Comparison Between Behavior Trees and Finite State Machines

Behavior Trees (BTs) were first conceived in the computer games industry as a tool to model agent behavior, but they received interest also in the robotics community as an alternative policy design to Finite State Machines (FSMs). The advantages of BTs over FSMs had been highlighted in many works, but there is no thorough practical comparison of the two designs. Such a comparison is particularly relevant in the robotic industry, where FSMs have been the state-of-the-art policy representation for robot control for many years. In this work we shed light on this matter by comparing how BTs and FSMs behave when controlling a robot in a mobile manipulation task. The comparison is made in terms of reactivity, modularity, readability, and design. We propose metrics for each of these properties, being aware that while some are tangible and objective, others are more subjective and implementation dependent. The practical comparison is performed in a simulation environment with validation on a real robot. We find that although the robot’s behavior during task solving is independent on the policy representation, maintaining a BT rather than an FSM becomes easier as the task increases in complexity. Note to Practitioners—Behavior Trees (BTs) have gained significant traction in robotics, with over one hundred research papers published annually in the past five years. BTs have demonstrated their advantages in various applications, such as mobile manipulation, underwater and aerial robotics, and humanoids. Choosing the right policy representation is crucial for successful task completion. While Finite State Machines (FSMs) have been popular for their simplicity, they can become cumbersome as tasks grow more complex. We show this by implementing BTs and FSMs in a mobile manipulation task, tested in simulation and on a real robot. As task difficulty increases, FSMs become harder to maintain due to the rising number of transitions. Our findings provide practical guidance for engineers, helping them choose the best policy representation for their specific robotic applications.