A reinforcement learning - Adaptive control architecture for morphing Conference Paper uri icon

abstract

  • This paper develops a control methodology for morphing, bringing together the traditionally disparate fields of feedback control and artificial intelligence. The morphing control function, which uses reinforcement learning, is integrated with the trajectory tracking function, which uses adaptive dynamic inversion control. Optimality is addressed by cost functions representing optimal shapes corresponding to specified operating conditions, and an episodic unsupervised learning simulation is developed to learn the optimal shape change policy. The methodology is demonstrated by a numerical example of a 3-D morphing air vehicle, which simultaneously tracks a specified trajectory and autonomously morphs over a set of shapes corresponding to flight conditions along the trajectory. Results presented in the paper show that this methodology is capable of learning the required shape and morphing into it, and accurately tracking the reference trajectory in the presence of parametric uncertainties, unmodeled dynamics and disturbances.

published proceedings

  • Collection of Technical Papers - AIAA 1st Intelligent Systems Technical Conference

author list (cited authors)

  • Valasek, J., Tandale, M. D., & Rong, J.

complete list of authors

  • Valasek, J||Tandale, MD||Rong, J

publication date

  • December 2004