/robowaifu/ - DIY Robot Wives

Advancing robotics to a point where anime catgrill meidos in tiny miniskirts are a reality.

Reports of my death have been greatly overestimiste.

Still trying to get done with some IRL work, but should be able to update some stuff soon.


Max message length: 6144

Drag files to upload or
click here to select them

Maximum 5 files / Maximum size: 20.00 MB

no cookies?

(used to delete files and postings)

AFFORDABLE, PRACTICAL WAIFUBOTS ARE POSSIBLE TODAY Robowaifu Technician 09/11/2019 (Wed) 01:55:08 No.103 [Reply]
I've seen plenty of ideas on this board over time that have completely convinced me that practical, affordable waifubots are possible with today's tech. With clever artistic decisions to make up for where the tech lacks, we can make perfectly cute, huggable, and fuggable waifus for what couldn't possibly be more than a couple hundred bucks. Hell, half the technology needed has been in childrens' toys for decades, and the rest is either in your phone, or is just sticking a bunch of onaholes in said toys. All you need to do then is make it cute, which costs practically nothing except for creativity.

I've made an infographic with ideas in this regard. Feel free to edit or add to it. I've never bothered to try to make infographics before, but I've heard the good news of robowaifus, and I want to help spread the word.

Additionally, use this thread to give any other ideas you have to help make actual practical waifubots. There is no need for this to be an endeavor that costs tens of thousands of dollars. And the cheap results shouldn't need to simply be tiny things you can't even fuck.

And remember, the key is that you don't need to have a perfect waifubot right away. You only need one good enough to market, both to make money, and to spread awareness of just how possible they are. This will then fund further tech and result in the waifus of your dreams.
20 posts and 14 images omitted.
The show was garbage.
>>862 >shitpost thread >implying loli Optimus Prime isn't a great idea I'm pretty sure it's canon. I've never read Kiss Players, but I've been told that's pretty much what it is. And Takara seems just Japanese enough to license it for robowaifus, if we get a real company going. To link it to the OP, there are plenty of affordable, moving Optimus Prime toys out there (though Transformers are way too expensive these days, if you ask me). Give it the loli features from your pic and a fleshlight, and you're set. Make it a "salt" powered robot, like mentioned above, and have her beg you to fill her with your "Energon."
>>2543 >And Takara seems just Japanese enough to license it for robowaifus, if we get a real company going. This. Any chance you could think about a) finding cheap toys suitable for your approach b) obtaining at least one of these for modifications c) performing said modifications and photographing the process d) making a tutorial thread here on /robowaifu/ dedicated specifically to this entire effort? It would be both a big help and an encouragement to everyone here if you could do so Anon. Each of us have our part to play. For example, AI Anon is researching papers all day. I work on software most days. We have a lot to do here and splitting up the load will only help everyone tbh.
>>2545 >a) finding cheap toys suitable for your approach b) obtaining at least one of these for modifications c) performing said modifications and photographing the process d) making a tutorial thread here on /robowaifu/ dedicated specifically to this entire effort? I wish I could, but I don't have nearly enough capital for this. And I don't think it's literally as simple as buying a toy off the shelf, because the more advanced robot toys are too small. Going for a small size makes way more sense, both in terms of money and in terms of the actual energy it takes to power the robot, but there is a point where it literally becomes too small to fuck, which defeats the point. What we really need is a company with the capital to produce toys like robosapien (or a modern version of it) make one that is twice as big, and has a body that can actually fit a fleshlight inside it. The rest is just the case. Again, modifying the outside of a toy to our purposes is difficult. But if we were the type of people who had a company that could make toys, like Takara or Hasbro or whatever (not that Hasbro would ever do this), it would be a trivial matter to make a toy that was just cute from the start, and also had a space for a fleshlight in the torso.

OpenGL Resources Robowaifu Technician 09/12/2019 (Thu) 03:26:10 No.158 [Reply]
Good VR is one important interim goal for a fully-realized RoboWaifu, and it's also much easier to visualize an algorithm graphically at a glance than 'trying to second-guess a mathematical function'. OpenGL is by far the most portable approach to graphics atm.

