NavOL：基于在线模仿学习的导航策略
NavOL: Navigation Policy with Online Imitation Learning
AI总结：
NavOL通过在线模仿学习在仿真环境中训练导航策略，利用预训练的扩散策略和全局规划器，提升学习效率并减少分布偏移，实现在50个场景中每小时生成2000多条轨迹。
摘要：
学习鲁棒的导航策略仍是机器人领域的核心挑战。离线模仿学习面临分布偏移和滚动生成误差，而强化学习需要奖励工程且学习效率低下。本文提出NavOL，一种在线模仿学习范式，通过与仿真器交互并利用在线收集的专家演示更新自身。基于预训练的导航扩散策略，该策略将局部观测映射到未来路径点，通过滚动生成更新循环：在滚动生成时，策略在仿真器中执行动作并查询具有优先访问全局环境权限的全局规划器，获取最优路径段作为地面真实轨迹标签；在更新时，策略在在线收集的观测轨迹对上进行训练。这种在线模仿循环消除了奖励设计的需要，提高了学习效率，并通过在策略自身探索的滚动生成中训练来缓解分布偏移。基于IsaacLab，系统在8块RTX 4090 GPU上跨50个场景扩展，每小时生成超过2000条新轨迹，每条轨迹平均超过400步。我们还引入了一个室内视觉导航基准，包含预定义的起点和终点位置以实现零样本泛化。在仿真基准（包括NavDP基准和我们提出的新基准）以及精心设计的现实世界实验中，广泛评估显示了NavOL的有效性，展示了在线模仿学习中的一致性能提升。
英文摘要：
Learning robust navigation policies remains a core challenge in robotics. Offline imitation learning suffers from distribution shift and compounding errors at rollout, while reinforcement learning requires reward engineering and learns inefficiently. In this paper, we propose NavOL, an online imitation learning paradigm that interacts with a simulator and updates itself using expert demonstrations gathered online. Built upon a pretrained navigation diffusion policy that maps local observations to future waypoints, NavOL trains in a rollout update loop: during rollout, the policy acts in the simulator and queries a global planner which has privileged access to the global environment for the optimal path segment as ground truth trajectory labels; during update, the policy is trained on the online collected observation trajectory pairs. This online imitation loop removes the need for reward design, improves learning efficiency, and mitigates distribution shift by training on the policy own explored rollouts. Built on IsaacLab with fast, high-fidelity parallel rendering and domain randomization of camera pose and start-goal pairs, our system scales across 50 scenes on 8 RTX 4090 GPUs, collecting over 2,000 new trajectories per hour, each averaging more than 400 steps. We also introduce an indoor visual navigation benchmark with predefined start and goal positions for zero-shot generalization. Extensive evaluations on simulation benchmarks, including the NavDP benchmark and our proposed benchmark, as well as carefully designed real-world experiments, demonstrate the effectiveness of NavOL, showing consistent performance gains in online imitation learning.
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。
