Finite-state machines (FSMs) are a rule-based modeling approach used in traditional robotics to represent system behavior as a set of discrete states and transitions. Each state defines a specific behavior or control mode, while transitions are triggered by predefined conditions such as sensor inputs or timers. FSMs are widely used in robotic control architectures because they are simple, interpretable, and easy to debug. They work well for tasks with clearly defined stages, such as navigation sequences or industrial automation workflows. However, FSMs scale poorly as task complexity increases, since the number of states and transitions grows rapidly. In modern robotics, FSMs are often contrasted with learning-based approaches, which can generalize from data rather than relying on exhaustive rule definitions.