>"This is an excellent site for starting with OpenGL from scratch. It covers from very introductory topics all the way to advanced topics like Deferred Shading. Liberal usage of accompanying images and code. Strongly recommended."


Plus the two books related, but learnopengl.com is particularly well-suited for beginners.



Edited last time by Chobitsu on 09/26/2019 (Thu) 08:14:37.
18 posts and 16 images omitted.
Went ahead and created a public repo for this work.
Open file (236.01 KB 1920x1080 Workspace 1_012.png)
Well, it was kind of convoluted to work out all the details, but I've managed to add quality TTF text rendering to the MRS.
BTW, I removed GLAD as an external dependency. There's an option to create all-local files, so I moved MRS to that approach. It means anons don't have to deal with GLAD now.
Added a void rndr_tick(Shader txt_shdr, const unsigned fps_tick) function to ensure the MRS was really getting an honest 60fps (it is). However, occasionally I'd notice a little artifact that made me think that tearing was happening even though I set the swap interval to 1:
glfwSwapInterval(1); // 1 should prevent tearing

Now I'm not so sure it's actually tearing;
A) It only infrequently occurred
B) It is likely limited to only the fast-transitioning digit at the end, afaict.

This makes me think it's actually not tearing, but rather the screen capp program I'm using (Shutter) is simply 'snapping' the image right at the instant a digit is being redrawn. I'd welcome insight if anyone knows more about this stuff.
>pic related
Unrelated: Does the system redraw from the bottom-up? For some reason I thought the drawing happened from the upper-left corner down, but apparently not. Given that the coordinate origin for the system starts in the lower-left corner (similar to a Cartesian system) I guess that makes sense. Live and learn.

/robowaifu/ thread archives Robowaifu Technician 09/16/2019 (Mon) 06:36:14 No.273 [Reply]
julay robowaifu archives

https://archive.fo/yndgt Catalog

https://archive.fo/31E3X (Robo)Waifu personality thread
https://archive.fo/U4UPH /robowaifu/ is NOT dead.
https://archive.fo/A3A43 /robowaifu/ thread archives
https://archive.fo/YWPN7 3D printer resources
https://archive.fo/AK4tA AI + Brain/Computer Interface news & commentary
https://archive.fo/c0rRp AI Design principles and philosophy
https://archive.fo/lPRcU AI Software
https://archive.fo/nbA7W AI, chatbots, and waifus
https://archive.fo/SwCte About AI
https://archive.fo/y9f72 Actuators for waifu movement!
https://archive.fo/sAyZw Agalmatophilia
https://archive.fo/vHOdX Aoki Lapis model; Robot fairy
https://archive.fo/kjHh5 Artificial Wombs general
https://archive.fo/rEYe4 Batteries & Power
https://archive.fo/QBfEm Bipedal Robot Locomotion General
https://archive.fo/nO4L0 Building the ultimate waifu.
https://archive.fo/IaqKp C++ General
https://archive.fo/VlAmK Can Robowaifus Experience Love?
https://archive.fo/n6TOb Can the government really make anime real?
https://archive.fo/2RK3X Cuddling Robot
https://archive.fo/kGbHK Downloadable AI for robots?
https://archive.fo/i0W5a Electronics General
https://archive.fo/knsDo Embedded Programming Group Learning Thread 001
https://archive.fo/M8L4P Entry Level Waifu
https://archive.fo/Axxxd Fluffytail 800 dev thread
https://archive.fo/vpO2Y General Robotics news and commentary
https://archive.fo/habb1 Hold onto your papers
https://archive.fo/GNvBn Homemade doll waifu thread
https://archive.fo/59D0m Humanoid Robot Projects Videos
https://archive.fo/QKNPn IRL Drossel von Flügel?
https://archive.fo/H6MFt Important things about building living robots
https://archive.fo/zwpAv Meta Tread
https://archive.fo/3gJXH Micromouse - Minimum Viable Supercheap Open Source Robowaifu
https://archive.fo/WH2Pb My reason to live
https://archive.fo/Ch1ti Mycroft: Open Source Alexa
https://archive.fo/nVgJT NLP General
https://archive.fo/S5HgB New United Robowaifu Project
https://archive.fo/bwjgu New machine learning AI released
https://archive.fo/yFFUI Open Prosthetics
https://archive.fo/HjLB6 OpenGL Resources
https://archive.fo/PEZaa Papercraft waifu
https://archive.fo/Zbp32 Plastic Production
https://archive.fo/c2Khp Project: United Robowaifu Development
https://archive.fo/ZS3An Prototypes and failures

