System Identification of Self-Organizing Robotic Swarms

We discuss system identification of self-organizing, swarm robotic systems using a “gray-box” approach, based on probabilistic macroscopic models. Using a well known case study concerned with the autonomous inspection of a regular structure by a swarm of miniature robots, we show how to achieve highly accurate predictive models by combining previously developed probabilistic modeling and calibration methods, with parameter optimization based on experimental data (80 experiments involving 5-20 real robots). Key properties of the optimization process are outlined with the help of a simple scenario and a model that can be solved analytically. Concepts are then validated numerically for the more complex, non-linear inspection scenario.