As an engineering student in a co-op program, work terms give you incredible experiences that can’t be replicated in the classroom. My co-op term with Thalmic Labs has been no exception! My name is Valentin and I’m a student at the University of Waterloo, working as a Gesture Controls Software Developer at Thalmic. Essentially, this means that I create applications for the coolest technologies and integrate them with the Myo armband. One particular project that I worked on this summer was the integration of the armband with the Parrot AR.As expected, flying a quadcopter with your arm is pretty darn cool! This proved to be an awesome project and was also quite an adventure, with lots of spectacular crashes, and broken quadcopter parts. Before we get to the fun stuff, let me give you a good understanding of how controlling the AR.In order to communicate flight commands to the AR.Drone, you have to connect it via a wifi hotspot. You can then set up commands to modify the pitch, yaw, and roll angles of the AR.

Drone to effectively control how it flies. You can control the pitch by moving your arm up and down, the yaw by moving your arm from side to side, and the roll by rotating your arm clockwise and counter-clockwise. When all of these angles are at zero, the AR.Drone will hover on the spot; when the angles are changed, you can control its flight. I started the project by looking at the existing open source AR.Drone Free Flight app on iOS. This was actually a nice shortcut in the development process for me since all of the communication for flight commands, which contain the angles mentioned previously, were already taken care of. All that was left was to integrate the Myo armband with the existing app and figure out the best way to control the AR.Drone with my arm. After lots of experimenting, I decided that keeping your arm flat should make the AR.Moving your arm from side-to-side would cause the AR.Drone to strafe left and right, modifying the yaw angle. Pointing your arm down would cause the AR.

Drone to move forward, and pointing your arm up towards the sky would cause it to move back, modifying the pitch angle. We can also make it rotate on its spot by giving it a positive roll angle for rotating right and a negative one to rotate left. ar drone parrot mercadolibreKnowing what position your arm is in is trivial thanks to the armband’s motion API. parrot ar drone opisThis allows us to know what your arm’s pitch, yaw, and roll are in real time, and from that we’re able to feed commands to the AR.grendel drone commander modsDrone via the Myo armband.parrot ar drone knock offDrone was just one of the very cool things which I’ve had the opportunity to work on here at Thalmic Labs, and I must say that this has definitely been the best co-op experience I’ve had so far!ar drone 2 eladó

Download apps, toolboxes, and other File Exchange content using Add-On Explorer in MATLAB. AR Drone Simulink Development-Kit V1.1 Blockset for the simulation and Wi-Fi control of the Parrot ARDrone 2.0. Simulate, connect, and fly!ar drone 2 joypad The development kit consists of blocks and examples for the simulation and real-time Wi-Fi control of the Parrot AR Drone 2.0. The simulation blocks are based on models of the vehicle derived via system identification. The Wi-Fi control blocks are capable of sending commands to and reading the states of the drone in real-time. The examples provide a framework for the control and guidance of the vehicle. These examples enable velocity and position control, waypoint tracking, and mission execution for the AR.Drone in both simulation and Wi-Fi control. This development kit was produced in the context of the 2013 MathWorks Summer Research Internship project.

For more information about the overall project to develop an automated autonomous emergency response system see: This file inspired Control Ar Drone Parrot 2.0 With Matlab 2015a And Vicon. Simulink Verification and Validation Modifying description of the blockset This version (1.1) removes the need of the System Identification Toolbox to load the drone transfer functions for simulation.This project follows the development of a natural user interface for controlling a Parrot 2.0 AR Drone using body gestures with a Microsoft Kinect (v1). Through this document I will share the different techniques used in the gesture recognition task and implementation. This project was made some time ago, but finally took the time to publish it here, I started the project first as a hobby, but later new team members added, thanks to all of them for all the help with tests and documentation. (/en-us/download/details.aspx?id=40278)*Toolkits (Credits to their respective developers):The main challenge found when trying to make a body gestural interaction interface, is to select which are going to be the movements or patterns you are going to use.

First they have to be easy and natural actions to the body, and moreover, you need to be able to detect them with all kind of body complexities. With this I refer to a problem found commonly when smaller or taller people than the average (i.e kids) tried to use the system, it would be hard for them to execute a good control.As the gestures selected for the control are the following:*Takeoff: Both hands to the front of the chest, fully extended.*Emergency stop: Both hands at the head.*Landing: Take drone to low position and stay still.*Flight control was made to resemble the control used in the Parrot app, with the two joysticks in which right hand would control pitch and roll, and left hand controls yaw and altitude.Fig. 1. Working area for gesture detection. (Note the colors inverted to match left & right hand of the user with left and right joystick in the app)Reference for roll, pitch and yaw movements.In order to avoid problems when little or tall people used the control system, a coordinate normalization was proposed using the distance from the head to the hip of the user and all further measurements would be divided by this distance to be just a proportion of the height of the person, and not to take absolute coordinates.

To detect the desired gesture, a simple subtraction was made between the distance of the hand of the user and his/her shoulders.After taking some measurements of the minimum and maximum distances made by a natural extension of the arms, the following mean values were found.So with this, an active region of gesture detection was made as shown in the next figure by the blue surface. Be aware that outside of that region, no signal would be send to the drone for safety reasons. This also applies to Z axis, so that you need to have your hands extended to the front in order to take control.The first approach to control the drone was to send velocities proportional to how far your hand was extended. This is still documented in the attached documentation, but was later found to be better to just have an ON-OFF control with a limited max velocity. Explanation on how the program works can also be found there. (Btw, the document is still in Spanish –since I´m from México-, I’ll try to upload an English version later)