The Design of the Barkour Benchmark for Robot Agility
In this paper, we describe the design of the Barkour benchmark for measuring robot agility in navigating complex environments. Despite the growing interest in developing agile robot locomotion skills, the field lacks systematic benchmarks to measure the performance of robotic control systems and hardware in agility-focused tasks. This motivated us to propose the Barkour benchmark, an obstacle course designed to quantify agility across various robotic platforms. Inspired by dog agility competitions, the course features diverse obstacles and a time-based scoring mechanism, encouraging researchers to develop controllers that enable robots to move quickly, precisely, and with adaptability. This benchmark is challenging as it demands diverse motion skills and the time-based scoring requires control precision at high speed. Along with the design details presented in the paper, we release our simulated environment setups in MuJoCo-XLA and the CAD model of a custom-designed quadruped robot to facilitate future research to reproduce the Barkour setup (available at sites.google.com/view/barkour). We hope these together will accelerate the pace of robot agility research.
Authors
- Fereshteh Sadeghi (ORCID: https://orcid.org/0000-0003-4058-5261)
- Gabriel Dulac-Arnold
- Nathan Batchelor
- Yuheng Kuang (ORCID: https://orcid.org/0009-0005-3185-3836)
- Vincent Vanhoucke (ORCID: https://orcid.org/0000-0003-0544-2791)
- J. Chase Kew
- Zhichao Zheng (ORCID: https://orcid.org/0000-0002-4848-0862)
- Atıl Işçen
- Kuang-Huei Lee
- Deepali Jain (ORCID: https://orcid.org/0000-0001-5315-9814)
- Roland Hafner (ORCID: https://orcid.org/0000-0001-8061-8828)
- Steven Bohez
- Federico Casarini
- Daniel Freeman (ORCID: https://orcid.org/0000-0002-2541-2197)
- Francesco ROMANO (ORCID: https://orcid.org/0000-0002-1865-6396)
- José Enrique Chen
- Alejandro Escontrela
- Stefano Saliceti
- Baruch Tabanpour
- Michael Neunert (ORCID: https://orcid.org/0000-0003-2080-8376)
- Ofir Nachum
- Vikas Sindhwani
- Erik Frey
- Nicolas Heess (ORCID: https://orcid.org/0000-0001-7876-9256)
- Francesco Nori (ORCID: https://orcid.org/0000-0003-3763-6873)
- Ken Caluwaerts
- Vincent Zhuang (ORCID: https://orcid.org/0009-0007-2931-3069)
- Raia Hadsell (ORCID: https://orcid.org/0000-0002-2390-1771)
- Tingnan Zhang
- Ken Oslund
- Erwin Coumans (ORCID: https://orcid.org/0000-0001-6695-3400)
- Carolina Parada (ORCID: https://orcid.org/0009-0000-7772-4646)
- Adil Dostmohamed
- Bauyrjan Jyenis
- Edward Lee (ORCID: https://orcid.org/0000-0002-5708-2866)
- Lisa Lee (ORCID: https://orcid.org/0000-0001-5058-9464)
- Wenhao Yu (ORCID: https://orcid.org/0000-0002-6052-0839)
- Jie Tan (ORCID: https://orcid.org/0000-0002-7947-0333)
- Jeff Seto
Institutions
- Google (United States) (US)
- Google DeepMind (United Kingdom) (GB)
Publication Details
- Published
- 2024-10-14
- DOI
- https://doi.org/10.1109/iros58592.2024.10801377
- Citations
- 1
- Primary Topic
- Digital Transformation in Industry
- Type
- article
- Field-Weighted Citation Impact
- 0.35
Funders
- DeepMind