/robowaifu/ - DIY Robot Wives

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

LynxChan updated to 2.5.7, let me know whether there are any issues (admin at j dot w).


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.

#WEALWAYSWIN

Max message length: 6144

Drag files to upload or
click here to select them

Maximum 5 files / Maximum size: 20.00 MB

Captcha
no cookies?
More

(used to delete files and postings)


Welcome to /robowaifu/, the exotic AI tavern where intrepid adventurers gather to swap loot & old war stories...


Python General Robowaifu Technician 09/12/2019 (Thu) 03:29:04 No.159 [Reply] [Last]
Python Resources general

Python is by far the most common scripting language for AI/Machine Learning/Deep Learning frameworks and libraries. Post info on using it effectively.

wiki.python.org/moin/BeginnersGuide
https://archive.is/v9PyD

On my Debian-based distro, here's how I set up Python, PIP, TensorFlow, and the Scikit-Learn stack for use with AI development:
sudo apt-get install python python-pip python-dev
python -m pip install --upgrade pip
pip install --user tensorflow numpy scipy scikit-learn matplotlib ipython jupyter pandas sympy nose


LiClipse is a good Python IDE choice, and there are a number of others.
www.liclipse.com/download.html
https://archive.is/glcCm
51 posts and 12 images omitted.
Open file (20.03 KB 560x321 GottaPyFast.png)
Sentdex created an open-source Python code transformer model like Github Copilot. It has only been trained 2 epoches so it's not great but it's interesting and fun to play around with. I feel it's gonna be important to stay on top of these developments to keep up with AI-accelerated productivity so I made an easy-to-use GUI to inference these models (just press Control+Tab to generate.) GottaPyFast: https://gitlab.com/robowaifudev/gottapyfast/ Sentdex Demo: https://www.youtube.com/watch?v=1PMECYArtuk Sentdex Model: https://huggingface.co/Sentdex/GPyT How to use the model: from transformers import AutoTokenizer, AutoModelWithLMHead # set device to cuda if you have a GPU device = "cpu" tokenizer = AutoTokenizer.from_pretrained("Sentdex/GPyT") model = AutoModelWithLMHead.from_pretrained("Sentdex/GPyT").to(device) def generate(model, query, max_length=100, top_p=0.9, temperature=1.0, do_sample=True): newlinechar = "<N>"

Message too long. Click here to view full text.

Trying to package PyTorch and Transformers for Windows is a nightmare. I put together some notes here on how to get it to work: https://gitlab.com/robowaifudev/cookbook/-/wikis/python/pyinstaller I think using MLPack would be much more practical. PyTorch takes up a massive 3.1 GB which is completely unnecessary. Another option could be to rewrite the GPT2 transformer model to use NumPy instead which is only 5.4 MB. I'll look more into this later.
>>11683 Thanks for all your hard work here Anon. I apologize to you and everyone else here for being such a pussified faggot about Python. I recognize it's important to all of us, or else I wouldn't even consider picking it up. Please look into mlPack sooner rather than later if you at all can. It's probably our only real hope for doing waifu AI on a shoestring budget hardware-wise.
Open file (13.19 KB 849x445 chainer.png)
>>11684 MLPack's documentation is really lacking, especially for newer features and seems to be missing essential features. I'd I have to sit down with it for 3-6 months to get transformers and text-to-speech models working in it. I'm looking into using Chainer which is built on top of NumPy and quite popular in Japan. A basic application with Chainer packaged with PyInstaller compresses down to 14 MB. On top of that there's already lots of ML models implemented in it. I think if I roll out some waifu tech with Chainer to garner interest we could get some more help to build things in MLPack, which will be particularly useful for embedded systems and actual physical robowaifu.
>>11688 Migration guide from PyTorch to Chainer https://chainer.github.io/migration-guide/

Embedded Programming Group Learning Thread 001 Robowaifu Technician 09/18/2019 (Wed) 03:48:17 No.367 [Reply] [Last]
Embedded Programming Group Learning Thread 001

Greetings robowaifufags.
As promised in the meta thread, this is the first installment in a series of threads where we work together on mastering the basics of embedded programming, starting with a popular, beginner-friendly AVR 8-bit microcontroller, programming it in C on linux.

