articleIEEE Robotics and Automation LettersApr 25, 2023Closed access

Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments

ETH Zurich · Nvidia (United States) · +2 more institutions

Indexed incrossref

Abstract

We present Orbit , a unified and modular framework for robot learning powered by Nvidia Isaac Sim. It offers a modular design to easily and efficiently create robotic environments with photo-realistic scenes and high-fidelity rigid and deformable body simulation. With Orbit , we provide a suite of benchmark tasks of varying difficulty– from single-stage cabinet opening and cloth folding to multi-stage tasks such as room reorganization. To support working with diverse observations and action spaces, we include fixed-arm and mobile manipulators with different physically-based sensors and motion generators. Orbit allows training reinforcement learning policies and collecting large demonstration datasets from…

Citation impact

223
total citations
FWCI
38.86
Percentile
100%
References
55
Citations per year

Authors

15

Topics & keywords

Keywords
  • Computer science
  • Artificial intelligence
  • Reinforcement learning
  • Modular design
  • Benchmark (surveying)
  • Programming language
No related works found for this paper.