arXiv 2506.151572025-06-18cs.ROcs.CV

鲁棒即时策略：利用学生t回归模型实现机器人操作的鲁棒上下文模仿学习

Robust Instant Policy: Leveraging Student's t-Regression Model for Robust In-context Imitation Learning of Robot Manipulation

Industrial Cyber-Physical Systems Research Center at the National Institute of Advanced Industrial Science and Technology (AIST), Japan（日本国家先进工业科学技术研究院工业闭环系统研究中心）

Hanbit Oh, Andrea M. Salcedo-Vázquez, Ixchel G. Ramirez-Alpizar, Yukiyasu Domae

备注：: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025 accepted

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出鲁棒即时策略（RIP），利用学生t回归模型聚合LLM生成的候选轨迹，以抵抗幻觉，在模拟和真实环境中任务成功率提升至少26%。

摘要：

模仿学习（IL）旨在通过观察少量人类演示，使机器人能够自主执行任务。最近，一种名为上下文模仿学习的IL变体，利用现成的大型语言模型（LLMs）作为即时策略，从给定的少量演示中理解上下文以执行新任务，而非通过大规模演示显式更新网络模型。然而，其在机器人领域的可靠性受到幻觉问题的损害，例如基于LLM的即时策略偶尔会生成偏离给定演示的劣质轨迹。为缓解此问题，我们提出了一种新的鲁棒上下文模仿学习算法，称为鲁棒即时策略（RIP），该算法利用学生t回归模型来对即时策略的幻觉轨迹具有鲁棒性，从而实现可靠的轨迹生成。具体而言，RIP从LLM生成若干候选机器人轨迹以完成给定任务，并使用学生t分布对它们进行聚合，这有利于忽略异常值（即幻觉）；从而生成对幻觉鲁棒的轨迹。我们在模拟和真实环境中的实验表明，RIP显著优于最先进的IL方法，任务成功率至少提高26%，尤其是在日常任务的低数据场景中。视频结果见https://sites.google.com/view/robustinstantpolicy。

英文摘要：

Imitation learning (IL) aims to enable robots to perform tasks autonomously by observing a few human demonstrations. Recently, a variant of IL, called In-Context IL, utilized off-the-shelf large language models (LLMs) as instant policies that understand the context from a few given demonstrations to perform a new task, rather than explicitly updating network models with large-scale demonstrations. However, its reliability in the robotics domain is undermined by hallucination issues such as LLM-based instant policy, which occasionally generates poor trajectories that deviate from the given demonstrations. To alleviate this problem, we propose a new robust in-context imitation learning algorithm called the robust instant policy (RIP), which utilizes a Student's t-regression model to be robust against the hallucinated trajectories of instant policies to allow reliable trajectory generation. Specifically, RIP generates several candidate robot trajectories to complete a given task from an LLM and aggregates them using the Student's t-distribution, which is beneficial for ignoring outliers (i.e., hallucinations); thereby, a robust trajectory against hallucinations is generated. Our experiments, conducted in both simulated and real-world environments, show that RIP significantly outperforms state-of-the-art IL methods, with at least $26\%$ improvement in task success rates, particularly in low-data scenarios for everyday tasks. Video results available at https://sites.google.com/view/robustinstantpolicy.

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。