Share Email Print

Proceedings Paper

Development of dog-like retrieving capability in a ground robot
Author(s): Douglas C. MacKenzie; Rahul Ashok; James M. Rehg; Gary Witus
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 the Mobile Intelligence Team's approach to addressing the CANINE outdoor ground robot competition. The competition required developing a robot that provided retrieving capabilities similar to a dog, while operating fully autonomously in unstructured environments. The vision team consisted of Mobile Intelligence, the Georgia Institute of Technology, and Wayne State University. Important computer vision aspects of the project were the ability to quickly learn the distinguishing characteristics of novel objects, searching images for the object as the robot drove a search pattern, identifying people near the robot for safe operations, correctly identify the object among distractors, and localizing the object for retrieval. The classifier used to identify the objects will be discussed, including an analysis of its performance, and an overview of the entire system architecture presented. A discussion of the robot's performance in the competition will demonstrate the system’s successes in real-world testing.

Paper Details

Date Published: 4 February 2013
PDF: 15 pages
Proc. SPIE 8662, Intelligent Robots and Computer Vision XXX: Algorithms and Techniques, 86620M (4 February 2013); doi: 10.1117/12.2010679
Show Author Affiliations
Douglas C. MacKenzie, Mobile Intelligence Corp. (United States)
Rahul Ashok, Georgia Institute of Technology (United States)
James M. Rehg, Georgia Institute of Technology (United States)
Gary Witus, Turing Associates, Inc. (United States)

Published in SPIE Proceedings Vol. 8662:
Intelligent Robots and Computer Vision XXX: Algorithms and Techniques
Juha Röning; David Casasent, Editor(s)

© SPIE. Terms of Use
Back to Top