TU Darmstadt / ULB / TUbiblio

Learning to Approach a Moving Ball with a Simulated Two-Wheeled Robot

Flentge, Felix
Bredenfeld, A. and Jacoff, A. and Noda, I. and Takahashi, Y. (eds.) :

Learning to Approach a Moving Ball with a Simulated Two-Wheeled Robot.
RoboCup 2005: Robot Soccer World Cup IX Springer
[Conference or Workshop Item] , (2006)

Abstract

We show how a two-wheeled robot can learn to approach a moving ball using Reinforcement Learning. The robot is controlled by setting the velocities of its two wheels. It has to reach the ball under certain conditions to be able to kick it towards a given target. In order to kick, the ball has to be in front of the robot. The robot also has to reach the ball at a certain angle in relation to the target, because the ball is always kicked in the direction from the center of the robot to the ball. The robot learns which velocity differences should be applied to the wheels: one of the wheels is set to the maximum velocity, the other one according to this difference.We apply a REINFORCE algorithm [1] in combination with some kind of extended Growing Neural Gas (GNG) [2] to learn these continuous actions. The resulting algorithm, called ReinforceGNG, is tested in a simulated environment with and without noise.

Item Type: Conference or Workshop Item
Erschienen: 2006
Editors: Bredenfeld, A. and Jacoff, A. and Noda, I. and Takahashi, Y.
Creators: Flentge, Felix
Title: Learning to Approach a Moving Ball with a Simulated Two-Wheeled Robot
Language: German
Abstract:

We show how a two-wheeled robot can learn to approach a moving ball using Reinforcement Learning. The robot is controlled by setting the velocities of its two wheels. It has to reach the ball under certain conditions to be able to kick it towards a given target. In order to kick, the ball has to be in front of the robot. The robot also has to reach the ball at a certain angle in relation to the target, because the ball is always kicked in the direction from the center of the robot to the ball. The robot learns which velocity differences should be applied to the wheels: one of the wheels is set to the maximum velocity, the other one according to this difference.We apply a REINFORCE algorithm [1] in combination with some kind of extended Growing Neural Gas (GNG) [2] to learn these continuous actions. The resulting algorithm, called ReinforceGNG, is tested in a simulated environment with and without noise.

Title of Book: RoboCup 2005: Robot Soccer World Cup IX
Publisher: Springer
Divisions: Department of Computer Science > Telecooperation
Department of Computer Science
Date Deposited: 31 Dec 2016 12:59
Identification Number: Flentge06Learning
Export:

Optionen (nur für Redakteure)

View Item View Item