Implementation of back-stepping integral controller for a gesture driven quad-copter with human detection and auto follow feature

This work demonstrates building an ETH's back-stepping integral controller based quad-copter, and is driven by human gestures. A novel application of computer vision is introduced for easy operation of quad-copters. Furthermore a method for detecting and auto follow of human is devised in the quad-copter. The design and modeling have been successfully realized on the 450mm sized X-configured quad-copter built during this project. This paper also demonstrates a MATLAB framework, to simulate and analyze the performance of a quad-rotor designed with back-stepping integral controller. It gives a synopsis of the controller used in ETH OS4 quad-rotor and presents an easy to use GUI to tune the controller while designing the quad-rotor.

[1]  mokhtar mohammed hasan,et al.  Features Fitting using Multivariate Gaussian Distribution for Hand Gesture Recognition , 2012 .

[2]  Roland Siegwart,et al.  Backstepping and Sliding-mode Techniques Applied to an Indoor Micro Quadrotor , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[3]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Nathan P. Koenig,et al.  Toward real-time human detection and tracking in diverse environments , 2007, 2007 IEEE 6th International Conference on Development and Learning.