Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911868018229248 |
|---|---|
| author | Chuck, Caleb Qi, Carl Munje, Michael J. Li, Shuozhe Rudolph, Max Shi, Chang Agarwal, Siddhant Sikchi, Harshit Peri, Abhinav Dayal, Sarthak Kuo, Evan Mehta, Kavan Wang, Anthony Stone, Peter Zhang, Amy Niekum, Scott |
| author_facet | Chuck, Caleb Qi, Carl Munje, Michael J. Li, Shuozhe Rudolph, Max Shi, Chang Agarwal, Siddhant Sikchi, Harshit Peri, Abhinav Dayal, Sarthak Kuo, Evan Mehta, Kavan Wang, Anthony Stone, Peter Zhang, Amy Niekum, Scott |
| contents | Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might fail. To effectively reflect this challenging category of tasks, we introduce a dynamic, interactive RL testbed based on robot air hockey. By augmenting air hockey with a large family of tasks ranging from easy tasks like reaching, to challenging ones like pushing a block by hitting it with a puck, as well as goal-based and human-interactive tasks, our testbed allows a varied assessment of RL capabilities. The robot air hockey testbed also supports sim-to-real transfer with three domains: two simulators of increasing fidelity and a real robot system. Using a dataset of demonstration data gathered through two teleoperation systems: a virtualized control environment, and human shadowing, we assess the testbed with behavior cloning, offline RL, and RL from scratch. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_03113 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning Chuck, Caleb Qi, Carl Munje, Michael J. Li, Shuozhe Rudolph, Max Shi, Chang Agarwal, Siddhant Sikchi, Harshit Peri, Abhinav Dayal, Sarthak Kuo, Evan Mehta, Kavan Wang, Anthony Stone, Peter Zhang, Amy Niekum, Scott Robotics Artificial Intelligence Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might fail. To effectively reflect this challenging category of tasks, we introduce a dynamic, interactive RL testbed based on robot air hockey. By augmenting air hockey with a large family of tasks ranging from easy tasks like reaching, to challenging ones like pushing a block by hitting it with a puck, as well as goal-based and human-interactive tasks, our testbed allows a varied assessment of RL capabilities. The robot air hockey testbed also supports sim-to-real transfer with three domains: two simulators of increasing fidelity and a real robot system. Using a dataset of demonstration data gathered through two teleoperation systems: a virtualized control environment, and human shadowing, we assess the testbed with behavior cloning, offline RL, and RL from scratch. |
| title | Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2405.03113 |