Analyze, Debug, Optimize: Real-Time Tracing for Perception and Mapping Systems in ROS 2

Abstract

Perception and mapping systems are among the most computationally, memory, and bandwidth intensive software components in robotics. Therefore, analysis, debugging, and optimization are crucial to improve perception systems performance in real-time applications. However, standard approaches often depict a partial picture of the actual performance. Fortunately, instrumentation and tracing offer a great opportunity for detailed performance analysis of realtime systems. In this paper, we show how our novel opensource tracing tools and techniques for ROS 2 enable us to identify delays, bottlenecks and critical paths inside centralized, or distributed, perception and mapping systems.