>why work together on learning and making small projects that build up to the basis of a complete robot control system instead of just posting links to random microcontrollers, popular science robot articles, and coding tutorials and pretending we're helping while cheerleading and hoping others will do something so we don't have to?
Because, dumbass, noone else is going to do it. You know why in emergency response training they teach you to, instead of yelling "somebody call an ambulance!," you should always point to or grab someone and tell that person to do it? Because everyone assumes someone else will do it, and in the end, noone does. Well, I'm talking to YOU now. Yeah, you. Buy about 20 USD worth of hardware and follow the fuck along. We're starting from zero, and I will be aiming this at people with no programming or electronics background.

>I suppose I could get off my ass and learn enough to contribute something. I mean, after all, if all of us work together we can totally build a robowaifu in no time, right?
No, the final goal of these threads is not a completed robowaifu. That's ridiculous. What we will do though, by hands-on tackling many of the problems facing robot development today, is gain practical and useful knowledge of embedding programming as well as a more grounded perspective on things.

>so we're just going to be blinking a bunch of LEDs and shit? lame.
Not quite. We will try to cover everything embedded here: basic I/O, serial communications, servo/motor control, sensor interfacing, analog/digital conversion, pulse-width modulation, timers, interrupts, I2C, SPI, microcontroller-PC interfacing, wireless communications, and more.
93 posts and 16 images omitted.
>>3838 >moving eyes What I want is eyes that make eye contact with me, and possibly do cute things like shyly looking away and then back. It would work like the moving eye rigs you saw in the other thread, but there would be cameras installed inside the irises and an AI (CNN?) that learned to move the actuators such that the eyes pointed towards human eyes. (Pretty straight forward object recognition task.) >pressure sensors, piezoresistors or capacitive touch sensors We discussed this in another thread and talked about different options. I can't seem to find that thread right now though. What is the ohms of the resistors you are using? Mine are blue and use the 5 band codes, so I had to learn how to read the code and I don't think I got it right. Using the color codes I guess 220 ohms, and that's what I used.
>>3838 Another thing that would be valuable to learn is communication between the board and the PC. I'd probably want a wireless connection, and I'd want the PC to be running python (so as to interface with tensorflow).
> <archive ends>
Are you still with us, OP? Your thread convinced me to read the K&R 2e book. #include <stdio.h> /** * Print Fahrenheit-to-Celsius table using the formula: * C = (5/9) (F-32) * @code * 5 F-32 * ----- x ------ * 9 1 * @endcode * * @return exit status, 0 = success */ main() { int lo = -20, hi = 130, step = 10;

Message too long. Click here to view full text.

>tfw you find yourself innocently enough first just studying esoteric treatises, then presently realize you must now LARP as Thompson & Ritchie and only do your programming work using Vim, while trying to imagine what it must be like to craft UNIX & C using just an ancient 8K RAM minicomputer. The power of autism is generally what changes the world tbh. https://www.bell-labs.com/usr/dmr/www/chist.html

Open file (485.35 KB 1053x1400 0705060114258_01_Joybot.jpg)
Robowaifu Simulator Robowaifu Technician 09/12/2019 (Thu) 03:07:13 No.155 [Reply] [Last]
What would be a good RW simulator. I guess I'd like to start with some type of PCG solution that just builds environments to start with and build from there up to characters.

It would be nice if the system wasn't just pre-canned, hard-coded assets and behaviors but was instead a true simulator system. EG, write robotics control software code that can actually calculate mechanics, kinematics, collisions, etc., and have that work correctly inside the basic simulation framework first with an eye to eventually integrating it into IRL Robowaifu mechatronic systems with little modifications. Sort of like the OpenAI Gym concept but for waifubots.
https ://gym.openai.com/
117 posts and 53 images omitted.
What looks to be a very useful header-only C++ wrapper around the OpenGL C API. I'll try to make some time to have a look at it over the summer. https://oglplus.org/oglplus/html/index.html https://github.com/matus-chochlik/oglplus
Open file (407.22 KB 892x576 MoxRigForBlender.png)
Open file (23.94 KB 566x698 momo_rig.png)
Here's something I found through our Japanese colleagues. MoxRig / MomoRig https://mox-motion.com/ - I didn't try it out, but it seems to be useful for animation of human-like movement and simulation of robots.
>>11497 Neat! Thanks Anon, I'll give it a lookover.
>>11022 >emoji friendly islamic reminder this is a chan don't use emoji please

