机械专业外文翻译模板.docxVIP

International Journal of Control, Automation, and Systems (2014) 12(4):870-877ISSN:1598-6446 eISSN:2005-4092DOI 10.1007/s12555-013-0275-6/12555Humanoid Robot Arm Performance Optimization usingMulti Objective Evolutionary AlgorithmZulkifli Mohamed*, Mitsuki Kitani, Shin-ichiro Kaneko, and Genci CapiAbstract: As humanoid robots are expected to operate in human environments they are expected to perform a wide range of tasks. Therefore, the robot arm motion must be generated based on the specif-ic task. In this paper we propose an optimal arm motion generation satisfying multiple criteria. In our method, we evolved neural controllers that generate the humanoid robot arm motion satisfying three different criteria; minimum time, minimum distance and minimum acceleration. The robot hand is re-quired to move from the initial to the final goal position. In order to compare the performance, single objective GA is also considered as an optimization tool. Selected neural controllers from the Pareto so-lution are implemented and their performance is evaluated. Experimental investigation shows that the evolved neural controllers performed well in the real hardware of the mobile humanoid robot platform.Keywords: Genetic algorithm, mobile humanoid robot, multi-objective evolutionary algorithm, robot arm motion generation.1. INTRODUCTIONDuring everyday task performance, humans move their arms in different ways satisfying different constraints. For example, to move a cup of coffee, human arm need to move such as to minimize the acceleration in order not to spill the coffee. For more complicated tasks such as drawing a straight line or pushing a non-rigid object, the kinematics constraints such as velocity and acceleration are required to be decreased resulting in a longer execution time. Such scenarios inspired researchers to adapt the similar approach in generating robot hand motion for specific tasks.For a robot hand to have a human like motion, similar characteristics and approac