>>25099 The most common term I'm aware of is 'driver boards' or just 'drivers'. But today (and particularly in the context of building your own robowaifu from scratch) it seems to me that using a general purpose SBC/MC is the more reasonable approach. They're commonplace, cheap, flexible, and you're never going to have enough GPIOs 'laying around', right Anon? Good luck with your project research Anon. Good to hear from you again! Cheers. :^) >=== -minor edit

>>25098 You're absolutely right I expect, Greentext. I wish I had such a working relationship going myself.

>>25105 SBCs aren't really a replacement for motor driver boards. These boards are way cheaper or more expensive, but also maybe an add on to the SBC. Just look into some YouTube video. First you need to know what kind of motor it is (DC, BLDC (or the sub variant of stepper), then look for the right control boards, and first the explainer on some website or Youtube videos. We have a better thread for this, though: >>12810

>>25105 I've seen drivers before and they are generally h bridges with speed control which is far from servo functionality i need. I guess i could slap potenciometer or optical enkoder connected to analog input but i would quickly run out of those. Are input expansion modules a common thing?

>>25113 Ok, found meself some multiplexes and encoder. Gotta run the math if using them insted makes financial sense.

>>25111 Yep you're right NoidoDev. I even knew that but for some reason wasn't thinking clearly when I posted. >>25113 The other anon above is right. GPIO pins aren't meant to run a lot of power through them, merely signal-level current. As he pointed out 'motor driver board' is the correct keyword phrase. There are a variety of use-cases, which (I presume) your wiper motors will be straightforward brushed DC motors. Here's an example source link: https://www.pololu.com/category/11/brushed-dc-motor-drivers As to all the other ancillary needs, there are many possible ways to approach it. I prefer the Beaglebone Blue generally for prototyping, since robotics was the particular design goal behind that board's creation. For example with facial animation systems, very likely just two BBB's could directly run all the low-power servos needed for very sophisticated motions (say 15-20 smol servos), and could also accomodate the external encoders/sensors needed. And on top of that, they are general-purpose computers that can run Linux, support cameras, sound, networking, storage, etc. OTOH, its improbable they could run something as big as a hefty wiper motor all alone. But they could still be used to send the PWM signals needed, out to the drivers to run your wiper motors (though there are much cheaper alternatives to that for production designs). BTW, do you have a more 'personal' handle we can all refer to you by here, Anon? Cheers. :^) >=== -prose edit -add hotlink

>>25098 I don't know why the sd card with raspbi os burnt won't work. It makes no sense. But again I bought one that comes preinstalled with it and again if it doesn't work I'll return it and burn the raspberry pi zero w.

>>25142 I'm not too familiar with the Raspberry Pi platform, but shouldn't it be possible to just install the OS onto a blank SD card like a normal computer? Alternately, couldn't you download the OEM image and write it to an SD card with dd?

>>25142 >>25146 >couldn't you download the OEM image and write it to an SD card with dd? Yes, and I detailed the process here a while back. (>>5165).

>>25142 Aren't you the guy who tried to build a hasel actuator? You will be able to figure this out. Just don't us dd to overwrite your computer disk or so. Have backups or maybe use another program.

>>25111 I don't mean to be disrespectful anon. What i came for is not asking about motor but about additional boards that would come between said motor and microcontroler. Substantiate your claim that it should be in general actuator thread. >>25135 I'm useing PCA9685 for i did not intend to run power through Arduino anyway. End goal jhumanoid robot would use no less than 32 individual motors and goal of current endeavour is to build sufficient infrastructure to move joints w/o any added load and considering signal loss and power projection if boards and circutry should be centralized or disributed. Using servos or servo board modified wipers allows for much simpler command structure: arduino->PCA->servo as i do not need any additional feedback. while if i had to use feedback it would something look like: encoder->input_multiplex->arduino->PCA->motor driver->motor which adds lot of complexity and cable creep for no other benefit other than system could internaly monitor joint positions instead of ordering servos and leting them to do their work on their own. >do you have a more 'personal' handle we can all refer to you by here, Anon? I'm not big on using trips be it on thai crab wrestling or robo building imageboard but i may change it to "Podolek" if (You) prefer it.

>>25151 I don't want to sound like a schizo but I think I'm being targeted by hackers. It wouldn't be the first time. But I'm pretty persistent. I'm going to try to do it in a vm. I don't think they can hack their way into that.

