The integration of Cyber-Physical Systems (CPS) and AI presents both opportunities and challenges. AI operates on the principle that “good things happen probabilistically,” while CPS adheres to the principle that “all bad things must not happen,” requiring uncertainty-awareness. Furthermore, the difference between AI’s resource accessibility assumption and CPS’s resource limitations highlights the need for resource-awareness. We introduce Cyber-Physical AI (CPAI), an interdisciplinary sub-field of AI and CPS research, to address these constraints. To the best of our knowledge, CPAI is the first research domain on CPS-AI integration. We propose a 3D classification schema of CPAI: Constraint (C), Purpose (P), and Approach (A). We also systematize the CPS-AI integration process into three phases and nine steps. By analyzing 104 studies, we highlight nine key challenges and insights from a CPAI perspective. CPAI aims to unify fragmented studies and provide guidance for reliable and resource-efficient integration of AI as a component of CPS.
In mission-critical environments such as industrial and military settings, the use of unmanned vehicles is on the rise. These scenarios typically involve a ground control system (GCS) and nodes such as unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs). The GCS and nodes exchange different types of information, including control data that direct unmanned vehicle movements and sensor data that capture real-world environmental conditions. The GCS and nodes communicate wirelessly, leading to loss or delays in control and sensor data. Minimizing these issues is crucial to ensure nodes operate as intended over wireless links. In dynamic networks, distributed path calculation methods lead to increased network traffic, as each node independently exchanges control messages to discover new routes. This heightened traffic results in internal interference, causing communication delays and data loss. In contrast, software-defined networking (SDN) offers a centralized approach by calculating paths for all nodes from a single point, reducing network traffic. However, shifting from a distributed to a centralized approach with SDN does not inherently guarantee faster route creation. The speed of generating new routes remains independent of whether the approach is centralized, so SDN does not always lead to faster results. Therefore, a key challenge remains: determining how to create new routes as quickly as possible even within an SDN framework. This paper introduces a caching technique for forwarding rules based on predicted link states in SDN, which was named the CRIMSON (Cashing Routing Information in Mobile SDN Network) algorithm. The CRIMSON algorithm detects network link state changes caused by node mobility and caches new forwarding rules based on predicted topology changes. We validated that the CRIMSON algorithm consistently reduces end-to-end latency by an average of 88.96% and 59.49% compared to conventional reactive and proactive modes, respectively.