1 / 11

Helicopter Neural Network Control for Stable Flight and Data Collection

Explore the design and implementation of a Neural Network on a WashUAV Helicopter for stable flight, obstacle avoidance, data collection, and refinement. The project integrates an Arduino Pro Mini, IMU, and Compass Module for ambitious flight goals. Testing and refining the Neural Network architecture involves gathering data from accelerometers, gyros, and a compass for controlling throttle, aileron, elevator, and rudder. Overcoming obstacles like ground effect and aerodynamics is crucial while learning to control the helicopter for indoor hovering. Previous work from Stanford and Australia on autonomous hovering and full-scale helicopter NN control inform the project's progress and ambitions.

koleyna-nelson
Télécharger la présentation

Helicopter Neural Network Control for Stable Flight and Data Collection

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. WashUAV Helicopter Sean Reynolds March 23, 2009

  2. Blade CP Pro2

  3. Arduino Pro Mini

  4. IMU 5 Degrees of Freedom

  5. Roving Networks RN-41

  6. Compass Module - HMC6352

  7. Ambitious Goals • Stable Hover • Flight • Obstacle Avoidance

  8. Stable Hover • Data collection for Neural Network • Data computation and refinement of Neural Network • Testing Neural Network on Helicopter

  9. NN Design Architecture • 3 Accelerometer: X,Y,Z • 2 Gyro: X,Y • 1 Compass Heading • Throttle • Aileron • Elevator • Rudder

  10. Obstacles • Ground effect and takeoff vs. in flight aerodynamics • Teaching myself to fly the new helicopter • Controlling the helicopter enough to hover indoors.

  11. Prior Work • Stanford Helicopter Team Project • Australia ANN Autonomous Hover • Full Scale Helicopter using Neural Network • International Aerial Robotics Competition, $10,000 • WashUAV progress.

More Related