arXiv 2602.066982026-03-17cs.RO

Crowd-FM: 基于学习的条件流匹配生成轨迹的最优选择用于人群导航

Crowd-FM: Learned Optimal Selection of Conditional Flow Matching-generated Trajectories for Crowd Navigation

Robotics Research Center, IIIT Hyderabad, India（IIIT海得拉巴机器人研究中心，印度）；Nanyang Technological University, Singapore（新加坡南洋理工大学）；University of Tartu, Estonia（爱沙尼亚塔尔图大学）；Inria, Université de Lorraine, France（法国里尔大学Inria研究院）

Antareep Singha, Laksh Nanwani, Mathai Mathew P., Samkit Jain, Phani Teja Singamaneni, Arun Kumar Singh, K. Madhava Krishna

备注：: Accepted at IEEE ICRA 2026. Authors Antareep Singha and Laksh Nanwani have equal contributions

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出Crowd-FM方法，通过条件流匹配学习碰撞自由的轨迹生成策略，提升机器人在人群中的安全性和人似性。

摘要：

在密集、无结构的人群中为移动机器人实现安全且计算高效的局部规划仍然是一个基本挑战。此外，确保机器人轨迹与人类移动方式相似将提高机器人在人类环境中的接受度。本文提出Crowd-FM，一种基于学习的方法，解决安全性和人似性挑战。我们的方法有两个新颖组成部分。首先，我们训练一个条件流匹配（CFM）策略，利用最优控制轨迹数据集学习一组碰撞自由的原始动作，机器人在任何场景中均可选择。所选最优控制求解器可生成多模式碰撞自由轨迹，使CFM策略学习多样化的操作。其次，我们学习一个在人类示范轨迹数据集上的评分函数，为流原始动作提供人似性评分。在推理时，计算最优轨迹需要选择评分最高的轨迹。我们的方法通过展示CFM策略单独可产生比现有学习基线更高的碰撞自由导航成功率而改进了现有水平。此外，当与推理时的细化相结合时，我们的方法可以超越甚至昂贵的优化规划方法。最后，我们验证了我们的评分网络可以比手动设计的成本函数选择更接近专家数据的轨迹。

英文摘要：

Safe and computationally efficient local planning for mobile robots in dense, unstructured human crowds remains a fundamental challenge. Moreover, ensuring that robot trajectories are similar to how a human moves will increase the acceptance of the robot in human environments. In this paper, we present Crowd-FM, a learning-based approach to address both safety and human-likeness challenges. Our approach has two novel components. First, we train a Conditional Flow-Matching (CFM) policy over a dataset of optimally controlled trajectories to learn a set of collision-free primitives that a robot can choose at any given scenario. The chosen optimal control solver can generate multi-modal collision-free trajectories, allowing the CFM policy to learn a diverse set of maneuvers. Secondly, we learn a score function over a dataset of human demonstration trajectories that provides a human-likeness score for the flow primitives. At inference time, computing the optimal trajectory requires selecting the one with the highest score. Our approach improves the state-of-the-art by showing that our CFM policy alone can produce collision-free navigation with a higher success rate than existing learning-based baselines. Furthermore, when augmented with inference-time refinement, our approach can outperform even expensive optimisation-based planning approaches. Finally, we validate that our scoring network can select trajectories closer to the expert data than a manually designed cost function.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。