Offloading Robotic and UAV Applications to the Network Using Programmable Data Planes

Next-generation 5G networks are rapidly expanding to support the growing demand for efficient connectivity in Internet of Things (IoT) and Machine-to-Machine (M2M) applications across various sectors (e.g., agriculture, automotive, healthcare, smart cities, and manufacturing). Industrial Internet of Things (IIoT) promises to transform manufacturing through Digital Twins while Industry 4.0 advances digitalization with Cyber-Physical Systems (CPS), machine learning, big data, and cloud computing. Hence, achieving Ultra-low latency (ULL) is crucial for applications like robotic control. Although 5G powered by Software-Defined Networking (SDN) and Network Function Virtualization (NFV) have improved the network capacity and reduced the ULL constraints, challenges persist due to wireless signal unpredictability. To address these issues, this research proposes leveraging in-network applications to the network edge to implement ULL solutions for industrial and Unmanned aerial vehicles (UAVs) applications. Furthermore, we propose the hardware-based P7 emulation environment to evaluate data plane applications' performance, feasibility, effectiveness, and impact.