>>25170 >PCA9685 >arduino->PCA->servo Yes that sounds like a great solution Anon. >thai crab wrestling or robo building imageboard Lol. Podolek sounds like a good handle, but we can just call you 'Anon', Anon and it seems like you'd prefer that. Good luck. Please keep /robowaifu/ abreast of your progress! Cheers.

>>25171 Heh, I doubt you're a bigger schizo sh*teposter than yours truly, Pete. I'd at least encourage you to stay grounded in some kind of objective reality though (for example, there's a ginormous weight of evidence now for the Globohomo and their machinations at the state & corporate level). >I'm going to try to do it in a vm. I'd recommend that as a first exploratory step for beginners Anon. Just ask for help and I'm sure some anons can at least point you in the general direction of the answers. Cheers.

>>25173 there is nothing to ask. Raspberry pi os writer is supposed to be straightforward and fool proof. Anyways other than that I used wireshark and just syn ddos attacked all that crap idc. I'm assuming the hacker prob ran out of vpns now.

>>25170 We don't use SBCs just for motor control, these are small general purpose computers. But your question is closer related to actuators. We very likely discussed these things in the actuator thread, where I would post it, so I would also look there for such info. This might also help: >Embedded Programming Group Learning Thread 001 >>367 >>25171 Make sure to write your most important data on an M-Disk. A SD card failing is not an indicator for being under attack, though.

>>25176 Fine, as you wish. Hope it's not as dead as it's been last few days.

>>25178 >Hope it's not as dead as it's been last few days. Be the future you want to see :^)

>>25099 >Cannibalize cheap servos for wiper motor servo Not worth it. Those boards are cheap chinese junk with terrible pots. Using a real microcontroller would be far batter. Assuming you are a beginner, starting with an Arduino and an easy tutorial will help you build the skills you want. https://www.instructables.com/Wiper-Motor-and-Arduino-Mega-Servo/

I got the raspberry pi zero w cause I thought it'd make things smoother. I have spent like a month altogether on that junk... My last video was like a month ago lol. I got it to run but it says no carrier for the wifi. I did not have any issues with the orange pi ironically but its gpio pin support sucks so I'm going to have to find a way to combine it with the esp and that's it. I don't know what I'm going to do with that raspberry pi I might throw it it in the trash I don't want to look at it anymore.

>>25207 You do know that Raspi has it's own forum with troubleshooting? https://forums.raspberrypi.com/viewtopic.php?t=313806

>>25188 >Those boards are cheap chinese junk with terrible pots. Alrightyou convinced me. Last thing i wanna do is troubleshhoot & run wires on those tiny boards.

I ran across something really interesting. I think. Apparently server centers are selling their used "Nvidia Tesla K40 12GB GDDR5 Graphics Card GPU Accelerator Card w/ Low Bracket". Look up the above in ebay. They're like $32 USD. The power of these things is immense and blows the living hell out of any sort of single board computer. Of course the trick with them is, 1. Programming a huge parallel processor will be difficult. 2. They don't have fans because data centers have a mass of cool air blowing through them. You will need one or a better solution some sort of pumped cooling.(there is apparently some solutions to this but I don't know exactly what that is yet) Some solutions to the programming are they have a library called CUDA. I see this is used in open source video upscale software. They use these for machine learning, engineering and...not sure what else. Maybe they also use them for general computing "if" they can code this mass of parallel processors. Other problems are you will have to have specific motherboards and you will have to get a monster beast power supply somewhere around 800W. Specifications 2880 CUDA GPU cores (GK110b) 4.2 TFLOPS single; 1.4 TFLOPS double-precision 12GB GDDR5 memory Memory bandwidth up to 288 GB/s PCI-E x16 Gen3 interface to system GPU Boost increased clock speeds Supports Dynamic Parallelism and HyperQ features Active and Passive heatsinks available for installation in workstations and specially-designed GPU servers The new GPU also leverages PCI-E 3.0 to achieve 4.2 TFLOPS!! Damn they are fast. And this sort of processing is exactly what you need for a waifu to process speech, movement and visual navigation and personal visual recognition. A ESP32 micro-controller has 600MIPS it would take 7,000 of them to equal this one card in power, roughly. At $8 a piece it would take $56,000 to equal it. I wonder if this is some one time deal where they dump a bunch on the market and no one yet has really found a way to use them. This is changing fast because people have already figured a way to run games with them. While not optimal for this the price of graphics cards being so high I bet soon the prices will go way up. I'm thinking about buying one of these even if I don't ever do anything with it. The power if I could ever figure a way use it would make it a steal. They could be used to train. I'm guessing most of us will use mostly pretrained open source models then add extra training for what we want. These would be slow compared to these huge data centers but if you let it run for a few weeks it could do the same and you don't have your data sent to some data center.