(1 of 2)
Edited last time by rw_archive_bot on 10/22/2019 (Tue) 04:40:12.
https://archive.fo/4oI7v Python General
https://archive.fo/jiIlz R&D General
https://archive.fo/K1mMj ROBOWAIFU U
https://archive.fo/0X004 Ricky Ma General
https://archive.fo/jhbyL Roastie Fear 2: Electric Boogaloo
https://archive.fo/1YZXA Roastie Fear General
https://archive.fo/kRw5G Robo Face Development
https://archive.fo/baQU5 RoboWaifuBanners
https://archive.fo/6a7Zv Robot Vision General
https://archive.fo/Aj3ue Robot Voices
https://archive.fo/RNuzT Robot Wife Programming
https://archive.fo/1q3TD Robot skeletons and armatures
https://archive.fo/O7Sov Robot skin? Possible sensitivity?
https://archive.fo/PggAO Robot waifu desires
https://archive.fo/6fzQg Robotics Hardware General
https://archive.fo/xYeg0 Robotics sites, organizations and projects
https://archive.fo/4XVDS Robowaifu Design Software
https://archive.fo/TozNM Robowaifu Simulator
https://archive.fo/ZWjOk Robowaifu Systems Engineering
https://archive.fo/ANueJ Robowaifu Thermal Management
https://archive.fo/h7WOV Robowaifu fiction to promote the product and expand the market
https://archive.fo/l6ie7 Robowaifu references
https://archive.fo/0YYO1 Robowaifu-OS & Robowaifu-Brain(cluster)
https://archive.fo/vGxXW Robowaifus in media
https://archive.fo/LDccH Robowaifus unique advantages
https://archive.fo/qSoqB Selecting a Programming Language
https://archive.fo/9MlZb Self-driving cars AI + hardware
https://archive.fo/q4lvk Self-replicating waifubots.
https://archive.fo/uckxp Single board computers & micro-controllers
https://archive.fo/lyjnv Speech Synthesis general
https://archive.fo/mG710 TensorFlow
https://archive.fo/j0lRU The Lounge
https://archive.fo/AXH9u The important question
https://archive.fo/awe7R Tools to Create 3D Models of Humans
https://archive.fo/rSxdo True Love
https://archive.fo/sXIrZ Visual Waifus
https://archive.fo/no96g Waifu Materials
https://archive.fo/fNNW3 Waifu Robotics Project Dump
https://archive.fo/W4jdA Waifus in society
https://archive.fo/x2aeH Walking
https://archive.fo/FmdeN Welcome to /robowaifu/
https://archive.fo/ViRty What can we buy today?
https://archive.fo/svCvW What happens to your robowaifu when you die?
https://archive.fo/XobuW Who wouldnt hug a kiwi.
https://archive.fo/BVu8m Wifu that gives you Hope.
https://archive.fo/HCuGs your file is too big onii-chan

(2 of 2)
Edited last time by rw_archive_bot on 10/22/2019 (Tue) 04:40:15.

Aoki Lapis model; Robot fairy Robowaifu Technician 09/16/2019 (Mon) 02:51:51 No.266 [Reply]
Height; 15cm
Type; Vocaloid

I'm making it in as natural looking way as I can, this means a bone structure and a similar layout of the electronics and components as with a living humanoid

This is a prototype version that I'm working on, I might change things later and make modifications or adjustments to the design or components
20 posts and 31 images omitted.
Teflon is explicitly designed to stay slippery. You might have better success using it over plastic insulation.

ah got it. i plan to eventually repopulate the threads here, including the electronics learning class one.

