I bought an Frsky DF 2.4Ghz Combo Pack and dismantled the transmitter package and built my own transmitter as shown.
Apart from the DFT 8-channel transmitter, the RC Tx/Rx unit has an own built board with 2 psoc1 mcu’s from Cypress for generating the ppm signal, reading the sticks position and BT pc communication.
Milling of pcb
A python program controls the settings of the RC Tx/Rx unit and displays the telemetry data
The different parts of the quadcopter are milled in plastic and aluminum. The flightcontroller is the wellknown KK2.0.
By using Intels OpenVINO and neural computing stick (NCS1) the inference speed of my neural network is increased from 5 frames per second (fps) to 20 using a RPI3. This enabled a far better obstacle avoidance performance of my drone. More info at https://github.com/avncalst/drone_cnn.
Simple testflight of my E-Flite Convergence equipped with a pixracer flight controller complemented with a "sbus to pwm" home-made circuit to extend the number of servo outputs. Flight stack: Ardupilot Quadplane; Flight mode: loiter.
Recently I started working on convolutional neural networks (cnn) for obstacle avoidance. With the help of "DroNet" from ETH Zurich and the "Deep Learning for Computer Vision" book from Adrian Rosebrock, I managed to build my first cnn algorithm for obstacle avoidance. The cnn module is written in python, using a keras…Continue