Learning Finite State Machine Controllers from Motion Capture Data

Gillies, Marco. 2009. Learning Finite State Machine Controllers from Motion Capture Data. IEEE Transactions on Computational Intelligence and AI in Games, 1(1), pp. 63-72. ISSN 1943-068X [Article]

[img]
Preview
Text
fsm_preprint.pdf - Accepted Version

Download (1MB) | Preview

Abstract or Description

With characters in computer games and interactive media increasingly being based on real actors, the individuality of an actor's performance should not only be reflected in the appearance and animation of the character but also in the Artificial Intelligence that governs the character's behavior and interactions with the environment. Machine learning methods applied to motion capture data provide a way of doing this. This paper presents a method for learning the parameters of a Finite State Machine controller. The method learns both the transition probabilities of the Finite State Machine and also how to select animations based on the current state.

Item Type:

Article

Identification Number (DOI):

https://doi.org/10.1109/TCIAIG.2009.2019630

Departments, Centres and Research Units:

Computing
Research Office > REF2014

Dates:

DateEvent
2009Published

Item ID:

2290

Date Deposited:

30 Jul 2009 09:17

Last Modified:

29 Apr 2020 15:27

Peer Reviewed:

Yes, this version has been peer-reviewed.

URI:

https://research.gold.ac.uk/id/eprint/2290

View statistics for this item...

Edit Record Edit Record (login required)