Search the Community

Hi all, I've updated this front post with the awesome gallery by wile1411 Hardware Project Links @Mulbin - Link @stibbons - Link @Luis - Link @MrOnak - Link @Krewmember - Link @cm2227 - Link @Antipaten - Link @7thGraal - Link @AmeliaEatyaheart - Link @zitronen - Link @KK4TEE - Link @Peter KG6LSE - Link @NeoMorph - Link @ChaseHQ - Link @T.A.P.O.R. - Link @richfiles - Link @mr. engino - Link @hugopeeters - Link @Freshmeat - Link @One Wheeled Panda - Link @lawnmowerlatte - Link @Freshmeat - Link <image pending> @Steven Marlowe - Link @JoshTheCoward - Link @mountaineerman - Link @mountaineerman - Link @Sputnix - Link Jeff Rogers - Link @niko1499 - Link @rhcprul3 - Link @Apache600 - Link @KK4TEE - Link @marzubus - Link Joycem134 - Link @zitronen - Link @hakan - Link @Daid - Link @ytmytm - Link Makerforce - Link Roo - Link @drat1856 - Link @ajden - Link @ohMorrissey - Link Simon Rob - Link @JeffSergeant - Link @Kotagi - Link @Monsterlunch - Link @KingLuxor - Link @Crawcik - Link @Hacourt - Link @Captain_Hair - Link @REMD - Link @Hebel - Link @kl0buk - Link If I've missed any or you'd like a link removed, let me know and I'll edit the post. Also, if you want a different link / image - same deal. Console Count: 54 Last Updated: (updated 24-Sep-2018) - New project by kl0buk

i'm making this post so people can share their early experiments with Breaking grounds Here's a small Rocker Bogie rover that thing really sticks to the ground Configuration : motors disengaged, unmotorized. maximum angle set at -45° to + 45° on each of the hinges

Hi everybody! (UPDATE on page 3, it's now sort of working) Hope I'm in the right section, I don't come very often to the forums, so just tell me if I got this wrong! So here's the idea: for a few months now I've been thinking about hooking a machine learning program to a rocket and pressing 'Launch' to see how bad things could go. I've looked it up, but it seems not much people have * actually* done it successfully. So HUGE disclaimer: I have no idea where this is going to go. Maybe I'll stop in 2 weeks, maybe I'll get super on board with the idea. But I think there's something really cool to try here and that's all I need. The main idea I have for how to do this is: - Control KSP through the kRPC mod, enabling us to run Python, which means we can import any machine / deep learning librairies alongside it. - Use reinforcement learning to learn from each launch, and try to improve the performances of the rocket. Note that here I'm not trying to generate a rocket design, I just start from a particular rocket and try to teach it to fly it. To put a bit of context around this, I have a few months of practice on neural networks (using mostly Keras over TenserFlow, which will most probably be the library used for running the basic neural network that will be trained) I have barely used kRPC for a hours the last few days to say what was possible with it, I just made a successful program that reloads a quicksave when a rocket after a certain time and looks at the altitude it's gone, to see if it was possible. I've also been through some of the documentation. Oh, and I've never done anything related to reinforcement learning, so just like when I started playing KSP a few years a go, I don't really know what I'm doing, but I have theoretical knowledge, and think this could be fun, that's good enough for me to start! I thought opening a new post here on the KSP forum could be a good place for me to first of all take the time to lay down what I want to do, and get some feedback from people that might have more experience than me, maybe some people might even want to follow progress on this! So to make things a little more interesting, I'm gonna give my IA a name, because I don't like how we just refer all the time to "IA". I'm going to call my 'IA' Bertrand. So, here are the initial ideas I have (this will be a bit technical as the trickiest part of this is to get a neural network running and interacting with KSP, while minimising the RUD counter). - In order to make any reinforcement learning, we need to define a loss function, this is what the neural network is going to have to minimize. Basically what is Bertrands purpose in life? What I would like to try for the very first stage is to get the rocket to a certain altitude. Say 50km to start with. That sounds super easy: just full throttle and nothing else. Yeah, but you haven't seen how dumb a untrained neural network is. So basically the reward function would be something like a function of the altitude, say Altitude*10 and you get -500 if you blow up (this is just a rough idea first, I have to figure out the specifics later). I think taking into the account the amount of fuel left when reaching the altitude is also important, as that's what we want it to do: be the best rocket out of all the self-teaching rockets out there, and make the best ascend possible, using the least amount of fuel possible. - Second, the controls: Bertrand, my IA, needs to be able to control the rocket to make it blow up fly it. But the thing is, with KSP, controls aren't really something we're short of. Remember, Bertrand is going to be really, really dumb at first, we're talking cat-walking-on-a-keyboard-level dumb here. I thought having control over yaw, pitch and thrust would be a good start. Since most rockets are cylindrically shaped, roll doesn't have much of an effect, and I think keeping just 6 buttons (2 for each control) is already going to be hard enough. I'm also afraid that if we start letting roll in, it will heavily confuse Bertrand, because it will change what yaw and pitch do. If this thing turns out to be a good idea, I might add multiple stages to my rockets and thus decoupling as a control. (I'm also pretty curious to see how it starts just randonly decoupling at any time and things just blowing up even more). But I'm worried that at first decoupling will make the capsule hop and give an easy win, so Bertrand keeps doing it without learning anything else. But we'll save that for later, let's not spoil Bertrand too much for now. - Third, this is going to need to run a loooot of times before Bertrand starts doing something not stupid and actually understand it has to throttle up and not do anything else to lift off. This is where my little kRPC program comes into play. I can make it reload the game as soon as the ship blows up, or reaches a certain altitude, and store the final altitude at which the game is reloaded. That's what I managed to do in a few hours of tinkering on kRPC, but I'm also going to need to register all the keystrokes Bertrand does, those are going to be the inputs of the neural network. That's a bit more tricky, but I don't think that going to be very hard. The hard part is going to be feeding that to the neural network. - Fourth I only have a Xiaomi Mi Notebook Pro, and that thing only has an 8th gen i5, with 8Gb of Ram and most laughable of all, an mx150 for a GPU. This bad boy doesn't have any issue running KSP at beautiful max settings and 60fps no problemo. But we're gonna have to train Bertrand too. And Bertrand is going to require some serious hoursepower to get better. This means I'm probably going to run KSP at a stupidly low resolution, and potato graphical settings to just even *try* to train the neural network. This is why it's going to be very important to keep the neaural network architecture as simple as possible! If that turns out to be really too long, I'll see if it isn't possible to use a Kaggle Kernel to get access to the free GPU and connect it to kRPC. Otherwise I might have to pay an online GPU, but I'd rather keep that as a last resort, I'm just a poor lonesome student with a bit too much time on his hands, but surely no money to rent a GPU. So I'll simply take this as the "optimization"' success trophy in my Bertrand plays KSP game. And if hooking a Kaggle Kernel to kRPC doesn't work, I'm not even sure it would with any other paid service; but that's for later anyways. - The idea I have, from this article from people that previously seemed to have relatively done what I want to do would be to use OpenAI's Gym, as a support for the reinforcement learning. OpenAI launched a thing called Universe a while back that was supposed to support KSP, but that got cancelled before we had time to see Terminator-powered rockets take over. But these guys (the ones from the article) made their own environment compatible with the Gym, which I will very happily clone, and tweak according to what I will be trying to do (after I eventually understand all of it). I'm basically going to use what these guys have done to try to get something working. I do think I should spend some time learning how to use OpenAI's gym on easier examples first before doing that though. So Bertrand isn't even going to see the world inside KSP first! That's basically how far my reflexion has gone for now. I've spend a good amount of time going through the internet looking for people trying this, and as I mentioned earlier, didn't seem to find anybody that did achieve this, apart from the guys who's work I shared in this last point. I also saw that a few years ago a guy streamed his neural network training, but that's long been finished, so I can't see that anymore Just to conclude here is what I have already done: Using kRPC, I made a program that goes on for 5 epoch (or 5 times) and each time makes the rocket turn after epoch_number seconds, then waits 5 seconds, gets the altitude the rocket got at after those 5 seconds, and reload to the last quicksave. These altitudes are stored in a dicitonnary called Dict_alt that is displayed at the end. This was my initial test to see if it was simply possible to be able to run multiple launches one after the other without me coming in. And storing in a dictionnary will probably need to be changed to a dataframe using a cuddly panda. TL;DR: I have no idea what I'm really doing, but I want to train an IA to fly a rocket, and I have a lot of work ahead of me for this to even remotely work. Anyways, if this is interesting to follow, well take a seat and prepare to wait a long time, and if you have any good ideas on how I could do this, things I have forgotten even if I haven't even started or improvements, please let me know! As I said, I don't really know what I'm doing with this, so all and any suggestions would be greatly appreciated! Thanks for having taken the time to read this! I hope this turns out to be a real project, maybe!

The KSP Moderation Team is proud to present Threads of the Month Awards, for June 2019! First up we have @sgt_flyer's thread where forum members are experimenting with parts from the new DLC Breaking Ground. Next we have @Jirokoh who is attempting to teach his AI 'Bertrand' to fly to orbit. We wish you the best in your endeavor and await the inevitable 'Is using AI cheating' thread. Congratulations @Kronus_Aerospace who has built a gorgeous F-104C Starfighter replica followed by some hilarious experiments with part offsets. @Willbl3pic has created a mod that allows you to control your KSP craft from within Minecraft in what has to be the most difficult control system ever devised. Well done, Mate! Keeping with the control theme we'd like to give a big shout out to @Mulbin and all the great contributors in this long running thread who have built or are building their own custom KSP hardware. And finally, while it is not a thread, we would like to give a special mention to @Stratzenblitz75 who has managed a rare first: getting to orbit using only jet engines and deviousness. Congratulations to all for your wonderful contributions and please remember to report a thread (add the comment 'totm') or PM a moderator if you feel it is worthy of thread of the month. Also thank you @Servo for your nomination. All winners are free to add the Thread of the month badge (created by our very own @adsii1970) to their posts, signatures or have it tattooed on their body if they are of legal age.

This craft is a full stock 1:1 replica of the F-104C Starfighter. Intended to be simple replica to serve as my introduction into the world of fighter craft replica's. Instead it became one of my highest part count fighter craft and by far my most accurate replica in general. With 660 parts it's a hefty 40 tonnes, however due to how it was designed it still has decent enough aerodynamics that a bit of engine clipping has allowed it to achieve the required performance. It is able to reach mach 2.6, which is much faster than the F-104 actually ever flew at, although the F-104 possessed the power and aerodynamics to achieve such speeds, however parts like the cockpit limited its speed as it was never designed to take such strain. It has a rotation speed of 60 m/s A stall speed of 40 m/s Its maneuverability...Well, it won't exactly be flying under any bridges All pretty much what you would expect from an F-104, so not a big loss. On the development side, this craft came to together slowly but smoothly. I spent just as much time in the blueprints as did actually building it, the result was that I really had to redo or adjust many sections. This style of building is one I have been employing for a while, but this craft shows the fruits of that labor more than any other. BIG THANKS TO PHANTOM AEROSPACE! Fellow builders have been suggesting that I build a fighter replica for quite some time now, although I always refused. That is until @Phantomic suggested that I start off simple to ease my way into it, specifically the F-104. I just want to give him a huge thanks for encouraging me to build this, as it was one of the most fun replicas I have done in a long time. Please check out his craft, he makes a variety of craft from really detailed trucks and other vehicle replicas, to really sexy and practical stockprop fighter craft. https://kerbalx.com/PhantomAerospace Also you should download his own F-104C replica, it's excellently done and quite practical, plus all of that for exactly 1/10 the part count of mine, you can't beat it! https://kerbalx.com/PhantomAerospace/F-104C Download Link: https://kerbalx.com/Kronus_Aerospace/Kronus-F-104C-Starfighter