Modeling Hydra Behavior Using Methods Founded in Behavior-Based Robotics

14 Chapter 4. Behavior-based roboticsrules, various modifications of finite state machines (FSMs) 2 , and artificial neural networks(ANNs). If-then-else-rules provides a quick way of generating simple behaviorsby means of hand-coding instructions directly into the robotic brain. As a simple exampleconsider a robot that moves straight ahead while there is no object in front of it, and stopsat the encountering of an obstacle. Assuming that conditions for obstacle-detection bythe robot’s sensors, as well as motor signals for the “move forward” and “stop” behaviorshave been defined, this behavior may be formulated as follows: if no object detected thenmove forward else stop.Biologically inspired architectures, such as ANNs, often provide a suitable frameworkfor the generation of robot behaviors by means of EAs. Especially in cases where it isdifficult to arrive at an explicit model for a specific behavior, such an approach has anobvious advantage over hand-coded behaviors. A brief introduction to ANNs is providedin Appendix B.4.2 Organization of robot behaviorsIn a behavior-based system, the behavioral organizer specifies how the constituent behaviorsare arranged and connected. As mentioned in Chapter 1, many methods have alreadybeen suggested, and new architectures continue to arise. One way of classifying methodsused for behavior organization, as discussed in [49], is to divide them into two maincategories: arbitration methods and command fusion methods, as suggested e.g. byA. Saffiotti [56]. In arbitration methods, only one behavior is active at a time, whereasin command fusion methods, the robot’s action is obtained by combining the results fromseveral behaviors. In both arbitration methods and command fusion methods, severalsub-categories exist, as shown in Fig. 4.1 below. In this project, a priority-based arbitrationmethod was used, which will be described in Chapter 6. For descriptions of othermethods, see e.g. [1, 49].✘ ✘ ✘ ✘✘ ✘ ✘✘ ✘ ✘❳ ❳ ❳ ❳❳❳ ❳❳❳ ❳ArbitrationCommand fusion ✏ ✏ ✏✏✏✏✏ ✏ ✏✏✏✏ ✁❆✁ ❆✁Priority-based Winner-take-all Superposition ❆Multiple objectiveState-based Fuzzy VotingFigure 4.1: Classification of methods for behavior organization.2 Examples include augmented finite state machines, used e.g. in [8], and generalized finite state machines,used e.g. in [68].