Schlagwort: navigation

  • Build a Raspberry Pi chartplotter for your boat

    Build a Raspberry Pi chartplotter for your boat

    Reading Time: < 1 minute

    Earlier this year, James Conger built a chartplotter for his boat using a Raspberry Pi. Here he is with a detailed explanation of how everything works:

    Building your own Chartplotter with a Raspberry Pi and OpenCPN

    Provides an overview of the hardware and software needed to put together a home-made Chartplotter with its own GPS and AIS receiver. Cost for this project was about $350 US in 2019.

    The entire build cost approximately $350. It incorporates a Raspberry Pi 3 Model B+, dAISy AIS receiver HAT, USB GPS module, and touchscreen display, all hooked up to his boat.

    Perfect for navigating the often foggy San Francisco Bay, the chartplotter allows James to track the position, speed, and direction of major vessels in the area, superimposed over high-quality NOAA nautical charts.

    Raspberry Pi at sea

    For more nautically themed Raspberry Pi projects, check out Rekka Bellum and Devine Lu Linvega’s stunning Barometer and Ufuk Arslan’s battery-saving IoT boat hack.

    Website: LINK

  • DeepWay helps the visually impaired navigate with a tap

    DeepWay helps the visually impaired navigate with a tap

    Reading Time: 3 minutes

    DeepWay helps the visually impaired navigate with a tap

    Arduino Team — August 20th, 2018

    In order to help those with visual impairments navigate streets, college student Satinder Singh has come up with an innovative solution that literally pokes the user in the right direction. 

    Singh’s system, called DeepWay, uses a chest-mounted camera to take images of the road that a wearer is walking down, then feeds this information to a laptop for processing. 

    If the deep learning algorithm determines that the user needs to move left or right to stay on the path, a serial signal is sent to an Arduino Uno, which in turn commands one of two servos mounted to a pair of glasses to tap the person to indicate which way to walk. Additional environmental feedback is provided through a pair of earphones.

    This project is an aid to the blind. Till date there has been no technological advancement in the way the blind navigate. So I have used deep learning particularly convolutional neural networks so that they can navigate through the streets.

    My project is an implementation of CNNs, and we all know that they require a large amount of training data. So the first obstruction in my way was a correclty labeled dataset of images. So I went around my college and recorded a lot of videos (of all types of roads and also off-roads). Then I wrote a basic Python script to save images from the video (I saved 1 image out of every 5 frames, because the consecutive frame are almost identical). I collected almost 10,000 such images almost 3,300 for each class (i.e. left right and center).

    I made a collection of CNN architectures and trained the model. Then I evaluated the performance of all the models and chose the one with the best accuracy. I got a training accuracy of about 97%. I got roughly same accuracy for all the trained model but I realized that the model in which implemented regularization performed better on the test set.

    The next problem was how can I tell the blind people in which direction to move. So I connected my Python program to an Arduino. I connected the servo motors to Arduino and fixed the servo motors to the sides of a spectacle. Using serial communication I can tell the Arduino which servo motor to move which would then press to one side of the blind person’s head and would indicate him in which direction to move.

    A demo of DeepWay can be seen in the video below, while code for this open source project is available on GitHub.

    [youtube https://www.youtube.com/watch?v=qkmU8mN0LwE?feature=oembed&w=500&h=281]

    You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.

    Website: LINK

  • Raspberry Pi as car computer

    Raspberry Pi as car computer

    Reading Time: 2 minutes

    Carputers! Fabrice Aneche is documenting his ongoing build, which equips an older (2011) car with some of the features a 2018 model might have: thus far, a reversing camera (bought off the shelf, with a modified GUI to show the date and the camera’s output built with Qt and Golang), GPS and offline route guidance.

    rearcam

    We’re not sure how the car got through that little door there.

    It was back in 2013, when the Raspberry Pi had been on the market for about a year, that we started to see carputer projects emerge. They tended to be focussed in two directions: in-car entertainment, and on-board diagnostics (OBD). We ended up hiring the wonderful Martin O’Hanlon, who wrote up the first OBD project we came across, just this year. Being featured on this blog can change your life, I tell you.

    In the last five years, the Pi’s evolved: you’re now working with a lot more processing power, there’s onboard WiFi, and far more peripherals which can be useful in a…vehicular context are available. Consequently, the flavour of the car projects we’re seeing has changed somewhat, with navigation systems and cameras much more visible. Fabrice’s is one of the best examples we’ve found.

    solarised map

    Night-view navigation system

    GPS is all very well, but you, the human person driver, will want directions at every turn. So Fabrice wrote a user interface to serve up live maps and directions, mostly in Qt5 and QML (he’s got some interesting discussion on his website about why he stopped using X11, which turned out to be too slow for his needs). All the non-QML work is done in Go. It’s all open-source, and on GitHub, if you’d like to contribute or roll your own project. He’s also worked over the Linux GPS daemons, found them lacking, and has produced his own:

    …the Linux gps daemons are using obscure and over complicated protocols so I’ve decided to write my own gps daemon in Go using a gRPC stream interface. You can find it here.

    I’m also not satisfied with the map matching of OSRM for real time display, I may rewrite one using mbmatch.

    street map display

    We’ll be keeping an eye on this project; given how much clever has gone into it already, we’re pretty sure that Fabrice will be adding new features. Thanks Fabrice!

    Website: LINK