期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 8, 期 5, 页码 2820-2827出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2023.3261751
关键词
Cooperating robots; mobile manipulation; imitation learning
类别
In this work, the authors propose a multi-robot push manipulation system that achieves better performance than baselines by incorporating a planner derived from a differentiable soft-body physics simulator into an attention-based neural network. The system demonstrates the ability to generalize to new configurations and adapt to environmental changes.
While natural systems often present collective intelligence that allows them to self-organize and adapt to changes, the equivalent is missing in most artificial systems. We explore the possibility of such a system in the context of cooperative 2D push manipulations using mobile robots. Although conventional works demonstrate potential solutions for the problem in restricted settings, they have computational and learning difficulties. More importantly, these systems do not possess the ability to adapt when facing environmental changes. In this work, we show that by distilling a planner derived from a differentiable soft-body physics simulator into an attention-based neural network, our multi-robot push manipulation system achieves better performance than baselines. In addition, our system also generalizes to configurations not seen during training and is able to adapt toward task completions when external turbulence and environmental changes are applied. Supplementary videos can be found on our project website: https://sites.google.com/view/ ciom/home.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据