Start Date

7-5-2014 11:00 AM

End Date

7-5-2014 1:00 PM

Subjects

Micro air vehicles -- Automatic control, Micro air vehicles -- Control systems, Adaptive control systems -- Design and construction, Artificial intelligence -- Engineering applications

Description

Flapping wing micro aerial vehicles (FWMAVs) are biomimetic vehicles, because they imitate insects in the way they fly. FWMAVs are very small and highly manoeuvrable and can be used in reconnaissance, environmental monitoring, search & rescue, and other applications. The goal of the project is to develop & verify an agent based flight controller for FWMAV that can adapt to different flight conditions, actuator failures, and different vehicles while delivering constant performance. Agent based control was successfully applied in industry and distributed applications, but to our best knowledge never in an actual flying vehicle. Agent based control utilizes machine learning, and outperforms traditional control approaches in situation, where the actual physical model is not properly known or varies in time. Based upon the mathematical model, a flight simulator was developed to evaluate different controllers. To verify the simulated results on actual hardware, a prototype of FWMAV is being built, and tested on flight polygon.

Persistent Identifier

http://archives.pdx.edu/ds/psu/11366

Share

COinS
 
May 7th, 11:00 AM May 7th, 1:00 PM

Agent-based Control of a Flapping Wing Micro Aerial Vehicle

Flapping wing micro aerial vehicles (FWMAVs) are biomimetic vehicles, because they imitate insects in the way they fly. FWMAVs are very small and highly manoeuvrable and can be used in reconnaissance, environmental monitoring, search & rescue, and other applications. The goal of the project is to develop & verify an agent based flight controller for FWMAV that can adapt to different flight conditions, actuator failures, and different vehicles while delivering constant performance. Agent based control was successfully applied in industry and distributed applications, but to our best knowledge never in an actual flying vehicle. Agent based control utilizes machine learning, and outperforms traditional control approaches in situation, where the actual physical model is not properly known or varies in time. Based upon the mathematical model, a flight simulator was developed to evaluate different controllers. To verify the simulated results on actual hardware, a prototype of FWMAV is being built, and tested on flight polygon.