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.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Douglas C. MacKenzie ; Rahul Ashok ; James M. Rehg and Gary Witus
Development of dog-like retrieving capability in a ground robot
", Proc. SPIE 8662, Intelligent Robots and Computer Vision XXX: Algorithms and Techniques, 86620M (February 4, 2013); doi:10.1117/12.2010679; http://dx.doi.org/10.1117/12.2010679