Here is the place for sharing ideas and projects about the use of Machine Learning algorithms with the ArduCopter. Above, a video of a full Autonomous Helicopter which is able to do aerobatic figures by itself... This development has been conducted by the Prof. Andrew Ng and the Machine Learning Teamwork of the Stanford University.
You need to be a member of diydrones to add comments!
Replies
Here a new interesting paper as food for thinking:
ROBUST NEURAL NETWORK CONTROL OF A QUADROTOR HELICOPTER - C. Nicol, C.J.B. Macnab, A. Ramirez-Serrano - Schulich School of Engineering, University of Calgary
This paper proposes a new adaptive neural network control to stabilize a quadrotor helicopter against modeling error and considerable wind disturbance. The new method is compared to both deadzone and e-modification adaptive techniques and through simulation demonstrates a clear improvement in terms of achieving a desired attitude and reducing weight drift.
This paper can be downloaded HERE
X4-flyer (quadrocopter) performs fully autonomous trajectory tracking, equipped with Aerojeep's BrainyBEE autopilot, which is the world's smallest high performance autopilot, embedded with neural network adaptive control technology, and capable of providing integraded guidance and control of a UAV network of different types including fixed wing, helicopter, X4-flyer, airship and other VTOL UAVs.
Here an interesting document as food for thinking for this topic:
Adaptive Neural Network Flight Control Using both Current and Recor...
by Girish Chowdhary and Eric N. Johnson
Modern aerospace vehicles are expected to perform beyond their conventional flight envelopes and exhibit the robustness and adaptability to operate in uncertain environments.Augmenting proven lower level control algorithms with adaptive elements that exhibit long term learning could help in achieving better adaptation performance while performing aggressive maneuvers. The current adaptive methodologies which use Neural Network based control methods use only the instantaneous states to tune the adaptive gains. This results in a rank one limitation on the adaptive law. In this paper we propose a novel approach to adaptive control, which uses the current or the online information as well as stored or
background information for adaptation. We show that using a combined online and background learning approach it is possible to overcome the rank one limitation on the adaptive law resulting in faster adaptation to the unknown dynamics. Furthermore, we show that using combined online and background learning methods it is possible to guarantee long
term learning in the adaptive flight controller, which enhances performance of the controller when it encounters a maneuver that has been performed in the past. We use Lyapunov based methods for showing boundedness of all signals for a proposed method. The performance of the proposed method is evaluated in the high fidelity simulation environment for the GTMAX UAS maintained by the Georgia Tech UAV lab. The simulation results show that the proposed method exhibits long term learning and faster adaptation leading to better performance of the UAS flight controller.
Here a video of the prof Andrew Ng of the Stanford University who explains how Artificial Intelligence can be used in autonomous helicopters or multicopters... The future is NOW...
Prepare to add a brain to your ArduCopter... All ideas are welcome here...
Thank you, this is most useful. The papers are wonderful.
Hope we can do the same with arducopter, a much more suitable platform.
Dara