Can I read Barkour: Benchmarking Animal-level Agility with Quadruped Robots on EtoBox?

Barkour: Benchmarking Animal-level Agility with Quadruped Robots by Caluwaerts, Ken; Iscen, Atil; Kew, J. Chase; Yu, Wenhao; Zhang, Tingnan; Freeman, Daniel; Lee, Kuang-Huei; Lee, Lisa; Saliceti, Stefano; Zhuang, Vincent; Batchelor, Nathan; Bohez, Steven; Casarini, Federico; Chen, Jose Enrique; Cortes, Omar; Coumans, Erwin; Dostmohamed, Adil; Dulac-Arnold, Gabriel; Escontrela, Alejandro; Frey, Erik; Hafner, Roland; Jain, Deepali; Jyenis, Bauyrjan; Kuang, Yuheng; Lee, Edward; Luu, Linda; Nachum, Ofir; Oslund, Ken; Powell, Jason; Reyes, Diego; Romano, Francesco; Sadeghi, Feresteh; Sloat, Ron; Tabanpour, Baruch; Zheng, Daniel; Neunert, Michael; Hadsell, Raia; Heess, Nicolas; Nori, Francesco; Seto, Jeff; Parada, Carolina; Sindhwani, Vikas; Vanhoucke, Vincent; Tan, Jie is a scholarly article available to read on EtoBox.

What is Barkour: Benchmarking Animal-level Agility with Quadruped Robots about?

Animals have evolved various agile locomotion strategies, such as sprinting, leaping, and jumping. There is a growing interest in developing legged robots that move like their biological counterparts and show various agile skills to navigate complex environments quickly. Despite the interest, the field lacks systematic benchmarks to measure the performance of control policies and hardware in agility. We introduce the Barkour benchmark, an obstacle course to quantify agility for legged robots. Inspired by dog agility competitions, it consists of diverse obstacles and a time based scoring mechanism. This encourages researchers to develop controllers that not only move fast, but do so in a controllable and versatile way. To set strong baselines, we present two methods for tackling the benchmark. In the first approach, we train specialist locomotion skills using on-policy reinforcement learning methods and combine them with a high-level navigation controller. In the second approach, we distill the specialist skills into a Transformer-based generalist locomotion policy, named Locomotion-Transformer, that can handle various terrains and adjust the robot's gait based on the perceived envi

Author

Caluwaerts, Ken; Iscen, Atil; Kew, J. Chase; Yu, Wenhao; Zhang, Tingnan; Freeman, Daniel; Lee, Kuang-Huei; Lee, Lisa; Saliceti, Stefano; Zhuang, Vincent; Batchelor, Nathan; Bohez, Steven; Casarini, Federico; Chen, Jose Enrique; Cortes, Omar; Coumans, Erwin; Dostmohamed, Adil; Dulac-Arnold, Gabriel; Escontrela, Alejandro; Frey, Erik; Hafner, Roland; Jain, Deepali; Jyenis, Bauyrjan; Kuang, Yuheng; Lee, Edward; Luu, Linda; Nachum, Ofir; Oslund, Ken; Powell, Jason; Reyes, Diego; Romano, Francesco; Sadeghi, Feresteh; Sloat, Ron; Tabanpour, Baruch; Zheng, Daniel; Neunert, Michael; Hadsell, Raia; Heess, Nicolas; Nori, Francesco; Seto, Jeff; Parada, Carolina; Sindhwani, Vikas; Vanhoucke, Vincent; Tan, Jie

Published

2023

Language

EN