让生成式导航具备真实尺度，避免撞墙，提升路径安全性和探索效率。
MetricNet: Recovering Metric Scale in Generative Navigation Policies
- 通过预测关键点间的真实距离，将抽象路径映射到度量空间。
- 在仿真与真实场景中，使用度量路径后导航成功率显著提升。
- 适合需要精准避障与长程规划的机器人导航任务。
生成式导航策略在端到端学习导航方面取得了快速进展。然而，该范式存在两个结构性问题：首先，采样轨迹存在于无度量基准的抽象空间中；其次，控制策略仅关注单个目标点，忽略完整路径，导致短视且不安全的行为，可能直接朝向障碍物移动。为解决此问题，我们提出 MetricNet，一种可插入生成式导航的附加模块，用于预测关键点间的度量距离，使策略输出具有度量坐标基准。我们在新提出的基准框架下进行仿真评估，结果表明，使用 MetricNet 校准后的路径能显著提升导航与探索性能。此外，我们在真实世界中进一步验证了该方法的有效性。最后，我们提出了 MetricNav，将 MetricNet 集成至导航策略中，引导机器人在靠近目标的同时避开障碍物。
原文摘要 · Abstract (English)
Generative navigation policies have made rapid progress in improving end-to-end learned navigation. Despite their promising results, this paradigm has two structural problems. First, the sampled trajectories exist in an abstract, unscaled space without metric grounding. Second, the control strategy discards the full path, instead moving directly towards a single waypoint. This leads to short-sighted and unsafe actions, moving the robot towards obstacles that a complete and correctly scaled path would circumvent. To address these issues, we propose MetricNet, an effective add-on for generative navigation that predicts the metric distance between waypoints, grounding policy outputs in metric coordinates. We evaluate our method in simulation with a new benchmarking framework and show that executing MetricNet-scaled waypoints significantly improves both navigation and exploration performance. Beyond simulation, we further validate our approach in real-world experiments. Finally, we propose MetricNav, which integrates MetricNet into a navigation policy to guide the robot away from obstacles while still moving towards the goal.
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。