Thread Tools
This thread is privately moderated by Jack Crossfire, who may elect to delete unwanted replies.
Jun 26, 2008, 12:25 AM
Registered User
Jack Crossfire's Avatar
Thread OP
Discussion

GPS logging, neural nihilism, & dynamic nihilism


Getting GPS logger to work in the dumpy apartment was easy. Getting it to work in a hand held, portable device in the real world is a major operation. Going to need a lot more error detection, recovery, & redundancy with that one.

The next step with VicaCopter will be logarithmic yaw damping on the PIC. This should reduce oscillation to increase tail servo life & increase the amount of rate damping available.

https://www.rcgroups.com/forums/atta...mentid=1702634

The equation was pwm = yaw rate * gain / sqrt(yaw rate * falloff).
gain = 0.2
falloff = 4


Found some more showstoppers with the neural network plan. Mainly observing the real world performance of many sets of weights to determine the optimum set would probably take eternity to yield useful results. Each set would need several seconds in the loop to determine its fitness & it takes thousands of sets to converge on a solution. E-Coli evolves faster.

Looking through a few thousand more copies of copies of a few papers on The Goog, correlating observed outputs & inputs in a neural network & inverting it to predict inputs was probably the right direction. The pros call it Dynamic Inversion & it's only possible with enough computing power to crunch huge data tables in flight.

It probably didn't work with acceleration because the data was too noisy & we didn't have enough computing power to gather enough points. There literally was no correlation between attitude & acceleration in 30 seconds of data.

Attitude changes from cyclic could be a different story. A lot more data points in a lot less time & they could be more accurate. Record attitude changes & cyclic inputs so you always have data points in all the ranges of magnitude. Either genetically adapt the recurrent network to get integral behaviour or go back to back propagating the feedforward network from your EM406 days & hope it adapts faster than an integral.
Sign up now
to remove ads between posts
Jun 29, 2008, 06:50 AM
Registered User
Been watching your posts with great interest for a while now. Can you elaborate a little more on the inversion of NN's or post links to a couple of articles? This is an area of interest for me too.


Quick Reply
Message:
Thread Tools

Similar Threads
Category Thread Thread Starter Forum Replies Last Post
Discussion GPS Logging on Slope Flight Martini Slope Soaring 16 Jul 12, 2006 07:59 PM