Open Access

The optimal operation of transportation systems is often susceptible to unexpected disruptions. Many established control strategies reliant on mathematical models can struggle with real-world disruptions, leading to significant divergence from their anticipated efficiency. This study integrates the cutting-edge concept of antifragility with learning-based traffic control strategies to optimize urban road network operations under disruptions. Antifragile systems not only withstand and recover from stressors but also thrive and enhance performance in the presence of such adverse events. We develop a deep reinforcement learning framework that incorporates antifragile modules composed of traffic state derivatives and redundancy. Subsequently, it is evaluated in a cordon-shaped transportation network and a case study with real-world data. Promising results highlight that the proposed algorithm provides: (i) superior performance achieving up to 27.6% and 41.9% performance gain over baselines under increasing demand and supply disruptions, (ii) lower distribution skewness under disruptions, demonstrating its relative antifragility against baselines, (iii) effectiveness under limited observability due to real-world data availability constraints, and (iv) the robustness and transferability to be incorporated into recent state-of-the-art RL architectures. The proposed antifragile methodology is generalizable and holds potential for applications beyond traffic engineering, offering integration into control systems exposed to disruptions across various disciplines.

The development of software on embedded platforms poses challenges due to limited processing capabilities and high latency. This makes development time-consuming, especially in edge computing scenarios where real-time responsiveness is crucial. A streamlined installation process combined with a straightforward communication protocol minimizes setup time and accelerates development. The proposed solution leverages Docker containers to encapsulate essential software components on the edge device, offering a modular architecture that isolates functionalities and enables efficient configuration across heterogeneous environments. Integrating a communication protocol via MATLAB facilitates the development of complex algorithms on a high-performance platform—an approach widely used in mechatronic systems across mobility, manufacturing, and energy domains. To demonstrate this, a case study from research and teaching at TH Nürnberg is presented: sensors and a Raspberry Pi are integrated into a 1:10 scale RC vehicle. Communication with sensors and actuators runs via Docker containers, enabling modular and reproducible deployment. Algorithms for autonomous driving—such as perception, planning, and motor control—are developed in MATLAB and transferred to the vehicle. This illustrates the flexibility of the approach for academic applications. It combines a fast, uniform hardware setup with a realistic scaled vehicle, well-suited for prototyping and experimentation in embedded systems.