改进模仿学习框架，让机器人导航更安全少碰撞。
Ratatouille: Imitation Learning Ingredients for Real-world Social Robot Navigation
- 设计新架构与训练策略提升模仿学习效果
- 碰撞率降6倍，成功率提升3倍
- 适合关注真实场景机器人导航的开发者
将强化学习扩展到真实社交机器人导航面临数据密集和安全隐患，因策略需通过直接交互学习，不可避免发生碰撞。离线模仿学习（IL）通过安全收集专家示范，在离线状态下训练并零样本部署，避免上述风险。然而我们发现，直接应用行为克隆（BC）在社交导航中效果不足；要获得良好性能，需精心设计模型结构与训练方法。本文提出Ratatouille，一种无需改变数据的流水线与模型架构，在仿真和真实世界中均验证有效。我们在密集校园环境中收集了超过11小时的数据，并在公开餐饮区展示定性结果。相比朴素的BC，该方法使每米碰撞次数减少6倍，成功率提升3倍。研究强调：精心设计的模仿学习可显著提升真实社交导航的安全性与可靠性。视频链接：https://youtu.be/tOdLTXsaYLQ。代码将在录用后发布。
原文摘要 · Abstract (English)
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.
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。