TY - GEN
T1 - Multi-objective genetic algorithm-based gesture recognition and its application in human-robot interaction
AU - Chen, Luefeng
AU - Zhou, Mengtian
AU - Shi, Wei
AU - Xu, Yirui
AU - Wu, Jianguo
AU - Liao, Cheng
AU - Wu, Min
AU - She, Jinhua
AU - Hirota, Kaoru
N1 - Publisher Copyright:
© 2016, Fuji Technology Press. All rights reserved.
PY - 2016
Y1 - 2016
N2 - A multi-objective genetic algorithm is proposed for gesture recognition in human-robot interaction, where robotic arm is moved according to the human gesture, and multi-objective genetic algorithm is used to optimize the tracking path of the steering gear. It aims to optimize the process of mutual conflict, mutual control objects, and a set of optimal solutions can be obtained by imitating the process of biological evolution mechanism more intelligently. To evaluate the optimal tracking path of the target steering gear, simulation is established by using MATLAB and the robotic arm. Kinect collection of human arm position information, simulation of the robot arm can follow the human arm to reach the corresponding position. Results show that the proposal is excellent in optimize the tracking path in 50 iterations (2.5s) based on the proposal. Preliminary application experiment is done in the real robotic arm, where the robotic arm can make vertical, bending and horizontal movements successively according to human arm. Based on the simulation and application experiments, the proposal is being transplanted and extended to gesture recognition and action of mobile robot.
AB - A multi-objective genetic algorithm is proposed for gesture recognition in human-robot interaction, where robotic arm is moved according to the human gesture, and multi-objective genetic algorithm is used to optimize the tracking path of the steering gear. It aims to optimize the process of mutual conflict, mutual control objects, and a set of optimal solutions can be obtained by imitating the process of biological evolution mechanism more intelligently. To evaluate the optimal tracking path of the target steering gear, simulation is established by using MATLAB and the robotic arm. Kinect collection of human arm position information, simulation of the robot arm can follow the human arm to reach the corresponding position. Results show that the proposal is excellent in optimize the tracking path in 50 iterations (2.5s) based on the proposal. Preliminary application experiment is done in the real robotic arm, where the robotic arm can make vertical, bending and horizontal movements successively according to human arm. Based on the simulation and application experiments, the proposal is being transplanted and extended to gesture recognition and action of mobile robot.
KW - Gesture recognition
KW - Human-robot interaction
KW - Multi-objective genetic algorithm
UR - http://www.scopus.com/inward/record.url?scp=84997822259&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84997822259
T3 - ISCIIA 2016 - 7th International Symposium on Computational Intelligence and Industrial Applications
BT - ISCIIA 2016 - 7th International Symposium on Computational Intelligence and Industrial Applications
PB - Fuji Technology Press
T2 - 7th International Symposium on Computational Intelligence and Industrial Applications, ISCIIA 2016
Y2 - 3 November 2016 through 6 November 2016
ER -