Surface estimation of a pedestrian walk for outdoor use of power wheelchair based robot

Khan, Abdul Attayyab; un Nabi, S. Riaz; Iqbal, Jamshed

Abstract

In mobile robotics, surface estimation and object recognition play vital role in navigation and control. This research presents a normal vector estimation method of a surface using Delaunay tessellation. The proposed strategy is an expansion of previously developed Continuous Nearest Neighbor Algorithm, underlining the trade-off between filtering and quality of input data. Initially, the 3D data points are segmented through a threshold process. The normal vectors are then determined based on an averaging method of centroids on Delaunay tessellation. Moreover, two similarity measures (vector angle and Euclidean distance) are considered for surface estimation of a pedestrian walk. Output from the Delaunay triangulation provides information for surface estimation. Results show that the proposed strategy has a great potential to be used for surface estimation in robotics.

Citation

Khan, A. A., un Nabi, S. R., & Iqbal, J. (2013). Surface estimation of a pedestrian walk for outdoor use of power wheelchair based robot. Life science journal, 10(3), 1697-1704

• Journal Article Type: Article
• Online Publication Date: Mar 9, 2013
• Publication Date: Jul 1, 2013
• Deposit Date: Sep 14, 2021
• Journal: Life Science Journal
• Print ISSN: 1097-8135
• Peer Reviewed: Peer Reviewed
• Volume: 10
• Issue: 3
• Article Number: 255
• Pages: 1697-1704
• Public URL: https://hull-repository.worktribe.com/output/3797198
• Publisher URL: http://www.lifesciencesite.com/lsj/life1003/255_B01849life1003_1697_1704.pdf