Open file (32.03 KB 400x400 FXCY9fGv.jpg)
THE LANGUAGE PROBLEM Robowaifu Technician 11/20/2020 (Fri) 13:22:39 No.6937 [Reply]
'Sup anons? I am here to remind you guys something important, TO DO YOUR RESEARCH IN MULTIPLE LANGUAGES. Our mutual language is English however that is not enough. We need people who can speak those 3 important languages: Japanese, Chinese, Russian. I've been learning japanese for 4 months and with the help of dictionary I am able to understand basic stuff. Here is the point, there is a whole another world out there. 1) Chinese: Chinese people work under such hard circumstances and put really much effort into their jobs. Nearly none of the projects are translated into English since Google is banned at China. However there are a lot of great stuff there, I mean like even Microsoft runs their virtual woman project there. Since it is too hard for me to learn I generally use DeepL (best translator out there) and Baidu (Chinese search engine) and read latest researches and projects there. I wish I knew chinese well, in that case I would be able to find not-so-popular webpages and grab more information on topics. 2) Japanese: Even though good Japanese projects gets translated into English most of the research there gets translated only when the projects is ready to publish and sometimes they are too hard to find. I try to read as much AI papers in Japanese as I can. Scientists there do great stuff. I've seen a lot of robowomen projects there. You can also find some 3d printing projects for anime girls. Really worth looking. 3) Russian: Russian is the least important one in my opinion. But a professor of mine graduated from a university there and he has a lot of academic books that aren't translated to English. You would be amazed at how much work they have on stuff such as algorithm theory, artificial intelligence, computer science. Most of the stuff there are focused on "science" part of CS. So they are theory-weighted. So right now we need people who can speek Japanese and Chinese (Korean would be good as well, but there isn't that much of research there tbh) Using DeepL is enough to understand most of the pages but only a person with fluent Chinese/Japanese would be able to find goldmines deep there. I am pretty sure that there are hundreds of Chinese people working on robowaifu related projects that we are not aware of. Same applies for Japanese people, but since Chinese people are in a much worse situation it becomes really hard to find those people. Anyone has some recommendations? I wish I had time and skills to learn all those languages but I can only afford to learn one and I am going with Japanese since I have a dream of moving there in the future. We need to brainstorm on this issue.
14 posts and 1 image omitted.
>>11389 >is an old post Heh, don't worry Anon. This isn't a typical IB in that sense. That is, there's no such thing as 'necrobumping' here (or any complaints about it either). If you have something to add, by all means put it in the correct thread.
Open file (476.56 KB 1100x600 example2.png)
Sometimes PDFs don't copy and paste text correctly because researchers upload scanned documents and whatever OCR they used on it sucks. For a long time I've been using Google Keep which has a great multilingual OCR feature but I'm looking for a simpler open-source solution so I don't have to copy pages and pages of paragraphs. So far I've found these two that support Asian languages: https://github.com/PaddlePaddle/PaddleOCR https://github.com/JaidedAI/EasyOCR It would be great to have a tool one day that automates PDF OCR and prepares it into a document for translation on DeepL. A lot of the time I just ignore research in other languages because it's such a hassle to read.
>>11491 I think I understand the need you're describing Anon. Having no experience with what's being depicted, I'm confused by the provided image however. Any chance you can break down what's being represented there for the uninitiate?
>>11492 It's optical character recognition. It's outputting the bounding box coordinates of text in the image, the predicted text, and the confidence level.
>>11494 Ah, I suspected that might be the case, seemed to make sense. I presume the Asian characters would be sent through some kind of translation software afterwards?

