[HN Gopher] Tiny quadrotor learns to fly in 18 seconds
___________________________________________________________________
Tiny quadrotor learns to fly in 18 seconds
Author : Brajeshwar
Score : 65 points
Date : 2024-02-09 15:01 UTC (7 hours ago)
(HTM) web link (spectrum.ieee.org)
(TXT) w3m dump (spectrum.ieee.org)
| ducktective wrote:
| Apart from this project, does anyone know any other DIY quadrotor
| building instructions with cheap off-the-shelf materials?
| pugworthy wrote:
| Have you looked into ArduPilot?
|
| https://ardupilot.org/
|
| https://github.com/ArduPilot/ardupilot
| IshKebab wrote:
| Honestly anything with `ardu` in the name screams "I just
| learnt to code and I don't know what I'm doing". I know
| nothing about this space but I'd definitely check out the PX4
| link that they other guy posted before this.
| olex wrote:
| Don't dismiss Ardupilot so easily. Yes, it grew out of
| Arduino Megas running the code with some stapled-on
| sensors, but that was many years ago - it's an extremely
| powerful and arguably more "hobbyist"-friendly platform
| that's very comparable to PX4. In my experience PX4 lends
| itself very well to more scientific or industrial use,
| especially when integrating with other on-board compute
| units that are part of the payload, whereas Ardupilot is
| much easier to get working and capable off-the-shelf. Both
| software stacks run on essentially the same hardware
| nowadays.
| cchance wrote:
| For freestyle betaflight is the goto firmware
| hadlock wrote:
| Ardupilot is very very mature software. It stopped being
| able to be run on an arduino about a decade ago. There's a
| guy who has been doing aireal waypoint missions for miles
| and miles, as well as terrestrial boat missions lasting
| days. It's been adapted for sailboats as well.
| wkipling wrote:
| At least click the link before submitting your premature
| damnation
| 05 wrote:
| The only advantage of PX4 is its license - it's BSD vs
| Ardupilot's GPL, so companies can use the code without
| giving back. The mindshare just isn't there - PX4 is orders
| of magnitude more obscure, so instead of YouTube tutorials
| you'll be trying to get help on PX4 specific forums or
| digging through the code base.
| inetknght wrote:
| I work for a drone company.
|
| PX4 is ubiquitous in the industry and in prosumer devices.
|
| PX4 provides the autopilot stack. There's all kinds of
| developer drone releases with all of the parts working and
| assembled.
| jabroni_salad wrote:
| I got a tinywhoop kit for my nephew and my sister hated it, so
| it's probably good.
|
| There is an entire ecosystem around those, so you can go
| piecemeal if you want.
| steve_gh wrote:
| This is interesting, because it seem to be a start at solving the
| Fulmar Problem.
|
| A fulmar is a cliff nesting sea bird (with a defensive habit of
| noxious projectile vomiting). They spend their early life on a
| ledge, but one day they have to start flying. And if you are a
| fulmar you have a very limited time to learn to fly.
|
| So the question is, how does a baby fulmar learn to fly in 10s!
|
| It would be interesting to know how much computing power is
| required for training (compared to the power requred to run the
| controlling NN).
|
| My own view is that the network architecture is important, so
| fulmar brains have evolved with a neural architecture that
| enables extremely quick learning to stable flight.
|
| I played around with a few ideas on using GAs to evolve NN
| architectures for rapid learning during my PhD 25 years ago, but
| ended up going in another direction.
| jahnu wrote:
| Why can't evolution build in the ability of flight and what it
| needs to learn in the 10 seconds is not how to fly but which
| way to go?
| throwup238 wrote:
| Instinct and coordinated muscle memory are two very different
| things. Animals can evolve to develop that muscle memory
| faster (i.e. see how long it takes a calf to walk versus a
| human infant) but it still needs time to develop and that
| development requires active practice.
| amelius wrote:
| A spider does not learn to make a web either. This is
| arguably more complicated than flying. And its brain is
| much smaller than a bird's.
| throwup238 wrote:
| A spider spinning web is an emergent behavior built up
| from a bunch of simpler ones like excretion, simple
| movement, and electrostatic hopping from point to point.
| A bird flying requires the coordination of a much larger
| number of muscles at the same time, which is much more
| complex from a nervous system perspective.
|
| Spiders reproduce much faster and have a much smaller
| survival rate so they're well selected for that kind of
| instinct. Birds less so.
| bitcurious wrote:
| A paper airplane can learn to fly on a breeze in being folded.
| I posit that a fulmar is closer to a paper airplane than to a
| drone.
| onion2k wrote:
| If that were true lots of young fulmars would drown in the
| sea at the bottom of a cliff when they fledge. That doesn't
| happen. They fly, with control, and enough understanding to
| land safely on water.
| ahepp wrote:
| Does anyone know of an affordable COTS drone one could try this
| out with? I'm very interested in the intersection of machine
| learning and control theory.
| UncleOxidant wrote:
| There's a link in the article to the open source drone they
| were using: https://www.bitcraze.io/products/crazyflie-2-1/
| cchance wrote:
| I've wondered why we haven't seen a lightweight model on quads
| for PID tuning, betaflight firmwares great but pid tunings such a
| pain in the ass if you want it tuned well how about an AI that on
| the fly adjusts the pid rates.
| ducktective wrote:
| Technically, PID only makes sense for linear time-invariant
| systems. A quadrotor drone is inherently a nonlinear system but
| people use linear controllers on it anyways.
|
| I mean if we're going to use "AI" on controls, it better be
| looking for tuning something else, better still, we should only
| utilize the "optimization algorithms" parts of "AI" hence
| optimal control.
| nvahalik wrote:
| I know this nit-picks but... it didn't "learn" anything.
|
| It progressively improved its algorithm using a series of
| feedback sessions.
|
| It _improved_ but it didn't _learn_. Someone pre-programmed basic
| control and feedback parameters.
|
| Don't get me wrong--this is still amazing and has useful
| applications. But can we please stop calling this
| improvement/refining/tuning process "learning"?
| disillusioned wrote:
| Ah yes, one step closer to Slaughterbots reality:
| https://www.youtube.com/watch?v=O-2tpwW0kmU
___________________________________________________________________
(page generated 2024-02-09 23:00 UTC)