TY - GEN
T1 - Development of dog-like retrieving capability in a ground robot
AU - MacKenzie, Douglas C.
AU - Ashok, Rahul
AU - Rehg, James M.
AU - Witus, Gary
PY - 2013
Y1 - 2013
N2 - 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.
AB - 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.
KW - autonomy
KW - CANINE
KW - computer vision
KW - object recognition
KW - unmanned ground vehicle
UR - http://www.scopus.com/inward/record.url?scp=84875898732&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84875898732&partnerID=8YFLogxK
U2 - 10.1117/12.2010679
DO - 10.1117/12.2010679
M3 - Conference contribution
AN - SCOPUS:84875898732
SN - 9780819494351
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Proceedings of SPIE-IS and T Electronic Imaging - Intelligent Robots and Computer Vision XXX
T2 - Intelligent Robots and Computer Vision XXX: Algorithms and Techniques
Y2 - 4 February 2013 through 6 February 2013
ER -