Hand Development Robowaifu Technician 07/28/2020 (Tue) 04:43:19 No.4577 [Reply] [Last]
Since we have no thread for hands, I'm now opening one. Aside the AI, it might be the most difficult thing to archive. For now, we could at least collect and discuss some ideas about it. There's Will Cogleys channel: https://www.youtube.com/c/WillCogley - he's on his way to build a motor driven biomimetic hand. It's for humans eventually, so not much space for sensors right now, which can't be wired to humans anyways. He knows a lot about hands and we might be able to learn from it, and build something (even much smaller) for our waifus. Redesign: https://youtu.be/-zqZ-izx-7w More: https://youtu.be/3pmj-ESVuoU Finger prototype: https://youtu.be/MxbX9iKGd6w CMC joint: https://youtu.be/DqGq5mnd_n4 I think the thread about sensoric skin >>242 is closely related to this topic, because it will be difficult to build a hand which also has good sensory input. We'll have to come up with some very small GelSight-like sensors. F3 hand (pneumatic) https://youtu.be/JPTnVLJH4SY https://youtu.be/j_8Pvzj-HdQ Festo hand (pneumatic) https://youtu.be/5e0F14IRxVc Thread >>417 is about Prosthetics, especially Open Prosthetics. This can be relevant to some degree. However, the constraints are different. We might have more space in the forearms, but we want marvelous sensors in the hands and have to connect them to the body.

Message too long. Click here to view full text.

73 posts and 18 images omitted.
>>11153 Lel. In Soviet Russia...
Open file (402.63 KB 1152x2048 IMG_20210624_175649.jpg)
>>11029 >Modified T-Pose Okay, but humans don't act like that. If possible I'd like to avoid very awkward behaviors. That said, it could be a fallback position. >>11146 All of us have slightly different goals and priorities. I want something quite human like, so this isn't really for me.
>>11167 Nice. Alita looks great with her long hair Anon. I liked her before, but I like her even better now.
>>8651 Cheap but reasonably powerful (like MG996R that can produce up to 15kg starting torque at 6V) analog servos weight around 55g each. There are 15 servos on that arm (3 for each finger it seems). So servos alone would weight 825g. And that's only for fingers actuation! There supposed to be more moving parts in that part of the arm but as you can see on the vid there's barely any space left and construction itself doesn't look like it was designed for anything more than this one demo. There are smaller and lighter servos. And they cost a lot. I think they can weight something like 15g. That would make 15x15=225(g). Better but super expensive.Imagine paying 750-1500$ just for servos that move only fingers on only one hand. It seems like they are using something like that in their vid because servos are tiny.
>>11482 The mass of servos is exactly why I've been lobbying for relocating them into the 'central core' of the robowaifus, and transmitting force out to the extremities via Bowden cables instead. >tl;dr Reducing thrown-weight in extremities is crucial to both agility/performance, and (much more importantly) reducing energy consumption in our robowaifus.

CNC Machine Thread Robowaifu Technician 05/12/2020 (Tue) 02:13:40 No.2991 [Reply] [Last]
Many of the parts needed to build our robowaifus will need to be custom made and they will need to be metal. For parts that have a high tolerance for imperfections a 3d printer can print a mold and then a small scale foundry can be used to cast the piece with metal (probably copper or aluminum). BUT there will be pieces that need a higher degree of precision (such as joints). For these pieces a CNC machine would be useful. CNC machines can widely range in size, price, and accuracy and I would like to find models suitable for our purposes. I know there are CNC machines available that can cut up to copper for under $300, but I don't know if that will be enough for our purposes. (https://www.sainsmart.com/products/sainsmart-genmitsu-cnc-router-pro-diy-kit?variant=15941458296905&currency=USD&utm_campaign=gs-2018-08-06&utm_source=google&utm_medium=smart_campaign) Some CNC machines can be used to engrave printed circuit boards and that may prove useful for our purposes as well. Are there any anons that know more about CNC machines? Anons looking to buy one ask your questions here.
55 posts and 10 images omitted.
>>11362 >but it's obvious. More x=x logic from "ur a troll" guy I think
>>11374 e.g., the plans for my waifu involve a build comprised solely of plastic printed parts, mainly polycarbonate for structural support. This is fairly easy and inexpensive to build an amateur 3d printer for
>>11375 >comprised solely of plastic printed parts, mainly polycarbonate for structural support It requires a better printer than other materials. It's not lighter than aluminium in relation to strength and parts like gears would wear down over time. Maybe you can do without metal parts or only using standardized metal parts, but it clearly has advantages to be able to use custom made parts. >>11374 You didn't address the problem that plastics are weaker and wearing off, so it was an appropriate answer, and yeah it is obvious that at least using some (custom made) metal parts has advantages. Maybe more so for the higher quality versions. Not necessarily many custom made ones in every case.
Open file (298.52 KB 963x1625 IMG_20210703_201416.jpg)
>>11410 >you may even be able to put some kind of metal plating for mechanical parts that interact That was one of ideas of using some custom made metal parts. Yes. >metals aren't very cost effective There are standardized parts, which are very cheap and companies that mill custom parts have been mentioned as a source in this this thread. >for the average user Some here want to build very cheap robowaifus, others might go for the more expensive version, which might be able to be build as a cheaper version with some drawbacks. >metal 3d printer That's only one option, there's milling, casting and ordering custom parts from companies. Also these printers might get cheaper at some point. >comparative stress-tests for materials CNC Kitchen on YouTube.
>>11417 What happened here? He deleted his posting I replied to?

