Title: Beyond Imitation: Constraint-Aware Trajectory Generation with Flow Matching For End-to-End Autonomous Driving
• Abstract summary: We propose CATG, a novel planning framework that leverages Constrained Flow Matching.<n>CatG explicitly models the flow matching process, which inherentlys mode collapse.<n>CatG parameterizes driving aggressiveness as a control signal during generation, enabling precise manipulation of trajectory style.
• Score: 18.239343348322134
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Planning is a critical component of end-to-end autonomous driving. However, prevailing imitation learning methods often suffer from mode collapse, failing to produce diverse trajectory hypotheses. Meanwhile, existing generative approaches struggle to incorporate crucial safety and physical constraints directly into the generative process, necessitating an additional optimization stage to refine their outputs. To address these limitations, we propose CATG, a novel planning framework that leverages Constrained Flow Matching. Concretely, CATG explicitly models the flow matching process, which inherently mitigates mode collapse and allows for flexible guidance from various conditioning signals. Our primary contribution is the novel imposition of explicit constraints directly within the flow matching process, ensuring that the generated trajectories adhere to vital safety and kinematic rules. Secondly, CATG parameterizes driving aggressiveness as a control signal during generation, enabling precise manipulation of trajectory style. Notably, on the NavSim v2 challenge, CATG achieved 2nd place with an EPDMS score of 51.31 and was honored with the Innovation Award.

