Saved in:
Bibliographic Details
Main Authors: Kumar, Abhinav, Mitrano, Peter, Berenson, Dmitry
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.00157
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917791923175424
author Kumar, Abhinav
Mitrano, Peter
Berenson, Dmitry
author_facet Kumar, Abhinav
Mitrano, Peter
Berenson, Dmitry
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00157
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Constraining Gaussian Process Implicit Surfaces for Robot Manipulation via Dataset Refinement
Kumar, Abhinav
Mitrano, Peter
Berenson, Dmitry
Robotics
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.
title Constraining Gaussian Process Implicit Surfaces for Robot Manipulation via Dataset Refinement
topic Robotics
url https://arxiv.org/abs/2410.00157