arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.10047cs.ROcs.AIcs.CVcs.LG
收藏

从游戏到政策:从未经策划的机器人数据生成条件行为

From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data

New York University(纽约大学)

Zichen Jeff Cui, Yibin Wang, Nur Muhammad Mahi Shafiullah, Lerrel Pinto

摘要:

虽然离线数据的大规模序列建模在自然语言和图像生成方面带来了令人印象深刻的性能提升,但将这些想法直接转化为机器人技术一直具有挑战性。其中一个关键原因是,从非专家人类演示者收集的未经策划的机器人演示数据,即游戏数据,通常是嘈杂的,多样的,并且是分布式多模态的。这使得从这些数据中提取有用的、以任务为中心的行为成为一个困难的生成建模问题。在这项工作中,我们提出了条件行为Transformers(C-BeT),一种方法,结合了多模态生成能力的行为Transformer与未来条件的目标规范。在一组模拟基准任务上,我们发现C-BeT在从游戏数据中学习方面比现有的最先进的工作平均提高了45.7%。此外,我们第一次证明,有用的以任务为中心的行为可以在现实世界的机器人上学习纯粹从播放数据没有任何任务标签或奖励信息。机器人视频最好在我们的项目网站上观看:https://play-to-policy.github.io

英文摘要:

While large-scale sequence modeling from offline data has led to impressive performance gains in natural language and image generation, directly translating such ideas to robotics has been challenging. One critical reason for this is that uncurated robot demonstration data, i.e. play data, collected from non-expert human demonstrators are often noisy, diverse, and distributionally multi-modal. This makes extracting useful, task-centric behaviors from such data a difficult generative modeling problem. In this work, we present Conditional Behavior Transformers (C-BeT), a method that combines the multi-modal generation ability of Behavior Transformer with future-conditioned goal specification. On a suite of simulated benchmark tasks, we find that C-BeT improves upon prior state-of-the-art work in learning from play data by an average of 45.7%. Further, we demonstrate for the first time that useful task-centric behaviors can be learned on a real-world robot purely from play data without any task labels or reward information. Robot videos are best viewed on our project website: https://play-to-policy.github.io

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。

↑