A Reactive/Deliberative Tactical Planner Using Genetic Algorithms
Stephen Thrasher, Christopher Dever · AIAA Guidance, Navigation, and Control Conference and Exhibit · 2008
Autonomous vehicles are increasingly assisting and replacing humans on physically demanding or dangerous tasks. In the future such systems will require higher levels of autonomy to eectively use their agile maneuvering capabilities and high-performance weapons and sensors in rapidly evolving, limited-communication situations. Many existing vehicle planning methods perform poorly on such realistic scenarios because they do not consider both continuous nonlinear system dynamics and discrete actions and choices. This paper proposes a exible framework for forming dynamically realistic, hybrid system plans composed of parametrized tactical primitives using genetic algorithms, which implicitly accommodate hybrid dynamics through a nonlinear tness function. The framework combines this deliberative planning with specially chosen tactical primitives to react to rapid changes in the environment. Tactical primitives encapsulate continuous and discrete elements together, using discrete switchings to dene the primitive type and both discrete and continuous parameters to capture stylistic variations. This paper demonstrates the combined reactive/deliberative framework on a problem involving two-dimensional navigation through a eld of threats while ring weapons and deploying countermeasures.