/robowaifu/ Embassy Thread Chobitsu Board owner 05/08/2020 (Fri) 22:48:24 No.2823 [Reply] [Last]
This is the /robowaifu/ embassy thread. It's a place where Anons from all other communities can congregate and talk with us about their groups & interests, and also network with each other and with us. ITT we're all united together under the common banner of building robowaifus as we so desire. Welcome. Since this is the ambassadorial thread of /robowaifu/, we're curious what other communities who know of us are up to. So w/o doxxing yourselves, if this is your first time posting ITT please tell us about your home communities if you wouldn't mind please Anons. What do you like about them, etc? What brought you to /robowaifu/ today? The point here is to create a connection and find common-ground for outreach with each other's communities. Also, if you have any questions or concerns for us please feel free to share them here as well.
Edited last time by Chobitsu on 05/23/2020 (Sat) 23:13:16.
158 posts and 48 images omitted.
>>11235 i guess its more fair to ask for something equal to what i can pay
>>11242 >>11234 haha I love the ending on that sentence. I think high quality is relative if you checkout my thread, the 4 model is what people prefer >>11242 I think maybe that's what you want but most people lean towards the simpler 2010's chat bot technology. I think as conversational ability degrades we will converge to AGI because people will be simpler than AI's in the current form.
>>11242 I certainly can't claim any expertise on the topic Anon, but as I understand it, the transformer simply uses a statistical probability model constructed during it's training phase to make a weighted prediction of suitable following text regarding input strings. This is why it works from an initial 'seed' &tc. And no, it most definitely isn't 'thinking' in any human sense. I'm personally skeptical that will ever happen, quite frankly. >anons dont want to fall in love with a database... Heh, very well-put Anon. I think we'll get there eventually with suitably satisfying simulacrums, just be patient. >>11243 >Lol, that's not very optimistic Fair enough Anon. :^) My estimate is on what we would roughly call an AGI today, and on second thoughts, I suspect my cost estimates are at least an order of magnitude low. >Within the next 5-7 years we are going to have something decent, I think you are correct Anon. Certainly something well-enough suited for a 'starter robowaifu' if you will. >>11299 >I think as conversational ability degrades we will converge to AGI because people will be simpler than AI's in the current form. LOL. I think just the opposite Anon, though I'm well aware of both the dynamics you're implying. Humans are profoundly capable and multifaceted. By far the most spectacular of all the natural creatures!
Open file (151.04 KB 1024x954 IMG_20210614_100642.jpg)
>>11321 >what we would roughly call an AGI today, >>Within the next 5-7 years we are going to have something decent, >Certainly something well-enough suited for a 'starter robowaifu' if you will. I'm confident that within that timeframe it would be possible to get something close to a human in many if not most cases, within a household. There might be cognitive gaps, where the system fails and can't kearn the right pattern, but I don't see why fixing and polishing this would cost billions or trillions or being impossible. Having that said, best way to find out is not to waste time and get to work. Thinking about this, at least got me back to learning and working on it. Five years will pass way too fast.
>>11361 >Having that said, best way to find out is not to waste time and get to work. THIS!111 :-DDDD

