UBSoft: A Simulation Platform for Robotic Skill Learning in Unbounded Soft Environments

TL;DR

UBSoft is a novel simulation platform enabling efficient robot skill learning in unbounded soft environments by dynamically adjusting simulation resolution, reducing computational costs, and supporting large-scale soft material interactions.

Contribution

The paper introduces UBSoft, a simulation platform with adaptive resolution for large-scale soft environments, facilitating broader soft material interaction studies and robot skill learning.

Findings

Sampling-based trajectory optimization outperforms gradient-based methods.

The platform reduces storage and computation costs significantly.

Real-world experiments validate simulation-to-reality transfer.

Abstract

It is desired to equip robots with the capability of interacting with various soft materials as they are ubiquitous in the real world. While physics simulations are one of the predominant methods for data collection and robot training, simulating soft materials presents considerable challenges. Specifically, it is significantly more costly than simulating rigid objects in terms of simulation speed and storage requirements. These limitations typically restrict the scope of studies on soft materials to small and bounded areas, thereby hindering the learning of skills in broader spaces. To address this issue, we introduce UBSoft, a new simulation platform designed to support unbounded soft environments for robot skill acquisition. Our platform utilizes spatially adaptive resolution scales, where simulation resolution dynamically adjusts based on proximity to active robotic agents. Our framework markedly reduces the demand for extensive storage space and computation costs required for large-scale scenarios involving soft materials. We also establish a set of benchmark tasks in our platform, including both locomotion and manipulation tasks, and conduct experiments to evaluate the efficacy of various reinforcement learning algorithms and trajectory optimization techniques, both gradient-based and sampling-based. Preliminary results indicate that sampling-based trajectory optimization generally achieves better results for obtaining one trajectory to solve the task. Additionally, we conduct experiments in real-world environments to demonstrate that advancements made in our UBSoft simulator could translate to improved robot interactions with large-scale soft material. More videos can be found at https://vis-www.cs.umass.edu/ubsoft/.