>Fab lab
cool. i've never been to one yet tbh. expensive?

>Also might be kinda tricky to 3d draw the parts properly but I might do that later actually
There's the Fusion 360 product anon, and Blender too ofc, whenever you feel inclined to design a reproducible system others can create as well.

Good luck.
Open file (7.82 MB 2138x1932 3d-printing-filament.png)
This insulation actually works surprisingly well like the video shows >>1004

Booking at a specific time probably costs, but I'm not sure how much and its kinda irrelevant for me right now anyway since I don't have money to spare
But it used to have open hours here for the public on specific days, I'm not sure if they have those open days since the schedule doesn't show it, but it still reads on the front page that they do, I'll have to check on that better later

I actually happened to get lucky the other day and got a bunch of 3d printing filament for free

Funnily when I started out making models for 3d printing I used sketchup
>I actually happened to get lucky the other day and got a bunch of 3d printing filament for free
very nice, gratz.

>Funnily when I started out making models for 3d printing I used sketchup
cool, cool. how was it?
It worked out fine, I would prefer to use something else for detail work tho
Fusion360 can get as detailed as they come. The (((Autodesk))) and (((cloud))) lock-in aren't to my tastes however. I think I'll stick with Ton & Blender.

Robowaifu-OS & Robowaifu-Brain(cluster) Robowaifu Technician 09/13/2019 (Fri) 11:29:59 No.201 [Reply]
I realize it's a bit grandiose (though probably no more than the whole idea of creating a irl robowaifu in the first place) but I want to begin thinking about how to create a working robowaifu 'brain', and how to create a special operating system to run on her so she will have the best chance of remaining an open, safe & secure platform.

OS Language Choice
C is by far the single largest source of security holes in software history, so it's out more or less automatically by default. I'm sure that causes many C developers to sneer at the very thought of a non-C-based operating system, but the unavoidable cost of fixing the large numbers of bugs and security holes that are inevitable for a large C project is simply more than can be borne by a small team. There is much else to do besides writing code here, and C hooks can be generated wherever deemed necessary as well.

C++ is the best candidate for me personally, since it's the language I know best (I also know C too). It's also basically as low level as C but with far better abstractions and much better type-checking. And just like C, you can inline Assembler code wherever needed in C++. Although poorly-written C++ can be as bad as C code in terms of safety due to the necessity of it being compatible with C, it also has many facilities to not go there for the sane coder who adheres to simple, tried-and-true guidelines. There is also a good C++ project already ongoing that could be used for a clustered unikernel OS approach for speed and safety. This approach could save drastic amounts of time for many reasons, not the least of which is tightly constrained debugging. Every 'process' is literally it's own single-threaded kernel, and mountains of old-style cruft (and thinking) typical with OS development simply vanishes.

FORTRAN is a very well-established language for the sciences, but a) there aren't a lot of FORTRAN coders, and b) it's probably not the greatest at being a general-purpose language anyway. I'm sure it could be made to run robotics hardware, but would probably be a challenge to turn into an OS.

There are plenty of dujour SJW & coffee languages out there, but quite apart from the rampant faggotry & SJWtardism plainly evident in most of their communities, none of them have the kind of industrial experience and pure backbone that C, C++, or FORTRAN have.

D and Ada are special cases and possibly bear due consideration in some year's time, but for now C++ is the obvious choice to me for a Robowaifu OS foundation, Python probably being the best scripting language for it.

