Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Minseok, Ha, JeongHo, Park, Bonggyeong, Park, Daehyung
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910924689899520
author Song, Minseok
Ha, JeongHo
Park, Bonggyeong
Park, Daehyung
author_facet Song, Minseok
Ha, JeongHo
Park, Bonggyeong
Park, Daehyung
contents We aim to solve the problem of manipulating deformable objects, particularly elastic bands, in real-world scenarios. However, deformable object manipulation (DOM) requires a policy that works on a large state space due to the unlimited degree of freedom (DoF) of deformable objects. Further, their dense but partial observations (e.g., images or point clouds) may increase the sampling complexity and uncertainty in policy learning. To figure it out, we propose a novel implicit neural-representation (INR) learning for elastic DOMs, called INR-DOM. Our method learns consistent state representations associated with partially observable elastic objects reconstructing a complete and implicit surface represented as a signed distance function. Furthermore, we perform exploratory representation fine-tuning through reinforcement learning (RL) that enables RL algorithms to effectively learn exploitable representations while efficiently obtaining a DOM policy. We perform quantitative and qualitative analyses building three simulated environments and real-world manipulation studies with a Franka Emika Panda arm. Videos are available at http://inr-dom.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00500
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulations
Song, Minseok
Ha, JeongHo
Park, Bonggyeong
Park, Daehyung
Robotics
Machine Learning
We aim to solve the problem of manipulating deformable objects, particularly elastic bands, in real-world scenarios. However, deformable object manipulation (DOM) requires a policy that works on a large state space due to the unlimited degree of freedom (DoF) of deformable objects. Further, their dense but partial observations (e.g., images or point clouds) may increase the sampling complexity and uncertainty in policy learning. To figure it out, we propose a novel implicit neural-representation (INR) learning for elastic DOMs, called INR-DOM. Our method learns consistent state representations associated with partially observable elastic objects reconstructing a complete and implicit surface represented as a signed distance function. Furthermore, we perform exploratory representation fine-tuning through reinforcement learning (RL) that enables RL algorithms to effectively learn exploitable representations while efficiently obtaining a DOM policy. We perform quantitative and qualitative analyses building three simulated environments and real-world manipulation studies with a Franka Emika Panda arm. Videos are available at http://inr-dom.github.io.
title Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulations
topic Robotics
Machine Learning
url https://arxiv.org/abs/2505.00500