arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.00157cs.RO

通过数据集精化约束高斯过程隐式曲面以实现机器人操作

Constraining Gaussian Process Implicit Surfaces for Robot Manipulation via Dataset Refinement

University of Michigan(密歇根大学)

Abhinav Kumar, Peter Mitrano, Dmitry Berenson

AI总结:

本文提出COGIS方法,通过视觉与状态跟踪推断接触数据并拟合带约束的GPIS来在线识别未观测障碍物,进而结合MPC完成销孔插入和可变形物体操作任务,在真实线缆操作中成功率显著优于基线。

摘要:

基于模型的控制在部分可观测环境中由于未建模的障碍物而面临根本性挑战。我们提出一种在线学习与优化方法,用于在线识别并避开未观测到的障碍物。我们的方法称为约束服从高斯隐式曲面(Constraint Obeying Gaussian Implicit Surfaces,COGIS),利用视觉输入与状态跟踪的组合,并结合标称动力学模型的预测来推断接触数据。然后,我们对这些数据拟合高斯过程隐式曲面(GPIS),并通过一种在估计曲面上施加约束的新方法对数据集进行精化。这使我们能够设计一种模型预测控制(MPC)方法,利用障碍物估计来完成多项操作任务。通过对环境进行建模,而不是尝试直接调整动力学,我们的方法在低维度的销孔插入任务和高维度的可变形物体操作任务中均取得了成功。在环境部分可观测条件下的真实世界线缆操作任务中,我们的方法在10次试验中成功10次,而基线方法仅成功1次。

英文摘要:

Model-based control faces fundamental challenges in partially-observable environments due to unmodeled obstacles. We propose an online learning and optimization method to identify and avoid unobserved obstacles online. Our method, Constraint Obeying Gaussian Implicit Surfaces (COGIS), infers contact data using a combination of visual input and state tracking, informed by predictions from a nominal dynamics model. We then fit a Gaussian process implicit surface (GPIS) to these data and refine the dataset through a novel method of enforcing constraints on the estimated surface. This allows us to design a Model Predictive Control (MPC) method that leverages the obstacle estimate to complete multiple manipulation tasks. By modeling the environment instead of attempting to directly adapt the dynamics, our method succeeds at both low-dimensional peg-in-hole tasks and high-dimensional deformable object manipulation tasks. Our method succeeds in 10/10 trials vs 1/10 for a baseline on a real-world cable manipulation task under partial observability of the environment.

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。

↑