Saved in:
Bibliographic Details
Main Authors: Tseng, Wei-Cheng, Zhang, Ellina, Jatavallabhula, Krishna Murthy, Shkurti, Florian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.09740
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917947266564096
author Tseng, Wei-Cheng
Zhang, Ellina
Jatavallabhula, Krishna Murthy
Shkurti, Florian
author_facet Tseng, Wei-Cheng
Zhang, Ellina
Jatavallabhula, Krishna Murthy
Shkurti, Florian
contents Recent advancements in learned 3D representations have enabled significant progress in solving complex robotic manipulation tasks, particularly for rigid-body objects. However, manipulating granular materials such as beans, nuts, and rice, remains challenging due to the intricate physics of particle interactions, high-dimensional and partially observable state, inability to visually track individual particles in a pile, and the computational demands of accurate dynamics prediction. Current deep latent dynamics models often struggle to generalize in granular material manipulation due to a lack of inductive biases. In this work, we propose a novel approach that learns a visual dynamics model over Gaussian splatting representations of scenes and leverages this model for manipulating granular media via Model-Predictive Control. Our method enables efficient optimization for complex manipulation tasks on piles of granular media. We evaluate our approach in both simulated and real-world settings, demonstrating its ability to solve unseen planning tasks and generalize to new environments in a zero-shot transfer. We also show significant prediction and manipulation performance improvements compared to existing granular media manipulation methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09740
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gaussian Splatting Visual MPC for Granular Media Manipulation
Tseng, Wei-Cheng
Zhang, Ellina
Jatavallabhula, Krishna Murthy
Shkurti, Florian
Robotics
Recent advancements in learned 3D representations have enabled significant progress in solving complex robotic manipulation tasks, particularly for rigid-body objects. However, manipulating granular materials such as beans, nuts, and rice, remains challenging due to the intricate physics of particle interactions, high-dimensional and partially observable state, inability to visually track individual particles in a pile, and the computational demands of accurate dynamics prediction. Current deep latent dynamics models often struggle to generalize in granular material manipulation due to a lack of inductive biases. In this work, we propose a novel approach that learns a visual dynamics model over Gaussian splatting representations of scenes and leverages this model for manipulating granular media via Model-Predictive Control. Our method enables efficient optimization for complex manipulation tasks on piles of granular media. We evaluate our approach in both simulated and real-world settings, demonstrating its ability to solve unseen planning tasks and generalize to new environments in a zero-shot transfer. We also show significant prediction and manipulation performance improvements compared to existing granular media manipulation methods.
title Gaussian Splatting Visual MPC for Granular Media Manipulation
topic Robotics
url https://arxiv.org/abs/2410.09740