BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929417460121600 |
|---|---|
| author | Chernyadev, Nikita Backshall, Nicholas Ma, Xiao Lu, Yunfan Seo, Younggyo James, Stephen |
| author_facet | Chernyadev, Nikita Backshall, Nicholas Ma, Xiao Lu, Yunfan Seo, Younggyo James, Stephen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07788 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark Chernyadev, Nikita Backshall, Nicholas Ma, Xiao Lu, Yunfan Seo, Younggyo James, Stephen Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning 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. |
| title | BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2407.07788 |