neural networks research group
areas
people
projects
demos
publications
software/data
Learning Powerful Kicks on the Aibo ERS-7: The Quest for a Striker (2010)
Matthew Hausknecht
and
Peter Stone
Coordinating complex motion sequences remains a challenging task for robotics. Machine Learning has aided this process, successfully improving motion sequences such as walking and grasping. However, to the best of our knowledge, outside of simulation, learning has never been applied to the task of kicking the ball. We apply machine learning methods to optimize kick power entirely on a real robot. The resulting learned kick is significantly more powerful than the most powerful hand-coded kick of one of the most successful RoboCup four-legged league teams, and is learned in a principled manner which requires very little engineering of the parameter space. Finally, model inversion is applied to the problem of creating a parameterized kick capable of kicking the ball a specified distance.
View:
PDF
,
PS
,
HTML
Citation:
In
Robocup International Symposium
, 2010.
Bibtex:
@inproceedings{hausknecht:robocup10, title={Learning Powerful Kicks on the Aibo ERS-7: The Quest for a Striker}, author={Matthew Hausknecht and Peter Stone}, booktitle={Robocup International Symposium}, url="http://nn.cs.utexas.edu/?hausknecht:robocup10", year={2010} }
People
Matthew Hausknecht
Former Collaborator
mhauskn [at] cs utexas edu
Peter Stone
pstone [at] cs utexas edu
Areas of Interest
Machine Learning
Quadruped Robots
RoboCup
Robot Soccer