Improving Rule Selection from Robot Soccer Strategy with Substrategies

Abstract : Robot Soccer is a very attractive platform in terms of research. It contains a number of challenges in the areas of robot control, artificial intelligence and image analysis. This article presents a method to improve the description of the strategy by creating substrategies in strategy and thus ensuring smoother implementation of actions defined by this strategy. In presented method we have extracted sequences of game situations from the log of a game played in our simulator, as they occurred during the game. Afterwards, these sequences were compared by methods for sequence comparison and thus we are able to visualize relations between the sequences of game situations and clusters of similar game situations in a graph. This output seems to be very helpful feedback for further strategy development.
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-01405561
Contributor : Hal Ifip <>
Submitted on : Wednesday, November 30, 2016 - 10:52:23 AM
Last modification on : Saturday, June 1, 2019 - 11:36:05 AM
Long-term archiving on : Monday, March 27, 2017 - 8:57:16 AM

File

978-3-662-45237-0_9_Chapter.pd...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Václav Svatoň, Jan Martinovič, Kateřina Slaninová, Václav Snášel. Improving Rule Selection from Robot Soccer Strategy with Substrategies. 13th IFIP International Conference on Computer Information Systems and Industrial Management (CISIM), Nov 2014, Ho Chi Minh City, Vietnam. pp.77-88, ⟨10.1007/978-3-662-45237-0_9⟩. ⟨hal-01405561⟩

Share

Metrics

Record views

53

Files downloads

225