Focused Adaptation of Dynamics Models for Deformable Object Manipulation
Focused Adaptation of Dynamics Models for Deformable Object Manipulation
复制标题
DOI：
10.1109/icra48891.2023.10161366
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
P. Mitrano;A. LaGrassa;Oliver Kroemer;D. Berenson
中科院分区：
文献类型：
--
作者：
P. Mitrano;A. LaGrassa;Oliver Kroemer;D. Berenson
为了在新环境中有效地学习任务的动态模型，可以调整在类似源环境中学习的模型。然而，当目标数据集包含动态与源环境非常不同的转换时，现有的自适应方法可能会失败。例如，源环境动力学可以是在自由空间中操纵的绳索，而目标动力学可以涉及障碍物上的碰撞和变形。我们的关键见解是通过仅将模型自适应集中在源和目标动态相似的区域来提高数据效率。在绳索示例中，与在学习碰撞动力学的同时调整自由空间动力学相比，调整自由空间动力学需要的数据明显更少。我们提出了一种新的适应方法，是有效的适应类似的动态区域。此外，我们结合联合收割机这种适应方法与以前的工作规划与不可靠的动态，使数据高效的在线适应的方法，称为FOCUS。我们首先证明，所提出的自适应方法在模拟绳索操作和植物浇水任务的相似动态区域中实现了统计上显著较低的预测误差。然后，我们展示了一个双手绳索操作任务，FOCUS实现了数据高效的在线学习，在模拟和真实的世界。
In order to efficiently learn a dynamics model for a task in a new environment, one can adapt a model learned in a similar source environment. However, existing adaptation methods can fail when the target dataset contains transitions where the dynamics are very different from the source environment. For example, the source environment dynamics could be of a rope manipulated in free space, whereas the target dynamics could involve collisions and deformation on obstacles. Our key insight is to improve data efficiency by focusing model adaptation on only the regions where the source and target dynamics are similar. In the rope example, adapting the free-space dynamics requires significantly less data than adapting the free-space dynamics while also learning collision dynamics. We propose a new method for adaptation that is effective in adapting to regions of similar dynamics. Additionally, we combine this adaptation method with prior work on planning with unreliable dynamics to make a method for data-efficient online adaptation, called FOCUS. We first demonstrate that the proposed adaptation method achieves statistically significantly lower prediction error in regions of similar dynamics on simulated rope manipulation and plant watering tasks. We then show on a bimanual rope manipulation task that FOCUS achieves data-efficient online learning, in simulation and in the real world.