FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
Summary
FlowR2A proposes a novel method that combines dense reward supervision with dynamic proposal generation using a flow-matching decoder for multimodal driving planning, achieving state-of-the-art results on the NAVSIM benchmarks.
View Cached Full Text
Cached at: 06/24/26, 05:46 AM
Paper page - FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
Source: https://huggingface.co/papers/2606.24231
Abstract
FlowR2A addresses the tension in multimodal driving planning by combining dense reward supervision with dynamic proposal generation through a flow-matching decoder that learns reward-conditioned action distributions.
Multimodal driving planningfaces a long-standing tension between two paradigms:scoring-based methodsbenefit from dense reward supervision but are confined to a fixed action vocabulary, whileanchor-based methodsgenerate proposals dynamically yet suffer from sparse supervision constrained to a single ground-truth trajectory. In this work, we propose FlowR2A, which resolves this tension by reframingsimulation-based rewardsfromdiscriminative targetsintogenerative conditions. By learning thereward-conditioned action distributionfromdense trajectory-reward pairswith aflow-matching decoder, FlowR2A unifies the dense supervision ofscoring-based methodswith the proposal generation ofanchor-based methodsin a single generative model, forcing the model to internalize the correlation between an action and its outcomes in safety, progress, comfort, and rule compliance. To balance hard safety constraints against soft progress objectives, we introduce fine-grained per-timestep reward conditioning and reward noise augmentation. The generative formulation naturally supports controllable test-time sampling viareward guidanceandanchored sampling, producing high-quality proposals. FlowR2A achieves state-of-the-art results on theNAVSIM v1and v2 benchmarks, with multimodal proposals of substantially higher quality than prior methods.
View arXiv pageView PDFProject pageGitHub2Add to collection
Get this paper in your agent:
hf papers read 2606\.24231
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.24231 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.24231 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.24231 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
ReflectDrive-2 is a new discrete diffusion planner for autonomous driving that uses reinforcement learning to enable self-editing of trajectory tokens, achieving high performance and low latency on the NAVSIM benchmark.
RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
RAD-2 presents a unified generator-discriminator framework for autonomous driving that combines diffusion-based trajectory generation with RL-optimized reranking, achieving 56% collision rate reduction compared to diffusion-based planners. The approach introduces techniques like Temporally Consistent Group Relative Policy Optimization and BEV-Warp simulation environment for efficient large-scale training.
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
DeltaRubric is a research paper introducing a two-step multimodal preference evaluation approach using a single MLLM to improve reward modeling reliability through joint planning and verification.
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
This paper proposes Discriminator-Guided Reinforcement Learning (DRL) to correct alignment issues in score- and flow-matching models by using a pretrained representation space discriminator as an optimal reward signal, significantly improving visual fidelity and semantic quality without human preferences.
Exploring the Design Space of Reward Backpropagation for Flow Matching
FlowBP introduces a unified surrogate-trajectory framework for aligning flow matching models with human preferences via reward backpropagation, reducing memory usage and gradient chaining while maintaining performance across multiple text-to-image models.