Research on Real-time Performance Testing Methods for Robot Operating System
Ming Huang, Shujie Guo, Xu Liang, Xudong Song
- Year
- 2014
- Citations
- 3
Abstract
Abstract—To test real-time performance of RGMP-ROS, a robot operating system, this paper takes an in-depth study of the basic functions of real-time operating system kernel. By analyzing the main factors that affect the real-time performance of an operating system, we propose a set of real-time performance testing methods based on mixed load. This paper introduces the concept of the calibration procedure program. Takes the average execution time of the program as the standard time unit to normalize the test results of each test indicator, so as to shield the effect of the hardware test environment on the test results to a certain extent. While testing task preemption time and interrupt response time, we use background tasks that can trigger banning preemption or disabling interrupts to simulate the load, which makes the test results more real and reliable. Index Terms—Operating System, Real-time performance
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991