TOPN Based Temporal Performance Evaluation Method of Neural Network Based Robot Controller

  • Authors:

  • Hua Xu;Peifa Jia

  • Affiliations:

  • State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, ...;State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, ...

  • Venue:
  • ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

These years, for some neural network (NN) controller based time critical systems, temporal performance is always required to be evaluated. In order to model complex time critical systems, timed hierarchical object-oriented Petri net (TOPN) has been proposed. On the base of TOPN method, this paper has proposed worst case execution time (WCET) calculation method called time accumulation effect (TAE) calculation, whose goal is to evaluate the performance of TOPN models such as NN based robot controller systems etc al. TAE method can be used to calculate the worst case execution time interval directly on the base of integral linear programming (ILP) method. The use and benefits of TAE calculation for TOPN models have also been illustrated by analyzing one robot controller system model.