Thread Tools
This thread is privately moderated by Jack Crossfire, who may elect to delete unwanted replies.
Sep 24, 2007, 03:48 AM
Registered User
Jack Crossfire's Avatar
Thread OP

First neural network flight

Well, the first test flight with the neural network estimating velocity happened in no wind of any kind. Used a new offline trained network with 6 inputs & 2 outputs, reduced the number of integration steps when predicting velocity to 1, and that got it fast enough to run on the Gumstix.

The neural network offered very little improvement over GPS when predicting velocity based on its own tilt feedback. Nevertheless, the velocity oscillation seemed 2 B gone. Instead, very large drifts in position happened.

The neural network may have eliminated small scale oscillations but left behind large scale oscillations. It may have done nothing and what we saw was virtually no wind combined with precisely calibrated neutral tilt.

Secondly, the offline training for that test flight was based on another flight recording with significant oscillation. When the network was trained using its own flight recording, it gave slightly better results. The network probably needs online training.
Sign up now
to remove ads between posts

Quick Reply
Thread Tools

Similar Threads
Category Thread Thread Starter Forum Replies Last Post
First real pico flight - first real pico crash - PARTS INFO PLEASE! rojoyinc Electric Heli Talk 2 Feb 23, 2002 11:46 AM
First Lite-Stick Flight Video Kidknight Parkflyers 18 Feb 13, 2002 12:05 AM
Help! first mini-max flight omega blood Parkflyers 2 Jan 05, 2002 10:12 PM
First Tiger Moth flight tonight.... it got the wife interested!! joemi Parkflyers 16 Oct 28, 2001 06:00 PM
My First T-52 Flight Aikens Foamies (Kits) 1 Apr 28, 2001 10:30 AM