iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes
Authors:
- Bokui ShenBSBokui Shen
- Fei XiaFXFei Xia
- Chengshu LiCLChengshu Li
- Roberto Martín-MartínRMRoberto Martín-Martín
- Linxi FanLFLinxi Fan
- Guanzhi WangGWGuanzhi Wang
- Claudia Pérez-D'ArpinoCPClaudia Pérez-D'Arpino
- Shyamal BuchSBShyamal Buch
- Sanjana SrivastavaSSSanjana Srivastava
- Lyne P. TchapmiLTLyne P. Tchapmi
- Micael E. TchapmiMTMicael E. Tchapmi
- Kent VainioKVKent Vainio
Preprint
Abstract
We present iGibson 1.0, a novel simulation environment to develop robotic solutions for interactive tasks in large-scale realistic scenes. Our environment contains 15 fully interactive home-sized scenes with 108 rooms populated with rigid and articulated objects. The scenes are replicas of real-world homes, with distribution and the layout of objects aligned to those of the real world. iGibson 1.0 integrates several key features to facilitate the study of interactive tasks: i) generation of high-quality virtual sensor signals (RGB, depth, segmentation, LiDAR, flow and so on), ii) domain randomization to change the materials of the objects (both visual and physical) and/or their shapes, iii) integrated sampling-based motion planners to generate collision-free trajectories for robot bases and arms, and iv) intuitive human-iGibson interface that enables efficient collection of human demonstrations. Through experiments, we show that the full interactivity of the scenes enables agents to learn useful visual representations that accelerate the training of downstream manipulation tasks. We also show that iGibson 1.0 features enable the generalization of navigation agents, and that the human-iGibson interface and integrated motion planners facilitate efficient imitation learning of human demonstrated (mobile) manipulation behaviors. iGibson 1.0 is open-source, equipped with comprehensive examples and documentation. For more information, visit our project website: http://svl.stanford.edu/igibson/Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics2021
- Shape2Motion: Joint Analysis of Motion Parts and Attributes From 3D Shapes2019
- Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks2019
- PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding2019
- Gibson Env: Real-World Perception for Embodied Agents2018
- Neural Task Programming: Learning to Generalize Across Hierarchical Tasks2018
- Matterport3D: Learning from RGB-D Data in Indoor Environments2017
- Target-driven visual navigation in indoor scenes using deep reinforcement learning2017
- RGB-D object pose estimation in unstructured environmentsRobotics and Autonomous Systems, 2016
- Intelligent bidirectional rapidly-exploring random trees for optimal motion planning in complex cluttered environmentsRobotics and Autonomous Systems, 2015