Application of Parallel Processing to Robotic Computational Tasks

Abstract

Robotic tasks (e.g., kinematics and dynamics) are computation ally expensive. The majority of these tasks must be computed in real-time to meet the high sampling rate modes of oper ations. Recently parallel processing has been used to speed up these computations. In this work, we propose a graph- based algorithm to map computational tasks onto multiple instruction-multiple data (MIMD) type of architectures. The algorithm automatically generates the task graph of a given task. Then an annealing procedure is used to allocate the gen erated subtasks to different processors, taking into account the network topology and the communication constraints. Moreover, the proposed technique is simple, flexible, and computationally viable. The efficiency of the algorithm is demonstrated by a case study with good results.