Title
Role-Based Teamwork Activity Recognition In Observations Of Embodied Agent Actions
Keywords
Embodied agents; Recognition; Roles; Teamwork
Abstract
Recognizing team actions in the behavior of embodied agents has many practical applications and had seen significant progress in recent years. One approach with proven results is based on HMM-based recognition of spatio-temporal patterns in the behavior of the agents. While it had been shown to work on real-world datasets, this approach was found to be brittle. In this paper we present two contributions which together can significantly increase the robustness of teamwork activity recognition. First we introduce a technique to reduce high dimensional continuous input data to a set of discrete features, which capture the essential components of the team actions. Second, we prefix the actual team action recognition with a role recognition module, which allows us to present the recognizer with arbitrarily shuffled input, and still obtain high recognition rates. We validate the improved accuracy and robustness of the team action recognizer on datasets derived from captured real world data. Copyright © 2008, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
Publication Date
1-1-2008
Publication Title
Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume
1
Number of Pages
558-565
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
84899991996 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84899991996
STARS Citation
Luotsinen, Linus J. and Bölöni, Ladislau, "Role-Based Teamwork Activity Recognition In Observations Of Embodied Agent Actions" (2008). Scopus Export 2000s. 10871.
https://stars.library.ucf.edu/scopus2000/10871