Kick extraction for reducing uncertainty in RoboCup logs

Tomoharu Nakashima*, Satoshi Mifune, Jordan Henrio, Oliver Obst, Peter Wang, Mikhail Prokopenko

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

2 Citations (Scopus)


The effectiveness of using log information in RoboCup soccer simulation 2D league is shown in this paper. Although it is not possible to exactly know a strategy that a team is taking, that strategy is well represented by how the players in the team kick during games. Extracted kicks such as passes and dribbles form a kick distribution, which hopefully represent the team’ strategy. In order to show the usefulness of the kick distribution, a series of computational experiments are conducted where the uncertainty in predicting the game results is reduced by grouping the games based on the kick distributions.

Original languageEnglish
Title of host publicationHuman interface and the management of information
Subtitle of host publicationInformation and knowledge in context
EditorsSakae Yamamoto
Place of PublicationCham, Switzerland
PublisherSpringer, Springer Nature
Number of pages12
ISBN (Electronic)9783319206189
ISBN (Print)9783319206172
Publication statusPublished - 2015
Externally publishedYes
Event17th International Conference on Human-Computer Interaction, HCI International 2015 - Los Angeles, United States
Duration: 2 Aug 20157 Aug 2015

Publication series

NameLecture Notes in Computer Science
PublisherSpringer International Publishing
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Other17th International Conference on Human-Computer Interaction, HCI International 2015
Country/TerritoryUnited States
CityLos Angeles


  • clustering
  • Earth Mover’s Distance (EMD)
  • feature extraction
  • RoboCup
  • strategy analysis


Dive into the research topics of 'Kick extraction for reducing uncertainty in RoboCup logs'. Together they form a unique fingerprint.

Cite this