Related papers

• 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)
• FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning [63.80677039120727]
  FlowR2A unifies the dense supervision of scoring-based methods with the proposal generation of anchor-based methods in a single generative model.<n>To balance hard safety constraints against soft progress objectives, we introduce fine-grained per-timestep reward conditioning and reward noise augmentation.<n>The generative formulation naturally supports controllable test-time sampling via reward guidance and anchored sampling, producing high-quality proposals.
  arXiv  Detail & Related papers  (2026-06-23T07:21:36Z)
• DriveAnchor: Progressive Anchor-based Flow Learning for Autonomous Driving Planning [6.848508447210393]
  DriveAnchor is a framework for autonomous driving planning.<n>It achieves behavioral diversity, controllability, and safety in a composable pipeline.<n>It reduces near-range collision rates by 89% and improves mean reward by 32% without degradation in imitation accuracy.
  arXiv  Detail & Related papers  (2026-05-30T04:17:59Z)
• Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction [21.408459244943597]
  We propose Dynamic-TD3, a physically enhanced framework that enforces strict constraints while maintaining maneuverability.<n>In experiments with aggressive dynamic threats, this approach demonstrates superior collision avoidance performance, reduced energy consumption, and smoother flight trajectories.
  arXiv  Detail & Related papers  (2026-04-30T02:56:29Z)
• DRIFT: Diffusion-based Rule-Inferred For Trajectories [15.78457153766977]
  Trajectory generation for mobile robots in unstructured environments faces a critical dilemma: balancing smoothness for safe execution with terminal precision for fine-grained tasks.<n>This article proposes DRIFT, a conditional framework designed to generate high-fidelity reference trajectories by integrating two complementary inductive biases.<n>Results demonstrate that DRIFT reconciles these conflicting objectives, achieving centimeter-level imitation fidelity (0.041m FDE) and competitive smoothness (27.19 Jerk)
  arXiv  Detail & Related papers  (2026-03-01T05:54:38Z)
• Primary-Fine Decoupling for Action Generation in Robotic Imitation [91.2899765310853]
  Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning.<n>We propose Primary-Fine Decoupling for Action Generation (PF-DAG), a two-stage framework that decouples coarse action consistency from fine-grained variations.<n>PF-DAG outperforms state-of-the-art baselines across 56 tasks from Adroit, DexArt, and MetaWorld benchmarks.
  arXiv  Detail & Related papers  (2026-02-25T08:36:45Z)
• Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection [1.7802147489386628]
  Large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors.<n>We propose Selective Steering, which addresses these limitations through two key innovations.<n> Experiments across nine models demonstrate that Selective Steering achieves 5.5x higher attack success rates than prior methods.
  arXiv  Detail & Related papers  (2026-01-27T08:56:25Z)
• GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving [22.92109402334754]
  Driving planning is a critical component of end-to-end (E2E) autonomous driving.<n>textittextbfGuideFlow explicitly models the flow matching process, which inherently mitigates mode collapse.<n>textittextbfGuideFlow parameterizes driving aggressiveness as a control signal during generation, enabling precise manipulation of trajectory style.
  arXiv  Detail & Related papers  (2025-11-24T03:45:32Z)
• 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)
• Steerable Adversarial Scenario Generation through Test-Time Preference Alignment [58.37104890690234]
  Adversarial scenario generation is a cost-effective approach for safety assessment of autonomous driving systems.<n>We introduce a new framework named textbfSteerable textbfAdversarial scenario textbfGEnerator (SAGE)<n>SAGE enables fine-grained test-time control over the trade-off between adversariality and realism without any retraining.
  arXiv  Detail & Related papers  (2025-09-24T13:27:35Z)
• Modeling and Control of Deep Sign-Definite Dynamics with Application to Hybrid Powertrain Control [1.9116784879310027]
  Deep learning is increasingly used for enforce physical systems or systems where first-principles modeling is difficult.<n>We develop a new type of deep learning model that satisfies constraints on Jacobian entries--that monotonicity, and sign-definite positivity.<n>On a two-tank system hybrid, the proposed approach improves control inputs than existing methods.
  arXiv  Detail & Related papers  (2025-09-24T08:15:26Z)
• FlowDrive: Energy Flow Field for End-to-End Autonomous Driving [50.89871153094958]
  FlowDrive is a novel framework that introduces physically interpretable energy-based flow fields to encode semantic priors and safety cues into the BEV space.<n> Experiments on the NAVSIM v2 benchmark demonstrate that FlowDrive achieves state-of-the-art performance with anS of 86.3, surpassing prior baselines in both safety and planning quality.
  arXiv  Detail & Related papers  (2025-09-17T13:51:33Z)
• Autoregressive Meta-Actions for Unified Controllable Trajectory Generation [10.123353592943968]
  Controllable trajectory generation is crucial for autonomous driving systems.<n>Existing frameworks rely on invariant meta-actions assigned over fixed future time intervals.<n>We introduce Autoregressive Meta-Actions, an approach integrated into autoregressive trajectory generation frameworks.
  arXiv  Detail & Related papers  (2025-05-29T16:19:59Z)
• RIFT: Group-Relative RL Fine-Tuning for Realistic and Controllable Traffic Simulation [13.319344167881383]
  We introduce a dual-stage AV-centric simulation framework that conducts imitation learning pre-training in a data-driven simulator.<n>We then learn fine-tuning in a physics-based simulator to enhance style-level controllability.<n>In the fine-tuning stage, we propose RIFT, a novel group-relative RL fine-tuning strategy.
  arXiv  Detail & Related papers  (2025-05-06T09:12:37Z)
• 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)
• A Tricycle Model to Accurately Control an Autonomous Racecar with Locked Differential [71.53284767149685]
  We present a novel formulation to model the effects of a locked differential on the lateral dynamics of an autonomous open-wheel racecar. We include a micro-steps discretization approach to accurately linearize the dynamics and produce a prediction suitable for real-time implementation.
  arXiv  Detail & Related papers  (2023-12-22T16:29:55Z)
• DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control [62.24301794794304]
  Deep Adaptive Trajectory Tracking (DATT) is a learning-based approach that can precisely track arbitrary, potentially infeasible trajectories in the presence of large disturbances in the real world. DATT significantly outperforms competitive adaptive nonlinear and model predictive controllers for both feasible smooth and infeasible trajectories in unsteady wind fields. It can efficiently run online with an inference time less than 3.2 ms, less than 1/4 of the adaptive nonlinear model predictive control baseline.
  arXiv  Detail & Related papers  (2023-10-13T12:22:31Z)
• Integrating Higher-Order Dynamics and Roadway-Compliance into Constrained ILQR-based Trajectory Planning for Autonomous Vehicles [3.200238632208686]
  Trajectory planning aims to produce a globally optimal route for Autonomous Passenger Vehicles. Existing implementations utilizing the vehicle bicycle kinematic model may not guarantee controllable trajectories. We augment this model by higher-order terms, including the first and second-order derivatives of curvature and longitudinal jerk.
  arXiv  Detail & Related papers  (2023-09-25T22:30:18Z)

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.