Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Journal articles
  4. Online Learning of Continuous Signed Distance Fields Using Piecewise Polynomials
 
Loading...
Thumbnail Image
research article

Online Learning of Continuous Signed Distance Fields Using Piecewise Polynomials

Maric, Ante  
•
Li, Yiming  
•
Calinon, Sylvain  
June 1, 2024
Ieee Robotics And Automation Letters

Reasoning about distance is indispensable for establishing or avoiding contact in manipulation tasks. To this end, we present an online approach for learning implicit representations of signed distance using piecewise polynomial basis functions. Starting from an arbitrary prior shape, our method incrementally constructs a continuous and smooth distance representation from incoming surface points, with analytical access to gradient information. The underlying model does not store training data for prediction, and its performance can be balanced through interpretable hyperparameters such as polynomial degree and number of segments. We assess the accuracy of the incrementally learned model on a set of household objects and compare it to neural network and Gaussian process counterparts. The utility of intermediate results and analytical gradients is further demonstrated in a physical experiment.

  • Details
  • Metrics
Type
research article
DOI
10.1109/LRA.2024.3397085
Web of Science ID

WOS:001226190400010

Author(s)
Maric, Ante  
•
Li, Yiming  
•
Calinon, Sylvain  
Date Issued

2024-06-01

Publisher

Ieee-Inst Electrical Electronics Engineers Inc

Published in
Ieee Robotics And Automation Letters
Volume

9

Issue

6

Start page

6020

End page

6026

Subjects

Technology

•

Polynomials

•

Robots

•

Computational Modeling

•

Gaussian Processes

•

Image Color Analysis

•

Vectors

•

Task Analysis

•

Signed Distance Fields

•

Incremental Learning

•

Representation Learning

•

Machine Learning For Robot Control

Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
LIDIAP  
FunderGrant Number

State Secretariat for Education, Research and Innovation

Available on Infoscience
June 19, 2024
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/208616
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés