The system architecture controlling a group of robots is generally set before deployment and can be either centralized or decentralized. This dichotomy is highly constraining, because decentralized systems are typically fully self-organized and therefore difficult to design analytically, whereas centralized systems have single points of failure and limited scalability. To address this dichotomy, we present the Self-organizing Nervous System (SoNS), a novel robot swarm architecture based on self-organized hierarchy. The SoNS approach enables robots to autonomously establish, maintain, and reconfigure dynamic multi-level system architectures. For example, a robot swarm consisting of $n$ independent robots could transform into a single $n$-robot SoNS and then into several independent smaller SoNSs, where each SoNS uses a temporary and dynamic hierarchy. Leveraging the SoNS approach, we show that sensing, actuation, and decision-making can be coordinated in a locally centralized way, without sacrificing the benefits of scalability, flexibility, and fault tolerance, for which swarm robotics is usually studied. In several proof-of-concept robot missions -- including binary decision-making and search-and-rescue -- we demonstrate that the capabilities of the SoNS approach greatly advance the state of the art in swarm robotics. The missions are conducted with a real heterogeneous aerial-ground robot swarm, using a custom-developed quadrotor platform. We also demonstrate the scalability of the SoNS approach in swarms of up to 250 robots in a physics-based simulator, and demonstrate several types of system fault tolerance in simulation and reality.