Movement Primitives as a Robotic Tool to Interpret Trajectories Through Learning-by-doing

作     者：Andrea Soltoggio Andre Lemme 

作者机构：Research Institute for Cognition and Robotics Bielefeld University 

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：2013年第10卷第5期

页      面：375-386页

核心收录：

学科分类：080202[工学-机械电子工程] 08[工学] 0804[工学-仪器科学与技术] 0802[工学-机械工程] 080201[工学-机械制造及其自动化] 

基　　金：supported by European Community s Seventh Framework Programme FP7/2007-2013 Challenge 2 Cognitive Systems Interaction Robotics(No.248311AMARSi) 

主　　题：Movement primitives learning pattern matching trajectory decomposition perception 

摘      要：Articulated movements are fundamental in many human and robotic *** humans can learn and generalise arbitrarily long sequences of movements,and particularly can optimise them to ft the constraints and features of their body,robots are often programmed to execute point-to-point precise but fxed *** study proposes a new approach to interpreting and reproducing articulated and complex trajectories as a set of known robot-based *** of achieving accurate reproductions,the proposed approach aims at interpreting data in an agent-centred fashion,according to an agent s primitive *** method improves the accuracy of a reproduction with an incremental process that seeks frst a rough approximation by capturing the most essential features of a demonstrated *** the discrepancy between the demonstrated and reproduced trajectories,the process then proceeds with incremental decompositions and new searches in sub-optimal parts of the *** aim is to achieve an agent-centred interpretation and progressive learning that fts in the frst place the robots capability,as opposed to a data-centred decomposition *** on both geometric and human generated trajectories reveal that the use of own primitives results in remarkable robustness and generalisation properties of the *** particular,because trajectories are understood and abstracted by means of agent-optimised primitives,the method has two main features： 1） Reproduced trajectories are general and represent an abstraction of the data.2） The algorithm is capable of reconstructing highly noisy or corrupted data without pre-processing thanks to an implicit and emergent noise suppression and feature *** study suggests a novel bio-inspired approach to interpreting,learning and reproducing articulated movements and *** applications include drawing,writing,movement generation,object manipulation,and other tasks where the performance