从模仿到对齐：面向长距离人行道导航的人类偏好流策略
From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation
AI总结：
提出FlowPilot，一种仅使用单目RGB相机的无地图导航策略，通过锚定流匹配进行预训练，并引入人类偏好学习实现对齐，在长距离人行道导航中提升鲁棒性和社会合规性。
摘要：
自主长距离人行道导航对于微出行应用（如机器人送餐和辅助电动轮椅）至关重要。与道路上的自动驾驶不同，长距离人行道导航需要在不可预测的人行道地形和行人中精确操作，且感知栈轻量，仅需单个单目RGB相机。虽然从演示中模仿学习（IL）提供了一种实用解决方案，但由此产生的自动驾驶策略常常遭受复合误差、人行道上缺乏社会合规性以及缺乏处理复杂情况的反事实推理能力。为解决这些挑战，我们提出了FlowPilot，一种仅使用单目RGB相机即可实现稳健高效长距离导航性能的无地图导航策略。我们首先提出使用锚定流匹配作为动作表示，用于在大型机器人车队数据上进行策略预训练，并捕捉人行道导航行为的多样、复杂、多模态分布。为弥合模仿与对齐之间的差距，我们进一步设计了一种人在环的偏好学习方案，通过少量人类干预数据调整策略。它增强了模型的反事实推理能力和在人行道上的社会合规性。我们通过在多样化人行道环境中的广泛仿真和真实世界实验评估了FlowPilot。在仿真中，FlowPilot实现了42%的成功率和66%的路线完成率，而FlowPilot-HP进一步提升了真实世界的鲁棒性和社会合规性，相对于基础模型，IR降低了40.0%，NIR降低了52.1%。
英文摘要：
Autonomous long-horizon sidewalk navigation is essential for micro-mobility applications such as robotic food delivery and assistive electronic wheelchairs. Unlike autonomous driving on the road, long-horizon sidewalk navigation requires precise maneuvering through unpredictable sidewalk terrains and pedestrians, with a lightweight perception stack as minimal as a single monocular RGB camera. While imitation learning (IL) from demonstrations offers a practical solution, the resulting autopilot policy often suffers from compounding errors, a lack of social compliance on sidewalks, and deficiencies in counterfactual reasoning to handle complex situations. To address these challenges, we introduce FlowPilot, a mapless navigation policy that achieves robust and efficient long-horizon navigation performance using only a monocular RGB camera. We first propose to use anchored flow matching as an action representation for policy pre-training on large-scale robot fleet data and to capture the diverse, complex, multimodal distribution of sidewalk navigation behaviors. To bridge the gap between imitation and alignment, we further design a human-in-the-loop preference learning scheme to tune the policy on a small amount of human intervention data. It strengthens the model's counterfactual reasoning and social compliance on sidewalks. We evaluate FlowPilot through extensive simulation and real-world experiments in diverse sidewalk environments. FlowPilot achieves 42% success rate and 66% route completion in simulation, while FlowPilot-HP further improves real-world robustness and social compliance, reducing IR by 40.0% and NIR by 52.1% relative to the base model.
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。
