DribbleBot: Dynamic Legged Manipulation in the Wild

Yandong Ji, Gabriel B. Margolis, Pulkit Agrawal
4/3/2023
cs.ROcs.AIcs.LG

No official code found. Best implementation: Improbable-AI/dribblebot (141 stars, last commit 2023-10-25).

Abstract

DribbleBot (Dexterous Ball Manipulation with a Legged Robot) is a legged robotic system that can dribble a soccer ball under the same real-world conditions as humans (i.e., in-the-wild). We adopt the paradigm of training policies in simulation using reinforcement learning and transferring them into the real world. We overcome critical challenges of accounting for variable ball motion dynamics on different terrains and perceiving the ball using body-mounted cameras under the constraints of onboard computing. Our results provide evidence that current quadruped platforms are well-suited for studying dynamic whole-body control problems involving simultaneous locomotion and manipulation directly from sensory observations.

View on arXivView PDF

Code Implementations(1)

Code release accompanying DribbleBot: Dynamic Legged Manipulation in the Wild

14116PythonMar 20, 20232 years agoNOASSERTION
reinforcement-learningrobot-soccerunitree

Similar Papers

Cite this paper

@article{ji2023dribblebot,
  title  = {DribbleBot: Dynamic Legged Manipulation in the Wild},
  author = {Yandong Ji and Gabriel B. Margolis and Pulkit Agrawal},
  year   = {2023},
  eprint = {2304.01159},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.01159v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2304.01159.svg)](https://codeofpaper.com/paper/2304.01159)

Discussion