An Evolutionary Method for Improving the Reliability of Safety-critical Robots against Soft Errors

Nowadays, Robots account for most part of our lives in such a way that it is impossible for us to do many of affairs without them. Increasingly, the application of robots is developing fast and their functions become more sensitive and complex. One of the important requirements of Robot use is a reliable software operation. For enhancement of reliability, it is a necessity to design the fault tolerance system. In this paper, we will present a genetic algorithm and learning automata with high reliability to evaluate the software designed into the robot against soft-error with minimum performance over-head. This method relies on experiment; hence, we use the program sets as criteria in evaluation stages. Indeed, we have used the error injection method in the execution of experimental processes. Relevant data, regarding program execution behavior were collected and then analyzed. To evaluate the behavior of program, errors entered using the simple scalar simulation software.