(1 of 2)
12 posts and 12 images omitted.
Related convo crosspost:
And, all the power, control and data wiring out to the rest of the robotics platform can more easily be home-runned and consolidated into driver banks and the RWBrain there as well. In fact, I'd guess the brain and stepper-drivers and other electronics will probably take up the majority of the internal chest cavity at a first guess.
Fantastic idea, why not build your own Linux distro though? I'd imagine that would make things easier. A custom version of Debian that was light weight, had OpenCV, PocketSphinx, and a custom program to allow easy control of SPI devices to interface with low level sensors and servo/stepper controllers. That would be fantastic. Also, I agree that Arm should be the architecture of choice. Their upcoming Cortex A76 and Mali G76 look go be very promising for AI. I'm not sure clusters are a good idea for something that needs to be inexpensive. Clusters add complexity, cost, and heat into a system. Though it is a really cool idea, perhaps a cluster based server could be an accessory that she'd wirelessly connect to for upgraded capabilities at her home? Overall, a robowaifu OS is something is very much like to see happen. Especially because I'm working on waifu hardware and would gladly test this.

From what classic anime has taught me, this is used to summon demons from CRTs.
Good points. In fact I do intend to create a lean image of Devuan (Debian sans Poettering) to place in the Node 0 ARM device. This will sort of act like a moderated gateway to my project, and could easily be used in the manner you described. And Devuan has fantastic support already for imaging working snapshots, and has an abundance of ready-made images for various ARM and other devices already in place. So, if you'd like to get ahead and prepare now for where I'm going here, then get a box set up with Devuan and start playing around with it now.

As for your point about clustering, that's kind of a separate topic and has many benefits it brings to [my] table. If you really want to understand my rationale, then I'd suggest you watch the first three videos I've already linked. That should give you a basic understanding.

Thanks for the input anon.

Cuddling Robot Robowaifu Technician 09/18/2019 (Wed) 11:37:33 No.411 [Reply]
I saw this cool looking interactive snake-bot. Thought some of you might enjoy it. Someday our waifus will cuddle us just like – no even better than – the robot in these videos.

10 posts and 2 images omitted.
Open file (45.74 KB 600x315 am_i_kawaii.jpg)
>those girls can't cook worth a damn. They can't taste anything!
>Do any images exist of robosnekwaifus?
don't know, i haven't looked for any personally. i know there are a number of robots now that are in a snake-like form (for crawling through pipes and rescue work, etc) so it would surprise me a bit if some anon decided to put a wig, makeup and a kawaii little dress on one tbh.
>so it wouldn't surprise me a bit*
I'd only be worried about being assaulted by schnitzel and hefeweizen daily. I could probably still conduct myself but it raises concerns about mortality.
Open file (216.32 KB 512x499 eb_question3.jpg)
>Schnitzel and Hefeweizen
Who or what?
heh this. obviously germanbro/austrianbro is considering whether it's wise to keep a pet lamia or not. :^)

Important things about building living robots Robowaifu Technician 09/09/2019 (Mon) 05:38:28 No.19 [Reply]
Robots in our price range would have to be made of cheap, but sturdy materials.

3D printed nylon is a good material, as it is sturdy, doesn't shatter like PLA, and is tolerant of many temperatures. Aluminum pieces like those in a VEX set are good for things like the thoracic vertebrae, or the femurs.

AI is also not born perfect. It is created like a child. You must raise it to be social. To accommodate this, an infant model must be built for the robot to learn basic social skills, movement, etc. Even MLAATR itself has shown this, though I imagine a head on a small body with simple legs or wheels would suffice. You could simply remove the head and place it onto the older body as a birthday gift for it.

