PARALLEL DYNAMIC SIMULATION OF MULTIPLE MANIPULATOR SYSTEMS - TEMPORAL VERSUS SPATIAL METHODS

In this paper, parallel algorithms are developed for real-time dynamic simulation of a multiple manipulator system, cooperating to manipulat e a large load. In an effort to achieve real-time computational rates on a general-purpose parallel system, temporal and spatial forms of pa rallelism are implemented to improve performance. Temporal parallelism is obtained with the use of parallel numerical integration methods. A speedup of 3.78 on four processors of a CRAY Y-MP8 was achieved with a parallel four-point block predictor-corrector method for the simulat ion of a four manipulator system. To overcome a loss of efficiency bec ause of a reduction in accuracy with the block integration methods, sp atial parallelism is used in which the dynamics of each chain is compu ted simultaneously. With the same four manipulator system, this form o f parallelism in conjunction with a serial integration method results in a speedup of 3.1 on four processors without the degradation in accu racy. In cases where there are more processors than chains, a new mult ipoint parallel integration method can still be advantageous despite t he reduced accuracy. In this case, it is shown that greater effective speedups are achieved when both forms of parallelism are combined to g enerate more parallel tasks.