Optimizing ROS 2 Communication for Wireless Robotic Systems

--Wireless transmission of large payloads, such as high-resolution images and LiDAR point clouds, is a major bottleneck in ROS 2, the leading open-source robotics middleware. The default Data Distribution Service (DDS) communication stack in ROS 2 exhibits significant performance degradation over lossy wireless links. Despite the widespread use of ROS 2, the underlying causes of these wireless communication challenges remain unexplored. In this paper, we present the first in-depth network-layer analysis of ROS 2's DDS stack under wireless conditions with large payloads. We identify the following three key issues: excessive IP fragmentation, inefficient retransmission timing, and congestive buffer bursts. T o address these issues, we propose a lightweight and fully compatible DDS optimization framework that tunes communication parameters based on link and payload characteristics. Our solution can be seamlessly applied through the standard ROS 2 application interface via simple XML-based QoS configuration, requiring no protocol modifications, no additional components, and virtually no integration efforts. Extensive experiments across various wireless scenarios demonstrate that our framework successfully delivers large payloads in conditions where existing DDS modes fail, while maintaining low end-to-end latency. Modern robotic systems rely on high-resolution sensors-such as LiDARs, RGB cameras, and depth cameras-and often integrate edge/cloud offloading to enable intelligent functionality. As a result, the reliable wireless transmission of large-payload data has become essential. In real-world environments where multiple robots operate simultaneously, concurrent data exchange is prone to latency, packet loss, and jitter. These communication issues can significantly impair decision-making and control in robots.