Extraction of Robot Primitive Control Rules from Natural Language Instructions

作     者：Guang-Hong Wang Ping Jiang Zu-Ren Feng 

作者机构：Department of Information and Control Engineering Tongji University Shanghai 200092 China Department of Cybernetics and Virtual Systems University of Bradford Bradford BD7 1DP UK Department of Information and Control Engineering Tongji University Shanghai200092 China Systems Engineering Institute Xi＇an Jiaotong University Xi＇an 710049 China 

出 版 物：《International Journal of Automation and computing》 (国际自动化与计算杂志（英文版）)

年 卷 期：2006年第3卷第3期

页      面：282-290页

学科分类：08[工学] 0835[工学-软件工程] 0802[工学-机械工程] 080201[工学-机械制造及其自动化] 

基　　金：This work was partially supported by the Royal Society of UK and the National Natural Science Foundation of PRC (No. 60175028) 

主　　题：Support vector machines (SVMs) fuzzy neural networks motion primitives motion controller language instruction based training natural language programming. 

摘      要：A support vector rule based method is investigated for the construction of motion controllers via natural language training. It is a two-phase process including motion control information collection from natural language instructions, and motion information condensation with the aid of support vector machine （SVM） theory. Self-organizing fuzzy neural networks are utilized for the collection of control rules, from which support vector rules are extracted to form a final controller to achieve any given control accuracy. In this way, the number of control rules is reduced, and the structure of the controller tidied, making a controller constructed using natural language training more appropriate in practice, and providing a fundamental rule base for high-level robot behavior control. Simulations and experiments on a wheeled robot are carried out to illustrate the effectiveness of the method.