Open file (166.07 KB 1462x1003 rpcs.png)
Robowaifu Power and Control Systems Electronic Chronicler 06/22/2021 (Tue) 21:45:47 No.11018 [Reply]
Hi Anons, making a thread as suggested in >>10947 I've been thinking about this for a long while, and wanted to throw in a draft and see if anyone has comments/criticisms/additions. I present to you the draft of the Robowaifu Power and Control System (RPCS). This draft is by no means complete or definite, but it is a starting point. Let's call it version 0.1a. The version follows major.minor and a letter for bug-fixes. Minor is for feature addition/reduction, major for when we eventually get there XD. From a legal stand point, this is under CC0 or public domain (unless Chobitsu has specific licensing for the content on /robowaifu/). I intend for the draft to develop further and stay open for use by anyone. Summary A full-size robowaifu system needs several things: - Power distribution. Main system bus coming from a Li-ON battery (or other technology). One backup 5V emergency power supply used by slow communications to check appendage integrity, sensors etc. - Main processor. In this post I won't be delving into it in great detail, and mostly treating it as a black box. - Low/medium throughput communication for simple sensor, debug, or status information. Must be robust and must work before any high-level software is working (including the network stack). - High throughput communication for large data-logging, visual processing etc. - "Spine" or communication interconnect. Multiplexes many connections from many sub-systems to the main processor. Includes power distribution connection (allowing individual control to sub-systems). - Sub-systems to actually do the fun stuff! (Arms, legs, nekomimi ears, etc.) Terminology Brain refers to the main processor (and all of its sub-systems treated as a single unit).

Message too long. Click here to view full text.

37 posts and 4 images omitted.
>>11155 I tried once or twice, but he was gone to fast and also my network wasn't very stable, which might have caused it. I installed a client for IRC on my tablet, so I could try again.
>>11164 That's fine no rush. I'll be happy to ask Robi about it myself. He'll need to enable you to make an account, so we'll probably need to arrange a timeframe with you for it.
>>11144 >That's a broad societal topic, and one I'm neither qualified nor enthusiastic about. I absolutely loathe public transportation, having had to actually use it frequently in urban America. It's both dangerous (blacks), and a practical nuisance. Mostly I do agree with you. I generally avoid using it when I can, however in euro it's at least tolerable. In the usa I remember it being kinda shit. >My apologies Anon. LOL I definitely didn't succeed at being concise. :^) Hehe, you ain't the only one ;) >>11150 >Now despite thinking that real autonomous cars are stupid, the STUDY of autonomous navigation is extremely useful. Specifically at a scale that you can install GPS modules and read AR markets (QR codes) to guide a machine along a planetary surface. Haven't considered it on a global scale, but I imagine that would be massively useful to mankind even today. Oh inter-planetary travel, when will you come... >Sometimes I even implement simple logic using discrete AND/OR/NAND/NOR gates and transistors if a microcontroller isn't necessary. I really like that line of thinking. Having cheap-as-dirt MCUs have spoiled engineers and hobbyists alike (myself included sometimes). >>11151 >Our road network is really cramped and badly designed. Very good points. It's too common for techies and marketing to have wishful thinking, while forgetting that infrastructure is a massive cost (that not even a big corpo could really handle).

Message too long. Click here to view full text.

>>11175 One more thing about the brain. Like a PC motherboard has a BIOS speaker, so should we have a minimal amount of hardware periphery for the low-level Brain, perhaps even just skip the whole concept and put all low level control in the Spine, with all the Brain sub-systems being connected via internal network. I imagine at least a speaker, some lights, maybe a status display (or a debug connector for one?) to be available for checking error codes, knowing what stage in the boot process the robowaifu is in.
>>11175 >Thanks m8. Hopefully we can discuss further via email this time. That'll be fine, I'll check in with it sometime soon. >>11164 >>11175 >I'm guessing this for another chap? Oh, heh. My apologies to you both. No, it was intended for you, Elec-Chron. Perhaps the other anon is helping us connect with Robi regarding your account setup? If so, thanks first Anon. >note BTW, I plan to migrate all the posting on our vol account discussion over to the /meta thread so we're not cluttering up your RPCS thread with such things. So, don't be surprised when a few posts disappear ITT.

