发表机构
School of Automation, Northwestern Polytechnical University; Mohamed bin Zayed University of Artificial Intelligence（西北工业大学自动化学院; 穆罕默德·本·扎耶德人工智能大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对移动机器人在复杂环境下导航问题，提出PIER-Flow策略。通过将MPC专家知识融入常微分方程，利用并行潜在采样等实现单步动作生成，经物理信息训练目标及异步架构提升性能，在模拟和实际部署中均取得良好效果，显著加速规划并降低延迟。
AI 中文摘要
在密集且高度动态的环境中进行自主导航既需要物理上可行的控制，也需要低延迟重新规划。基于优化的方法（如模型预测控制（MPC））明确处理机器人运动学和安全约束，但重复的非线性优化会限制实时响应性。确定性行为克隆策略能实现高效推理，但可能无法表示多模态避障行为，而扩散策略以耗时的迭代去噪为代价捕捉多模态。我们提出了PIER-Flow，一种用于移动机器人的轻量级导航策略。通过将MPC专家提炼到连续时间常微分方程（ODE）中，PIER-Flow通过并行潜在采样和轻量级可行性选择实现单步动作生成。我们引入了一个物理信息训练目标来强制运动学一致性，同时采用异步动作分块架构以实现稳健的模拟到现实部署。大量模拟表明，PIER-Flow成功率达到98.85%且零碰撞，平均推理时间约为1.29毫秒，与MPC相比规划加速37.2倍，与标准扩散模型相比超过800倍。关键的是，在资源受限的边缘计算机上进行实际部署时，进一步实现了约5.3毫秒的近似稳定推理延迟，避免了规划基线中观察到的延迟峰值和冻结事件。
英文摘要
Autonomous navigation in dense and highly dynamic environments requires both physically feasible control and low-latency replanning. Optimization-based methods such as Model Predictive Control (MPC) explicitly handle robot kinematics and safety constraints, but repeated nonlinear optimization can limit real-time responsiveness. Deterministic behavior-cloning policies enable efficient inference but may fail to represent multimodal avoidance behaviors, whereas diffusion policies capture multimodality at the cost of time-consuming iterative denoising. We propose PIER-Flow (Physics-Informed Efficient Rectified Flow), a lightweight navigation policy for mobile robots. By distilling an MPC expert into a continuous-time Ordinary Differential Equation (ODE), PIER-Flow achieves single-step action generation through parallel latent sampling and lightweight feasibility selection. We introduce a physics-informed training objective to enforce kinematic consistency, paired with an asynchronous action chunking architecture for robust sim-to-real deployment. Extensive simulations demonstrate that PIER-Flow achieves a 98.85\% success rate and zero collisions, with an average inference of $\sim$1.29 ms, which accelerates planning by 37.2$\times$ compared to MPC and over 800$\times$ against standard diffusion models. Crucially, real-world deployment on a resource-constrained edge computer further achieves an approximately stable inference latency of $\sim$5.3 ms, avoiding the latency spikes and freezing events observed with planning baselines.
