Title :
Seeing, understanding and doing human task
Author :
Kuniyoshi, Yasuo ; Inaba, Masayuki ; Inoue, Hirochika
Author_Institution :
Electrotech. Lab., Ibaraki, Japan
Abstract :
Functional units and working algorithms for real-time visual recognition of human pick-and-place action sequences are presented. The action recognizer consists of visual feature detectors, an action/environment model, and an attention stack. It generates a symbolic description of the observed action sequence. Given a different initial state, the system reinstantiates the recognized action sequence to carry out an equivalent assembly task. Experimental results on several assembly tasks support the effectiveness of the method
Keywords :
assembling; automatic programming; image recognition; real-time systems; robot programming; action sequence; action/environment model; assembly task; attention stack; functional units; human pick-and-place action sequences; real-time visual recognition; reinstantiation; symbolic description; visual feature detectors; Assembly systems; Computer vision; Detectors; Humans; Intelligent robots; Intelligent systems; Laboratories; Manipulator dynamics; Real time systems; Robotic assembly;
Conference_Titel :
Robotics and Automation, 1992. Proceedings., 1992 IEEE International Conference on
Conference_Location :
Nice
Print_ISBN :
0-8186-2720-4
DOI :
10.1109/ROBOT.1992.220342
