Multi-Cue 3D Object Recognition in Knowledge-Based Vision.pdfVIP

Proceedings of the 2007 IEEE/RSJ International ThB2.1 Conference on Intelligent Robots and Systems San Diego, CA, USA, Oct 29 - Nov 2, 2007 Multi-cue 3D Object Recognition in Knowledge-based Vision-guided Humanoid Robot System Kei Okada, Mitsuharu Kojima, Satoru Tokutsu, Toshiaki Maki, Yuto Mori, Masayuki Inaba Abstract— A vision based object recognition subsystem on knowledge-based humanoid robot system is presented. Hu- manoid robot system for real world service application must in- tegrate an object recognition subsystem and a motion planning subsystem in both mobility and manipulation tasks. These re- quirements involve the vision system capable of self-localization for navigation tasks and object recognition for manipulation tasks, while communicating with the motion planning subsys- tem. In this paper, we describe a design and implementation of knowledge based visual 3D object recognition system with multi-cue integration using particle filter technique. The parti- cle filter provides very robust object recognition performance and knowledge based approach enables robot to perform both object localization and self localization with movable/fixed information. Since this object recognition subsystem share knowledge with a motion planning subsystem, we are able to generate vision-guided humanoid behaviors without considering visual processing functions. Finally, in order to demonstrate the generality of the system, we demonstrated several vision-based humanoid behavior experiments in a daily life environment. Fig. 1. Behavior example of knowledge based vision guided humanoid