What is BEHAVIOR-1K?
BEHAVIOR-1K is a comprehensive simulation benchmark for human-centered robotics. Compared to its predecessor, BEHAVIOR-100, this new benchmark is more grounded on actual human needs: the 1,000 activities come from the results of an extensive survey on “what do you want robots to do for you?”. It is more diverse in the type of scenes, objects, and activities. Powered by NVIDIA’s Omniverse, BEHAVIOR-1K also achieves a new level of realism in rendering and physics simulation. We hope that BEHAVIOR-1K’s human-grounded nature, diversity, and realism make it valuable for embodied AI and robot learning research.
The BEHAVIOR-1K beta release is now available! This release features a subset of activities and examples picked to showcase BEHAVIOR-1K activity diversity and OmniGibson capabilities. Get started!
- BEHAVIOR-1K: A Benchmark for Embodied AI with 1,000 Everyday Activities and Realistic Simulation. Chengshu Li*, Ruohan Zhang*, Josiah Wong*, Cem Gokmen*, Sanjana Srivastava*, Roberto Martín-Martín*, Chen Wang*, Gabrael Levine*, Michael Lingelbach, Jiankai Sun, Mona Anvari, Minjune Hwang, Manasi Sharma, Arman Aydin, Dhruva Bansal, Samuel Hunter, Kyu-Young Kim, Alan Lou, Caleb R Matthews, Ivan Villa-Renteria, Jerry Huayang Tang, Claire Tang, Fei Xia, Silvio Savarese, Hyowon Gweon, Karen Liu, Jiajun Wu, Li Fei-Fei, Conference on Robot Learning (CoRL) 2022.
Building blocks of BEHAVIOR-1K
BEHAVIOR-1K includes two components. The first is the definition of 1,000 everyday activities, grounded in 50 scenes (houses, gardens, restaurants, offices, etc.) with more than 5,000 objects annotated with rich physical and semantic properties. The second is OmniGibson (based on Nvidia’s Omniverse), a novel simulation environment that supports these activities via realistic physics simulation and rendering of rigid bodies, deformable bodies, and liquids.
You can follow installation guide to start using BEHAVIOR-1K for your research. The main components are: