"Thanks! Will do"
Benjamin's Page
Latest Activity
Benjamin commented on Benjamin's blog post Evolving aircraft control values using a genetic algorithmRoy Brewer commented on Benjamin's blog post Evolving aircraft control values using a genetic algorithm"Good point re: PID. Its sort of like the duct tape of the controls world - not very elegant, but can often be used by non-experts to decent effect, and can sometime lead to more problems.If you are interested in non-GA algorithms for control…"
Benjamin commented on Benjamin's blog post Evolving aircraft control values using a genetic algorithm"Roy
"How do you know that you have generated sufficiently diverse "children" such that they have explored a large enough region of the solution space?"
That is a very good question. I am not an expert in GAs, but enjoy…"
Roy Brewer commented on Benjamin's blog post Evolving aircraft control values using a genetic algorithm"Benjamin,
Thanks for the interesting post.
I am not that familiar with genetic algorithms. How do you know that you have generated sufficiently diverse "children" such that they have explored a large enough region of the solution space?…"
Øyvind Løkling commented on Benjamin's blog post Evolving aircraft control values using a genetic algorithm"Nice work!"
Ken commented on Benjamin's blog post Evolving aircraft control values using a genetic algorithm"Bravo.
"
Benjamin commented on Benjamin's blog post Evolving aircraft control values using a genetic algorithm"That is the Y dollar question. To apply this practically, the target aeroplane must be described accurately enough in X-plane so the simulation gives a usable result that can be tested in the real world. I would only test the high fitness results in…"
Jason Lyons commented on Benjamin's blog post Evolving aircraft control values using a genetic algorithm"Interesting work... but is there a way to apply this practically without a low fitness condition causing a crash?"
Benjamin posted a blog postEvolving aircraft control values using a genetic algorithm
I've been doing some experiments to evolve PID control values in X-plane using a genetic algorithm, with some success. I posted a description about the experiment on my blog. I didn't want to reproduce the entire post here, but thought I would link it and post a video of the experiment:Blog post:http://www.1011ltd.com/web/blog/post/evolving_pidEnjoy!BenjaminSee More
Benjamin commented on Dror Caspi's blog post Quiet, Tilt-Rotor Unmanned Aircraft Is Behind the Lines Spy"How complicated is the control for the 2-rotor VTOL you describe? And the in-out seems tricky. Seems to me a rear prop is a pragmatic solution to achieve less complexity"
Benjamin commented on Curt Olson's blog post Command Augmentation System"Very nice. Is the source available for study or is it proprietary?"
Daniel NIkolov commented on Benjamin's blog post First bumpy, but successful landing in X-plane with Erlang autopilot"Yeah for the most part. Keep me updated on your progress as it seems like a good practice and tuning system for your autopilot."
Benjamin commented on Benjamin's blog post First bumpy, but successful landing in X-plane with Erlang autopilot"The aim of the project is to run the autopilot on something like a beagleboard, so at the moment the autopilot code is running on the same machine as the simulator. Thus, there is no need to handle the serial data at this point. When I get there, I…"
Daniel NIkolov commented on Benjamin's blog post First bumpy, but successful landing in X-plane with Erlang autopilot"What type of source code are you using to run the serial data into the autopilot and the instructions back out? I have heard that some people are using Perl to do this. Do you have any reference material to the coding?"
Benjamin posted a blog postFirst bumpy, but successful landing in X-plane with Erlang autopilot
Quick update on my last post. My PID control and waypoint following is still in the early stages, but I've managed to take off and land with my autopilot in X-plane. Here's the landing: First bumpy, but successful landing in X-plane with Erlang autopilot from Benjamin Nortier on Vimeo.See More
Profile Information
- About Me:
- I'm a South African software professional living in London. I am a freelance software engineer with a keen interest (unfulfilled at present) for flying.
- Tell us a bit about your UAV interest
- Although I have no RC/UAV experience, I am very interested in building UAVs as a hobby, and also to explore commercial opportunities for UAVs. Specifically for wildlife and poaching control, and search and rescue.
- Hometown:
- London
Benjamin's Blog
Evolving aircraft control values using a genetic algorithm
Posted on December 22, 2010 at 10:30am 9 Comments 0 Likes
I've been doing some experiments to evolve PID control values in X-plane using a genetic algorithm, with some success. I posted a description about the experiment on my blog. I didn't want to reproduce the entire post here, but thought I would link it and post a video of the experiment:
Blog post:…
Continue First bumpy, but successful landing in X-plane with Erlang autopilot
Posted on September 14, 2010 at 3:02am 3 Comments 0 Likes
Quick update on my last post. My PID control and waypoint following is still in the early stages, but I've managed to take off and land with my autopilot in X-plane. Here's the landing:
First bumpy, but successful landing in X-plane with Erlang autopilot from Benjamin Nortier on…
Continue First step towards an autopilot: browser-based instrumentation using X-plane
Posted on August 25, 2010 at 6:46am 3 Comments 0 Likes
As my inaugural blog post on DIY drones, here's a video of my first step towards building an autopilot: browser-based flight instruments using HTML5 canvas and websockets, with measurements from X-plane via UDP. Here I am flying (badly) off into the subset over Cape Town:
Continue
HTML5 Flight Instruments Demo from Benjamin Nortier on Vimeo.
(ed: seems like…
Comment Wall
- No comments yet!
Social Networking
Top Content
Contests
Season Two of the Trust Time Trial (T3) Contest has now begun. The fourth round is an accuracy round for multicopters, which requires contestants to fly a cube. The deadline is April 14th.A list of all T3 contests is here.
Groups
-
ArduCopter User Group
1355 members
-
ArduRover User Group
207 members
-
Moderators
24 members
-
Documentation Editors
52 members
-
ArduPlane User Group
719 members
Advertisement
© 2013 Created by Chris Anderson.
Powered by
