Autonomous Virtual Agent Navigation in Virtual Environments Using Dempster Shafer Approach and Fuzzy Logic
This paper presents a solution for behavioural animation of autonomous virtual agent navigation in virtual environments. We focus on using Dempster-Shafer’s Theory of Evidence in developing visual sensor for virtual agent. The role of the visual sensor is to capture the information about the virtual...
Saved in:
Main Authors: | , |
---|---|
Format: | Citation Index Journal |
Published: |
Universiti Kebangsaan Malaysia
2010
|
Subjects: | |
Online Access: | http://eprints.utp.edu.my/5510/1/Jafreezal.pdf http://www.ftsm.ukm.my/ejms/publications.asp http://eprints.utp.edu.my/5510/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | This paper presents a solution for behavioural animation of autonomous virtual agent navigation in virtual environments. We focus on using Dempster-Shafer’s Theory of Evidence in developing visual sensor for virtual agent. The role of the visual sensor is to capture the information about the virtual environment or to identify which part of an obstacle can be seen from the position of the virtual agent. This information is required for virtual agent to coordinate navigation in virtual environment. The virtual agent uses fuzzy controller as a navigation system and fuzzy alpha-level for the action selection method. The testing was divided into two parts namely navigating in complex environment using different degrees of uncertainty and measuring the effectiveness of proposed action selection method to coordinate the behaviours by comparing with Fuzzy Behaviour Fusion (FBF) method. The aim of the testing was to evaluate the performance in terms of robustness and quality of path generated by the virtual agent. The result clearly demonstrates that the path produced is reasonably smooth even though there is some sharp turn and not diverted too far from the potential shortest path. This indicates the strength of our method, where more reliable and accurate paths produced during navigation task. |
---|