Parallel Task Processing on a Multicore Platform in a PC-based Control System for Parallel Kinematics

Journal of Systemics, Cybernetics and Informatics

Yannick Dadji¹  Harald Michalik²  Jochen Maass³ 

[1] Institute of Computer and Communication Network Engineering, Braunschweig;Institute of Computer and communication Network Engineering, Braunschweig;Institute of Machine Tools and Production Technology, Braunschweig;

关键词: Pc-Based Control;    Multicore;    parallel processing;    Parallel Kinematics;   

DOI  :  

来源: DOAJ

【 摘 要 】

Multicore platforms are such that have one physical processor chip with multiple cores interconnected via a chip level bus. Because they deliver a greater computing power through concurrency, offer greater system density multicore platforms provide best qualifications to address the performance bottleneck encountered in PC-based control systems for parallel kinematic robots with heavy CPU-load. Heavy load control tasks are generated by new control approaches that include features like singularity prediction, structure control algorithms, vision data integration and similar tasks. In this paper we introduce the parallel task scheduling extension of a communication architecture specially tailored for the development of PC-based control of parallel kinematics. The Sche-duling is specially designed for the processing on a multicore platform. It breaks down the serial task processing of the robot control cycle and extends it with parallel task processing paths in order to enhance the overall control performance.

【 授权许可】

Unknown