Open file (154.32 KB 600x400 core3433.png)
New Paradigm of CPU and PCB Architecture meta ronin 06/18/2021 (Fri) 23:47:00 No.10965 [Reply]
Considering where we want to go, a robowaifu with brittle and fragile PCBs, soldering contacts and delicate wires is something which can and should be improved upon. Closed CPU architecture is key as well as the possibility to port the waifu to a new body if necessary. Several supplements and 6 shots of espresso later, I've sketched this (somewhat humorous but also somewhat serious) concept. This is only a processor and not a memory module, but there are a few things I wanted to bring up via this illustration 1. The idea of discarding the PCB model for something suspending in heat dissipating resin, mostly rigid, waterproof and shock resistant, those chips aren't going anywhere, plus it looks black/translucent and cool and we want our waifus aesthetic without clunky square innards. This gives it the mega-man memory crystal aesthetic 2. CPUs dedicated to specific types of processing. Do one job and do it well. a)Since our human brains are split into left-right, logical vs. abstract, I think it would be an advantage to have separate processors to say recall facts and perform calculations vs say, paint a picture or appreciate nature. The "creative" CPU may very well work like Google AI or something of that sort via self seeding feedback-recursion. (therefore our waifus can imagine and dream too). b)mirror neurons and environmental modeling: important for our waifu to understand that we are like her, and not simply another object like a chair or a tree. Gives her the ability to understand how to interact with others and the world via empathy by constantly comparing her own similar experiences with what she sees or experiences. This also requires an internal 3d spacial model of her environment which would be continually updates from sensory input, and like us, fuzzy logic assumption could fill in the gaps where necessary. I figure something like a GPU core array would do the trick here. c) Impetus motivational chip - basically the reward/dopamine system d) Safety or Hazard prevention Chip - would interface directly with the Environmental Simulation chip, any potential hazard or danger to herself or her owner (or even another, if she is the cause) would cause her to freeze or back up a step before assessing further. Would also be useful for necessary danger/pain avoidant reflexes and self preservation. I figure industrial (BUS for example) systems such as in factories or that manage car braking, steering, etc. would already be on the cutting edge of this and we might be able to borrow something from them. Ports would basically be for power and charging a small internal lithium battery and another strictly for I/O Use this thread for any elaboration on this concept, or feedback (or your own ideas if you think you have something better but along the same lines) -M.Ronin
8 posts and 1 image omitted.
>>11075 >Thermal paste is mostly a grease carrier with some powdered solids in it. For AS5 the powder is ground up silver and it is considered very unlikely that the silver particles will ever perfectly line up to cause a short because of the very large amount of grease and tiny amount of solids. admittedly that's tricky, I imagine anything that surrounds the silver will impede its heat conductivity. This will require thinking outside the box, maybe metamaterials of a certain property could solve this one
>>11076 >This will require thinking outside the box, maybe metamaterials Sounds great. I'm sure you can think of something interesting for it. Please keep us updated here on it ITT. My guess is some form of liquid carrier for the heat -- something that is also electrically insulative -- will be the proper course for us in keeping our high-heat (eg, hip actuators, etc.) robowaifu components nice and cooled off.
>>11072 >>11074 >>11075 >>11076 >>11079 Simply crosslinking this post here, since we already have an entire thread dedicated to this topic. (>>11080)
>>11081 thanks! that led me to this as a possible solution https://en.wikipedia.org/wiki/Silicone_oil
>>11075 here we go, I posted in the other crosslinked thread. This is certainly doable. >>11106

Open file (259.83 KB 1024x576 2-9d2706640db78d5f.png)
Single board computers & microcontrollers Robowaifu Technician 09/09/2019 (Mon) 05:06:55 No.16 [Reply] [Last]
Robotic control and data systems can be run by very small and inexpensive computers today. Please post info on SBCs & micro-controllers. en.wikipedia.org/wiki/Single-board_computer https://archive.is/0gKHz beagleboard.org/black https://archive.is/VNnAr >=== -combine 'microcontrollers' into single word
Edited last time by Chobitsu on 06/25/2021 (Fri) 15:57:27.
61 posts and 32 images omitted.
>>8366 It would sure be nice if you taught everyone else here how to do this kind of stuff. Ever consider a /robowaifu/ teaching thread on these topics Anon?
Found out on nano/g about a new Raspberry Foundation's new Arduino microcontroller competitor called Pi Pico. >"$4 Raspberry Pi Pico board features RP2040 dual-core Cortex-M0+ MCU" https://web.archive.org/web/20210121070023/https://www.cnx-software.com/2021/01/21/raspberry-pi-pico-board-features-rp2040-dual-core-cortex-m0-mcu/
Open file (13.43 KB 164x68 fa_logo.png)
Wiki dedicated to Arm-based IoT & embedded. Seems like it's been around for a number of years. https://wiki.friendlyarm.com/wiki/index.php/Main_Page https://github.com/friendlyarm

Report/Delete/Moderation Forms
Delete
Report

no cookies?