I also have to point out something that might disappoint, do not read this spoiler if your dreams of a robot wife are delicate. You cannot fuck your robowaifu unless it's an already-existing girl's consciousness stuck into the robot. Making your own waifu's mind is like father and child incest.
5 posts and 2 images omitted.
Well, it’s true you have to train AI like a child, I think there are some things worth noting though.
A human has to be raised because it’s only born with genetic memory, such as drink milk, cry when hungry, all that stuff. It has no inherent understanding of society, languages, survival, or scientific knowledge.
Basically humans are a package you can drop anywhere and it will (hopefully) learn how to adapt to its surroundings.
I think robots can be a bit more robust than that. Its “genetic” memory can include encyclopedias of knowledge, translators of every language, scientific and mathematical calculators. Basically all that’s left to learn is how to adapt to its surroundings and its local society.
If you don’t want your robot roaming around town learning how people interact with each other, you’re gonna need to program in a personalty. At the very least its going to have to learn to live with you, hopefully it will enjoy that.
The problem with that is that commercially available programs can only self-teach in one direction. They can become practically human in their speech patters, and can then also learn to walk, but they can't connect the word "walk" to the action of moving their legs to go places. They can't even connect something as simple as moving to the word "moving".
That's why it's kind of silly to describe your creation as a child, even as it gets fully-taught, it will still have less learning power and less self-awareness than an insect. It's also silly because the thing already exists purely to solve your problems, and is given no time to express consent in this, so why limit yourself to taking total advantage of it in only some ways?
We simply don't program them to be able to learn multiple things. The problem is that we restrict their learning network. What needs to be done is simply giving pre-programmed groundwork, such as feeding, talking, etc. The rest of the programming comes from learning and what not. Also, we're eventually going to have to ascend to robotic bodies and what not, and if our only robots are preprogrammed sexbots, we are fucked.
I'm currently working on mine. If I could, I'd mass produce these and make a pretty penny. Good idea or no?

Pic related. Shit game, but selling these is a good idea.
Sure. You just gotta make sure your consumers know your robots are to be raised with as much discipline as a child. Basically like those robot dogs, but they actually grow up. If you are truly successful, you might have robots buy their own kind. Or cause a revolution or something, but by the time that happens, I'm sure you'll find a way to compromise that.

Entry Level Waifu Robowaifu Technician 09/15/2019 (Sun) 08:02:15 No.245 [Reply]
So I've been lurking here for a little while. I figured it's finally time I made a thred so I have a place to share my ideas about a project I want to build. Robowaifus has been a dream of mind for a good while, i'm glad I stumbled across this place.

So with this project I want to focus on something that is viable now, with todays tech. And it has to be affordable, under $1k. I don't have 10k to drop on Real doll robot, or even 2k for a sex doll. This also has to be something an average anon like me can piece together. I'm not an engineer or a programmer.

So my fist version of this won't be including any robotics. The goal will be to put a computer inside a doll, with a voice interface and chatbot AI. As well as a battery pack so it's portable. I'm think by really focusing on the right elements, I can build an effective waifu.

I think AI is vital to robowaifus. More vital than the robotics. That's what's gonna make this whole thing a viable option. Having something you can connect with. I want to start exploring that.

That beings aid, I think from is really important too. There's no need to have an AI voice in a plain speaker like Amazon and Google are offering. We can easily do better than that. And without the botnet and privacy concerns.

I vastly prefer 2D over 3DPD. I also think it's a great way to sidestep the uncanny valley. It's herd to get a 3D version of a 2D character that looks right. One of the best I've seen are the 1/3 scale vinyl dolls like the Dollfie Dream. Danny Choo seemed like he was on the path to create a robowaifu version of these dolls with his Smart Doll, but the version he eventually released is non robotic. It does however have a mostly hollow torso that could be filled with electronics. I think the Smart Doll is a great base for a project like this, and they are highly customizable too.

Alright that's enough to start, I'll be going into more detail in future posts.
1 post omitted.
Hey anon, glad to see your project thread, welcome. Seems like you have good insight on costs. This stuff will be expensive, one way or another.

I also like the idea that good AI is a vital initial phase for your project. Sad to say, from my perspective at least, it's also the most difficult problem (in the long list of problems) to solve when inventing good robowaifus. But I think with everybody pitching in ideas, then some geniuses among us might pull of a breakthrough or two. We'll see. But as you said, we certainly do not want botnets infesting our beloved robowaifus.

And yea it's kind of a theme here "Waifubots, not slutbots", crude as it is. Why some big corporations are not already making cute waifubots is quite beyond me tbh. The pent-up demand is very plainly a huge one.

Obviously full-sized will be the most desirable, but I think for the first several years scale models are the only practical approach while keeping the costs relatively modest. Danny Choo's injection-molding line when it's in full swing will probably be a good model to look at for a BJD approach.

