Fully Autonomous Quadrotor for indoor flight

I have an interest in developing a fully autonomous quadrotor robot specifically for indoor flight.

I am an engineer (what I do in my day job) with experience in robotics, computer vision, navigation/localization, and overall AI.

I was wondering what peoples opinions would be on what quadcopter platform I should attempt to base this project of mine? 

So far i am thinking of using an AR Parrot 2, DJI Phantom 3, or a 3DR Solo as the quadcopter. 

I currently intend to use a Jetson TK1 as the the onboard computer for control. Also my idea is to use a combination of an on board camera stereo pair, a (or pair of) depth sensor camera(s) (such as a Kinect, or any other OpenNI compatible sensor), a IMU (probably an XSens), along with N ultra sonic rangers.

I know this may seem overly ambitious, but i am familiar with the current research in controlling a quadcopter via on board sensors. I am also adept at developing and expanding upon techniques such as particle filter based localization, visual odometry, SLAM, and Kalman filter based sensor fusion.

The key concept here is that i would like to have this thing be able to fly indoors, and explore its environment.

Any suggestions?

You need to be a member of diydrones to add comments!

Join diydrones

Email me when people reply –

Replies

  • A new demo of fully autonomous flight indoor:



  • In case you are still looking for some response!

    I heard good things about DJI Matrice100 + the guidance.

    Not sure about the size of the drone and the price..

    I think that this is a larger drone than the solo but has a much larger payload capacity.

    (Which Im sure will be good for the TX1, TK1)

    Matrice 100  also has ROS compatibility.

    Question for the group - how does one accommodate for the larger power pull by the TX1 19V ??

    Thanks

    Prasanna

  • You can use a precise (+-2cm) Indoor "GPS": http://marvelmind.com/.

    Here is a couple of demos:

  • I am also beginning masters project using Jetson Tx1 (why do you use tk1 by the way, if there is a reason apart from the price). I am still planning either will it be only cameras or a lidar would be included too. Are you planning to use only 2 cameras or 4*2 cameras for all directions? And I would like to learn your approach on the problem, which type of slam, neural net training etc. As for the controller, the pixhawk handles all the flight related jobs, you can just "control the controller" via mavlink.

  • Yuneec USA is coming out with the Typhoon H mid March. The RealSense adapter that is coupled with this drone allows it autonomous flight and collision prevention in real time. Youtube the Typhoon H collision testing. Also I am a certified Yuneec dealer if you need one when it comes out.
  • lets begin with a practical slam.
    • Any suggestions on a quadcopter that would be good for indoor use, has a payload that could support the TK1 and at least on kinect like sensor, and has an open enough api that I could control the copter at a low enough level to achieve highly reactive behaviors?

      • DJI has a TK1 board but close source.

        I am building one, currently planning the interfaces and form factors etc.

        3702736243?profile=original

This reply was deleted.

Activity

DIY Robocars via Twitter
RT @a1k0n: @DanielChiaJH @diyrobocars @circuitlaunch Here's my car's view of that race. About 8.4 second lap times for laps 2 and 3... both…
yesterday
DIY Robocars via Twitter
RT @DanielChiaJH: Great racing against @a1k0n today at @diyrobocars! Pretty cool to both break sun-9s at the track today I think I got very…
Sunday
DIY Robocars via Twitter
Broadcasting the @circuitlaunch race live now at https://m.twitch.tv/diyrobocars Races begin around 2:00pm PT
Saturday
DIY Robocars via Twitter
RT @a1k0n: ran a huge number of hyperparameter tuning experiments yesterday; now I can train a new policy, far with better quality, in 15 m…
Saturday
DIY Robocars via Twitter
RT @a1k0n: Did I get rid of hand-tuned parameters? Yes. Am I still hand-tuning more parameters? Also yes. I have a few knobs to address the…
Sep 26
DIY Robocars via Twitter
RT @a1k0n: I'm not going to spoil it, but (after charging the battery) this works way better than it has any right to. The car is now faste…
Sep 26
DIY Robocars via Twitter
RT @a1k0n: Decided to just see what happens if I run the sim-trained neural net on the car, with some safety rails around max throttle slew…
Sep 26
DIY Robocars via Twitter
Sep 24
DIY Robocars via Twitter
RT @SmallpixelCar: @a1k0n @diyrobocars I learned from this. This is my speed profile. Looks like I am too conservative on the right side of…
Sep 24
DIY Robocars via Twitter
RT @a1k0n: @SmallpixelCar @diyrobocars Dot color is speed; brighter is faster. Yeah, it has less room to explore in the tighter part, and t…
Sep 24
DIY Robocars via Twitter
RT @a1k0n: I'm gonna try to do proper offline reinforcement learning for @diyrobocars and throw away all my manual parameter tuning for the…
Sep 23
DIY Robocars via Twitter
RT @circuitlaunch: DIY Robocars & Brazilian BBQ - Sat 10/1. Our track combines hairpin curves with an intersection for max danger. Take tha…
Sep 22
DIY Robocars via Twitter
RT @SmallpixelCar: Had an great test today on @RAMS_RC_Club track. However the car starts to drift at 40mph. Some experts recommended to ch…
Sep 11
DIY Robocars via Twitter
RT @gclue_akira: 世界最速 チームtamiyaのaiカー https://t.co/1Qq2zOeftG
Sep 10
DIY Robocars via Twitter
RT @DanielChiaJH: Always a good time working on my @diyrobocars car at @circuitlaunch. Still got some work to do if I’m to beat @a1k0n howe…
Sep 10
DIY Robocars via Twitter
RT @SmallpixelCar: My new speed profile for @RAMS_RC_Club track https://t.co/RtLb7TcgIJ
Sep 10
More…