Automatic Case Generation of Variation Testing in Navigation Software Based on the Genetic Algorithm

Navigation software can be extensively used in vehicle navigation, robot navigation, etc. commonly used such as RTKLIB, the quality of which directly affects the navigation effect. Variation testing is a software testing method that effectively identifies the quality of test data sets, and occupies a significant position in the field of software testing. Based on the source program, it generates variants by subtle changes in the fallible place, producing automatically the testing data of killing the variants to improve the efficiency of variation testing. As the core of RTKLIB navigation software, this paper adopts the weak variant testing method based on paths comparison, i.e., the variant is killed if the paths generated by the testing data running the source program and variations respectively are the same. Compared with randomization, the genetic algorithm adopted in this paper is qualified with shorter testing time and higher efficiency in generating variation testing data.