There's lots of challenges ahead. Good luck to us all anon.
Yeah it seems like the madman was actually gonna do it for a while, create robo waifus. They would have been expensive though and it would have been an even more niche product. Pandering to normalfags is probably the better business decision.

I see the goal of waifubots as simulating relationships and companionship. And it's not that i'm some puritan who's against the idea of sexbots, simulating sex has already been solved. Sex robots for both mean and women already exist, and have for years. Onaholes can be bought online for under $20, you can do VR on your cellphone. The technology is already here and readily available. When people say sexbot, they are usually talking about a full robotic humanoid that's also capable of having sex. That's like calling a computer a porn machine.
I know people want one that can move around and stuff, but wouldn't it be easier to focus on the AI and the mechanics first before making it fully portable? I know back when this board was on 8chan, there were a few on-going projects that just halted because of the magnitude of what they were trying to do. It would be nice to see someone's project come through without getting burned out or bogged-down.
>but wouldn't it be easier to focus on the AI and the mechanics first before making it fully portable?
Not that anon, but I agree with you anon. The challenge of creating an inexpensive bipedal robowaifu is challenging atm to a high degree imo. This is why the Visual Waifu thread was started, to enable forward progress in the AI and simulation arenas simultaneously with the mechanical systems.

>the magnitude of the problem
The laws of nature don't care how good one's intentions are, heh. You either satisfy the constraints of real physics or you fail. Simple as that. So yea, I think a lot of younger anons go into this over-enthusiastically w/o really understanding, as you indicated, the magnitude of the problem.

That opens up whole other areas of discussion about the correct approaches to this whole topic of DIY Robot Wives. I'd be happy to go there if you're up for it anon.

Hey, if this were easy, everyone would be doing it!

Self-replicating waifubots. Robowaifu Technician 09/18/2019 (Wed) 11:38:52 No.412 [Reply]
Why not build a waifu with a rudimentary AI and give her the objective to help you build a better waifu with better AI and repeat the process until you get one that is perfect?
7 posts and 1 image omitted.
In the far future, I can imagine billions of robot catgirls conquering the galaxy, 3D printing their sisters into existence. The implications are insane… imagine if they have artificial wombs installed, they can terraform the entire solar system for us.

But right now I'm just thinking of a Minimum Viable Product. With my current abilities that means is no better than a fancy Tickle Me Elmo, except one that arches her back, sticks her butt out, and goes Nyaa every 10 seconds. Just think of NPCs, they only speak two lines but it's good enough for me to find them attractive.
Pretty simple once you reach human-tier levels of dexterity and motion planning. Then you simply employ excess robowaifus in your robowaifu factory as sweatshop slave labor. There you go, self-replicating waifubots.
Perhaps you can go from nanobots to humanoids through hyper-evolution. It's not any less fictional I suppose.
>self replicating waifubots
Open file (1.03 MB 1528x686 Selection_029.png)
QT-pi RoboEnforcer GF when anon?


Open file (34.77 KB 480x360 0.jpg)
Downloadable AI for robots? Robowaifu Technician 09/15/2019 (Sun) 07:59:54 No.244 [Reply]
When I say AI, I mean actual robots that learn how to use their own inputs and outputs, not just chatbots. Are there any downloadable AI programs? I'm the OP of the Drossel thread, and I'd like to see if there's any downloadable programs for this shit. Also, I'd like some tips for inserting mounts for servos and shit inside the Drossel model.

There's shit-tier AI that comes embedded in boards such as Sparkfun Edge (tensorflow voice recognition) and ESP-EYE (face recognition), pretty limited but otherwise offline after firmware updates. I have those boards but haven't started using them yet.
Tensorflow might be your best bet. Deep learning “AI”, which is really just fancy statistics, is the current meme that lets robots learn about their bodies.

Honestly I don’t know how possible any of this is without citing some Ph.D research papers.

Report/Delete/Moderation Forms

Captcha (required for reports)

no cookies?