Reinforcement Learning for Quadrupedal Dribbling in the Wild

Yandong Ji*     Gabriel B. Margolis*     Pulkit Agrawal
Improbable AI Lab
Computer Science and Artificial Intelligence Laboratory (CSAIL)
Massachusetts Institute of Technology

CoRL 2022 Workshop on Sim-to-Real Robot Learning: Locomotion and Beyond

ICRA 2023


Paper


Abstract


We present progress on a legged robotic system that can dribble a soccer ball under the same real-world conditions as humans. We identify key challenges of in-the-wild soccer ball manipulation, including variable ball motion dynamics and perception using body-mounted cameras. To overcome these challenges, we propose a domain and task specification for learning viable soccer dribbling behaviors in simulation that transfer to real fields. Our system provides promising evidence that current legged robots are physically capable and adequately sensorized for varied and dynamic real-world soccer play.


Paper


Reinforcement Learning for Quadrupedal Dribbling in the Wild
Yandong Ji*, Gabriel B. Margolis*, Pulkit Agrawal
CoRL 2022 Workshop on Sim-to-Real Robot Learning: Locomotion and Beyond
ICRA 2023
paper / project page


Dribbling maneuvers in simulation





Demonstrating soccer fetching skills in hallway





Soccer ball as a medium for human-robot interactive play





Dribbling on slope terrain







Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior
Gabriel B. Margolis, Pulkit Agrawal
Conference on Robot Learning (CoRL), 2022
paper / project page / bibtex
 
Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning
Xiaoyu Huang, Zhongyu Li*, Yanzhen Xiang, Yiming Ni, Yufeng Chi, Yunhao Li, Lizhi Yang, Xue Bin Peng, Koushil Sreenath
International Conference on Robotics and Automation (ICRA), 2023
paper / project page / bibtex
 
Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot
Yandong Ji*, Zhongyu Li*, Yinan Sun, Xue Bin Peng, Sergey Levine, Glen Berseth, Koushil Sreenath
International Conference on Intelligent Robots and Systems (IROS), 2022, (Best RoboCup Paper Award Finalist)
paper / project page / bibtex
 
Rapid Locomotion via Reinforcement Learning
Gabriel B. Margolis, Ge Yang, Kartik Paigwar, Tao Chen, Pulkit Agrawal
Robotics: Science and Systems (RSS), 2022
paper / project page / code / bibtex


Website made using this template.