BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark

Nikita Chernyadev, Nicholas Backshall, Xiao Ma, Yunfan Lu, Younggyo Seo, Stephen James
Proceedings of The 8th Conference on Robot Learning, PMLR 270:4201-4217, 2025.

Abstract

We introduce BiGym, a new benchmark and learning environment for mobile bi-manual demo-driven robotic manipulation. BiGym features 40 diverse tasks set in home environments, ranging from simple target reaching to complex kitchen cleaning. To capture the real-world performance accurately, we provide human-collected demonstrations for each task, reflecting the diverse modalities found in real-world robot trajectories. BiGym supports a variety of observations, including proprioceptive data and visual inputs such as RGB, and depth from 3 camera views. To validate the usability of BiGym, we thoroughly benchmark the state-of-the-art imitation learning algorithms and demo-driven reinforcement learning algorithms within the environment and discuss the future opportunities.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-chernyadev25a, title = {BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark}, author = {Chernyadev, Nikita and Backshall, Nicholas and Ma, Xiao and Lu, Yunfan and Seo, Younggyo and James, Stephen}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {4201--4217}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/chernyadev25a/chernyadev25a.pdf}, url = {https://proceedings.mlr.press/v270/chernyadev25a.html}, abstract = {We introduce BiGym, a new benchmark and learning environment for mobile bi-manual demo-driven robotic manipulation. BiGym features 40 diverse tasks set in home environments, ranging from simple target reaching to complex kitchen cleaning. To capture the real-world performance accurately, we provide human-collected demonstrations for each task, reflecting the diverse modalities found in real-world robot trajectories. BiGym supports a variety of observations, including proprioceptive data and visual inputs such as RGB, and depth from 3 camera views. To validate the usability of BiGym, we thoroughly benchmark the state-of-the-art imitation learning algorithms and demo-driven reinforcement learning algorithms within the environment and discuss the future opportunities.} }
Endnote
%0 Conference Paper %T BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark %A Nikita Chernyadev %A Nicholas Backshall %A Xiao Ma %A Yunfan Lu %A Younggyo Seo %A Stephen James %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-chernyadev25a %I PMLR %P 4201--4217 %U https://proceedings.mlr.press/v270/chernyadev25a.html %V 270 %X We introduce BiGym, a new benchmark and learning environment for mobile bi-manual demo-driven robotic manipulation. BiGym features 40 diverse tasks set in home environments, ranging from simple target reaching to complex kitchen cleaning. To capture the real-world performance accurately, we provide human-collected demonstrations for each task, reflecting the diverse modalities found in real-world robot trajectories. BiGym supports a variety of observations, including proprioceptive data and visual inputs such as RGB, and depth from 3 camera views. To validate the usability of BiGym, we thoroughly benchmark the state-of-the-art imitation learning algorithms and demo-driven reinforcement learning algorithms within the environment and discuss the future opportunities.
APA
Chernyadev, N., Backshall, N., Ma, X., Lu, Y., Seo, Y. & James, S.. (2025). BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:4201-4217 Available from https://proceedings.mlr.press/v270/chernyadev25a.html.

Related Material