Share Email Print

Proceedings Paper

An autonomous navigation method for intelligent virtual agent in virtual urban environment
Author(s): Qing Zhu; Litao Han; Shenghua Xu; Yeting Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper presents a dual approach of autonomous navigation for intelligent virtual agent in large complex virtual urban environments. A hierarchical global road map of the environment for global path planning is precomputed at first by using of the constrained Delauny triangulation algorithm to partition the free space, which takes into consideration the uneven feature of terrain. The accuracy of the road map may be adjusted by resizing the length of constrained segment. At runtime, A* algorithm is performed to automatically computes a collision-free and constrained path between two specified locations, and then the local navigation is realized by obtaining the environmental information immediately through visual image based 3D virtual vision. Experimental results demonstrate that the approach can provide satisfying global path and real-time obstacle avoidance effect.

Paper Details

Date Published: 28 October 2006
PDF: 7 pages
Proc. SPIE 6421, Geoinformatics 2006: Geospatial Information Technology, 642102 (28 October 2006); doi: 10.1117/12.712588
Show Author Affiliations
Qing Zhu, Wuhan Univ. (China)
Litao Han, Wuhan Univ. (China)
Shenghua Xu, Wuhan Univ. (China)
Yeting Zhang, Wuhan Univ. (China)

Published in SPIE Proceedings Vol. 6421:
Geoinformatics 2006: Geospatial Information Technology
Huayi Wu; Qing Zhu, Editor(s)

© SPIE. Terms of Use
Back to Top