QoS Balancing Optimization in Aggregated Robot Processing Architecture: Rate and Buffer

Abstract

This study developed an optimization algorithm to balance the Quality of Service (QoS) rates and buffer size for robot data communication in the Aggregated Robot Processing (ARP) architecture. Robot Operating System 2 (ROS 2) is robotic software that uses a set of QoS policies to control the quality of data transmission in robotic networks, such as DEADLINE to determine the rates, and DEPTH to determine the buffer size. An unbalanced DEADLINE and DEPTH configuration in ROS 2 node communication can result in high packet latency and packet loss in RELIABLE connections. This happens when the DEADLINE sets the rates at high frequencies, and the DEPTH sets the buffers with small sizes. The results of this study show that the optimization algorithm developed in this study can determine the rate and buffer size through a balancing configuration for better quality robot data transmission in ARP architecture, influence the improvement of latency and reduce the packet loss.