Behavior Trees and State Machines in Robotics Applications

Autonomous robots combine a variety of skills to form increasingly complex behaviors called missions. While the skills are often programmed at a relatively low level of abstraction, their coordination is architecturally separated and often expressed in higher-level languages or frameworks. State Machines have been the go-to modeling language for decades, but recently, the language of Behavior Trees gained attention among roboticists. Originally designed for computer games to model autonomous actors, Behavior Trees offer an extensible tree-based representation of missions and are praised for supporting modular design and reuse of code. However, even though, several implementations of the language are in use, little is known about its usage and scope in the real world. How do concepts offered by behavior trees relate to traditional languages, such as state machines? How are behavior tree and state machine concepts used in applications? We present a study of the key language concepts in Behavior Trees and their use in real-world robotic applications. We identify behavior tree languages and compare their semantics to the most well-known behavior modeling language in robotics: state machines. We mine open-source repositories for robotics applications that use the languages and analyze this usage. We find similarity aspects between the two behavior modeling languages in terms of language design and their usage in open-source projects to accommodate the need of robotic domain. We contribute a dataset of real-world behavior models, hoping to inspire the community to use and further develop this language, associated tools, and analysis techniques.