用势场引导流匹配，让机器人模仿动作更安全
Towards Safe Imitation Learning via Potential Field-Guided Flow Matching
- 从成功示范中同时学任务策略和障碍物势场
- 推理时用势场调制生成路径，碰撞率显著下降
- 适合复杂障碍环境的机器人导航与操作
深度生成模型，尤其是扩散和流匹配模型，在通过模仿学习构建复杂策略方面展现出巨大潜力。然而，生成动作的安全性在存在固有障碍的复杂环境中仍被忽视。本文提出势场引导流匹配策略（PF2MP），从同一组成功示范中同时学习任务策略和障碍物相关势场信息。推理阶段，PF2MP通过学习到的势场调节流匹配向量场，实现安全轨迹生成。借助互补的双场机制，该方法在不牺牲任务成功率的前提下，显著提升安全性，适用于导航与机器人操作等多种场景。我们在仿真与真实世界中评估了PF2MP，验证其在任务空间与关节空间控制中的有效性。实验表明，相比基线策略，PF2MP显著降低了碰撞率，为非结构化、障碍密集环境中的安全运动生成开辟新路径。
原文摘要 · Abstract (English)
Deep generative models, particularly diffusion and flow matching models, have recently shown remarkable potential in learning complex policies through imitation learning. However, the safety of generated motions remains overlooked, particularly in complex environments with inherent obstacles. In this work, we address this critical gap by proposing Potential Field-Guided Flow Matching Policy (PF2MP), a novel approach that simultaneously learns task policies and extracts obstacle-related information, represented as a potential field, from the same set of successful demonstrations. During inference, PF2MP modulates the flow matching vector field via the learned potential field, enabling safe motion generation. By leveraging these complementary fields, our approach achieves improved safety without compromising task success across diverse environments, such as navigation tasks and robotic manipulation scenarios. We evaluate PF2MP in both simulation and real-world settings, demonstrating its effectiveness in task space and joint space control. Experimental results demonstrate that PF2MP enhances safety, achieving a significant reduction of collisions compared to baseline policies. This work paves the way for safer motion generation in unstructured and obstaclerich environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。