arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.15919cs.RO
收藏

ReMoBot: 基于检索的少样本模仿学习用于移动操作与视觉基础模型

ReMoBot: Retrieval-Based Few-Shot Imitation Learning for Mobile Manipulation with Vision Foundation Models

School of Electrical Engineering, Aalto University, Espoo, Finland(艾尔沃大学电气工程学院,埃斯波,芬兰)

Yuying Zhang, Wenyan Yang, Francesco Verdoja, Ville Kyrki, Joni Pajarinen

AI总结:

提出ReMoBot,一种基于检索的少样本模仿学习框架,利用视觉基础模型从演示中检索信息,解决移动操作任务中的部分可观测性和数据有限问题,在真实世界任务中取得高成功率。

摘要:

模仿学习算法通常将演示提炼为参数化策略以模仿专家行为。然而,在数据有限和部分可观测的情况下(例如在自我中心的移动操作中),现有方法往往难以生成准确的动作。为了解决这些挑战,我们提出了ReMoBot,一种少样本、轨迹条件的模仿学习框架,它直接从演示中检索信息,以解决具有自我中心视觉观察的移动操作任务。利用视觉基础模型,ReMoBot通过结合状态级相似性、历史感知轨迹对齐和动作序列一致性来识别相关的专家演示,从而消除感知上相似观察的歧义。然后,智能体以完全无需训练的方式基于这些检索到的演示选择适当的控制命令。我们在波士顿动力Spot机器人上,在仿真和真实世界环境中评估了ReMoBot在三个移动操作任务上的表现。在仿真中对比了五种方法后,我们将我们的方法与两个直接在真实世界数据上训练(无仿真到真实迁移)的基线进行了比较。每个任务仅用20个演示,ReMoBot就优于基线,在Table Uncover(70%)和Gap Cover(80%)任务中取得了高成功率,同时在更具挑战性的真实世界Curtain Open任务中也展示了有前景的性能。此外,ReMoBot能够泛化到不同的机器人位置、物体尺寸和材料属性,突显了其在真实世界可变形移动操作中的鲁棒性。更多细节请访问:this https URL

英文摘要:

Imitation learning (IL) algorithms typically distill demonstrations into parametric policies to mimic expert behavior. However, with limited data and partial observability, such as in egocentric mobile manipulation, existing methods often struggle to generate accurate actions. To address these challenges, we propose ReMoBot, a few-shot, trajectory-conditioned imitation learning framework that directly Retrieves information from demonstrations to solve Mobile manipulation tasks with ego-centric visual observations. Leveraging vision foundation models, ReMoBot identifies relevant expert demonstrations by combining state-level similarity, history-aware trajectory alignment, and action-sequence consistency to disambiguate perceptually similar observations. The agent then selects appropriate control commands based on these retrieved demonstrations in a fully training-free manner. We evaluate ReMoBot on three mobile manipulation tasks using a Boston Dynamics Spot robot in both simulation and real-world settings. After benchmarking five approaches in simulation, we compare our method with two baselines trained directly on real-world data without sim-to-real transfer. With only 20 demonstrations per task, ReMoBot outperforms the baselines, achieving high success rates in Table Uncover (70%) and Gap Cover (80%), while also showing promising performance on the more challenging Curtain Open task in the real-world setting. Furthermore, ReMoBot generalizes across varying robot positions, object sizes, and material properties, highlighting its robustness in real-world deformable mobile manipulation. Additional details are available at: https://sites.google.com/view/remobot/home

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。

↑