Open Source
FlowDrive: moderated flow matching with data balancing for trajectory planning
arXiv cs.RO0 views
arXiv:2509.21961v4 Announce Type: replace Abstract: Learning-based planners are sensitive to the long-tailed distribution of driving data. Common maneuvers dominate datasets, while dangerous or rare scenarios are sparse. This imbalance can bias models toward the frequent cases and degrade performance on critical scenarios. To tackle this problem, we compare balancing strategies for sampling training data and find reweighting by trajectory pattern an effective approach. We then present FlowDrive, a flow-matching trajectory planner that learns a conditional rectified flow to map noise directly to trajectory distributions with few flow-matching steps. We further introduce moderated, in-the-loop guidance that injects small perturbation between flow steps to systematically increase trajectory diversity while remaining scene-consistent. On nuPlan and the interaction-focused interPlan benchmarks, FlowDrive achieves state-of-the-art results among learning-based planners and approaches methods with rule-based refinements. After adding moderated guidance and light post-processing (FlowDrive*), it achieves overall state-of-the-art performance across nearly all benchmark splits. Our code is available at https://github.com/einsteinguang/flow_drive_planner.
Source:https://arxiv.org/abs/2509.21961PreviousImproving Imitation Policies for Multi-Phase Tasks through Residual Learning AllocationNextLCLA: Language-Conditioned Latent Alignment for Vision-Language Navigation
Related posts
Our Quote Conversion Rate Was Eighteen Percent Because Every Revised Quote Counted as One We Had Lost
0dev.to
A sticky Kakeya set over F3 that beats the classical construction, and where the question stands
0dev.to
In 2022 I learned to build Android apps in a country where I could not publish one
0dev.to
Are You Buying a Company or a model_id?
0dev.to Discuss
How to Test a Resistor, Diode, LED and Capacitor with a Multimeter (Before You Blame Your Code)
0dev.to Beginners
Omni-modal decomposition autoencoders learn full-stack wearable disentangled representations
0arXiv eess.SP