UAV heading controller using reinforcement learning

Kimathi, Stephen
Kang’ethe, Samuel
Kihato, Peter
Journal Title
Journal ISSN
Volume Title
Strathmore University
The control of heading of an Unmanned Aerial Vehicle is a vital operation. It is accomplished by employing a design of control algorithms that control its flying direction. The available autopilots exploit Proportional-Integral-Derivative (PID) based heading controllers. Here we propose an adaptive controller based on reinforcement learning. The heading controller will be designed in Matlab/Simulink for controlling a UAV in X-Plane test platform. Through this platform, the performance of the designed controller is compared with that of a well-tuned PID controller using real time simulations. The results show that the proposed method performs better.
The conference aimed at supporting and stimulating active productive research set to strengthen the technical foundations of engineers and scientists in the continent, through developing strong technical foundations and skills, leading to new small to medium enterprises within the African sub-continent. It also seeked to encourage the emergence of functionally skilled technocrats within the continent.
UAV, Reinforcement Learning, PID, X-Plane
Kimathi, S., Kang’ethe, S., & Kihato, P. (2017). UAV heading controller using reinforcement learning. In Pan African Conference on Science, Computing and Telecommunications (PACT). Nairobi: Strathmore University. Retrieved from