Skip to main content Skip to secondary navigation
Journal Article

iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks

iG2

Recent research in embodied AI has been boosted by the use of simula- tion environments to develop and train robot learning approaches. However, the use of simulation has skewed the attention to tasks that only require what robotics simulators can simulate: motion and physical contact. We present iGibson 2.0, an open-source simulation environment that supports the simulation of a more diverse set of household tasks through three key innovations. First, iGibson 2.0 supports object states, including temperature, wetness level, cleanliness level, and toggled and sliced states, necessary to cover a wider range of tasks. Second, iGibson 2.0 implements a set of predicate logic functions that map the simulator states to logic states like Cooked or Soaked. Additionally, given a logic state, iGibson 2.0 can sample valid physical states that satisfy it. This functionality can generate poten- tially infinite instances of tasks with minimal effort from the users. The sampling mechanism allows our scenes to be more densely populated with small objects in semantically meaningful locations. Third, iGibson 2.0 includes a virtual reality (VR) interface to immerse humans in its scenes to collect demonstrations. As a result, we can collect demonstrations from humans on these new types of tasks, and use them for imitation learning. We evaluate the new capabilities of iGibson 2.0 to enable robot learning of novel tasks, in the hope of demonstrating the potential of this new simulator to support new directions of research in embodied AI. iGibson 2.0 and its new dataset are publicly available at http://svl.stanford.edu/igibson/.

Paper   Code   Video

Author(s)
Chengshu Li
Fei Xia
Roberto Martin-Martin
Michael Lingelbach
Sanjana Srivastava
Bokui Shen
Kent Elliot Vainio
Cem Gokmen
Gokul Dharan
Tanish Jain
Andrey Kurenkov
C. Karen Liu
Hyowon Gweon
Jiajun Wu
Li Fei-Fei
Silvio Savarese
Journal Name
Conference on Robot Learning (CoRL), 2021
Publication Date
November, 2021