用约束高斯过程表面在线识别隐藏障碍，提升机器人操作可靠性
Constraining Gaussian Process Implicit Surfaces for Robot Manipulation via Dataset Refinement
- 结合视觉与状态追踪，用高斯过程建模未知障碍物表面
- 在10次真实电缆操作中成功10次，基线仅成功1次
- 适合需在部分可观测环境中执行复杂抓取任务的机器人系统
基于模型的控制在部分可观测环境下因未建模障碍物而面临挑战。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。所提方法约束遵守高斯隐式表面（COGIS）通过结合视觉输入与状态跟踪，利用名义动力学模型的预测推断接触数据，再将这些数据拟合为高斯过程隐式表面（GPIS），并通过一种新型约束强化方法对估计表面进行数据集精炼。该方法支持设计基于模型预测控制（MPC）的障碍物规避策略，可完成多种操纵任务。通过建模环境而非直接调整动力学，本方法在低维插销任务和高维柔体物体操纵任务中均取得成功。在环境部分不可见条件下，真实世界电缆操纵任务中成功率10/10，基线仅为1/10。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。