Ratatouille：面向真实世界社交机器人导航的模仿学习要素
Ratatouille: Imitation Learning Ingredients for Real-world Social Robot Navigation
AI总结：
本文提出 Ratatouille 流水线与模型架构，通过精心设计模仿学习组件而非增加数据，在真实社交导航中将碰撞率降低 6 倍、成功率提高 3 倍。
摘要：
将强化学习扩展到野外社交机器人导航既数据密集又不安全，因为策略必须通过直接交互来学习，并且不可避免地会遇到碰撞。离线模仿学习（IL）通过安全地收集专家演示、完全离线训练以及零样本部署策略来避免这些风险。然而，我们发现将行为克隆（BC）天真地应用于社交导航是不够的；实现强大性能需要仔细的架构和训练选择。我们提出了 Ratatouille，一种流水线和模型架构，在不改变数据的情况下，与天真的 BC 相比，将每米碰撞次数减少了 6 倍，并将成功率提高了 3 倍。我们在仿真和现实世界中验证了我们的方法，在密集的大学校园中收集了超过 11 小时的数据。我们进一步在公共美食广场展示了定性结果。我们的发现强调，经过深思熟虑的 IL 设计，而不是额外的数据，可以显著提高现实世界社交导航中的安全性和可靠性。视频：https://youtu.be/tOdLTXsaYLQ。代码将在录用后发布。
英文摘要：
Scaling Reinforcement Learning to in-the-wild social robot navigation is both data-intensive and unsafe, since policies must learn through direct interaction and inevitably encounter collisions. Offline Imitation learning (IL) avoids these risks by collecting expert demonstrations safely, training entirely offline, and deploying policies zero-shot. However, we find that naively applying Behaviour Cloning (BC) to social navigation is insufficient; achieving strong performance requires careful architectural and training choices. We present Ratatouille, a pipeline and model architecture that, without changing the data, reduces collisions per meter by 6 times and improves success rate by 3 times compared to naive BC. We validate our approach in both simulation and the real world, where we collected over 11 hours of data on a dense university campus. We further demonstrate qualitative results in a public food court. Our findings highlight that thoughtful IL design, rather than additional data, can substantially improve safety and reliability in real-world social navigation. Video: https://youtu.be/tOdLTXsaYLQ. Code will be released after acceptance.
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。