>>25396 I mentioned the K80 and the M40 before, it requires additional tinkering with the cooling to make it work. If you have barely any money then maybe the K40 is worth trying, otherwise it's better to use the K80 which has internally 2 GPUs each with 12GB. This said, these old GPUs also aren't well supported, so you might need to compile more basic programs like CUDA and some models might not work. The M40 is better in that regard, and it has 24GB. These are also not SBCs but for the use in a home server to which your waifu can connect. OT: They don't make much sense for gaming, since they need to much energy for what they do, might require overclocking and even more cooling, and the GPU prices came down. If I wanted to run the biggest Falcon model at home, then I would consider using the M40 (28 of them, ~1KW / 40-80€ per month energy costs, price for all seven servers: ~3-5K )

Yes it's obvious it''s not a single board computer but it fits here better than elsewhere and fits the basic idea of what SBC here are used for. I bought 2-K20's for under $30 plus shipping here, https://www.ebay.com/itm/314144513426 I may not ever do a single thing with them but...$30 for that kind of power...You never know. Some things they dump on the market surplus and they are super cheap then disappear. Some don't. If you look at the same seller, and others, they have HP 1200watt power supplies for $30 or less. There are break out boards where you can plug a card in to the PS for around $18. Some have cables, some not. People are using these for mining. I have an old computer I do nothing with. It has a slot that I think will take it. Get a PS and this older computer could be used to train. Maybe. The K20 is 60% of the K40. And no I'm not buying a K80 they're $160. This is just a whim. I'm not dogged serious about it but for $30 maybe I can piece something together if it comes up. Some K20 cards have passive cooling. I have no idea if the ones I bought do or not. I did see them online though. But I expect a fan would be good. They are designed for servers with good air flow. >=== -rm URI fingerprinting

>>25437 Okay, but make sure you know how to do take care of the cooling.

>>25396 >4.2 TFLOPS!! Nice. You'll need active cooling. Here's Nvidia's CUDA page. It's basically an extension of C programming (cf. >>20980) . https://developer.nvidia.com/cuda-toolkit >=== -add crosslink

As already mentioned in the meta-thread: The P40 (server GPU) also exists with 24GB. I didn't know. It's better than the M40. https://technical.city/en/video/Tesla-M40-24-GB-vs-Tesla-P40 - They need extra work with adding coolers or a cooler in a PCI slot.

This thread here becomes more and more a thread about GPUs. Maybe we should make one for that., or simply for AI related hardware topics in PCs and home servers. Right now these topics are spread over many threads, since in the past we didn't use this thread here for it. Anyways, I'm I the only one with a AMD APU in a PC? It seem not have been interesting for anyone that we can now run neural networks on such an APU. https://www.tomshardware.com/news/dollar95-amd-cpu-becomes-16gb-gpu-to-run-ai-software https://youtu.be/H9oaNZNJdrw https://youtu.be/HPO7fu7Vyw4 I didn't test it yet, but try to keep it in mind when I reboot. I need to change some Bios settings.

>>25759 I have a 5700G and it is honestly terrible for AI compared to a GPU. Yes, I can feed it heaps of RAM. It is too slow for it to matter though. My RTX 3060 undervolted and underclocked to 65 watts generates a Stable Diffusion image at 1024x768 with several LoRA's in 27 seconds. Considering a RTX 3060 can be had for 200 USD equivalent or even less if you're careful, it is hard to see the point

>>25769 One point is, that there are mini-PCs with APUs, which would fit into a robowaifu. That aside I'm more interested in trying it for some LLM. It could at least hold 16GB and some claim 64GB, but also if this works then sometimes only a few GB are missing in a PC/homeserver to run a model could come from the APU.

>>25770 LLM's do make sense for these systems. In which case, using LLaMAC++ (https://github.com/ggerganov/llama.cpp) is ideal. Those Zen cores are also very powerful and utilizing them with the iGPU can lead to good results. This hybrid approach is still being improved but, has great potential. I'm looking forward to further refinement in ROCm drivers. AMD has been making strides that have improved their performance in AI over the last year which should continue to benefit APU based systems.

Old chromebooks as alternative to SBCs: https://www.youtu.be/1qfSJxcgH5I (sometimes $99 for 10 of them, ofter cheaper). Of course, don't use an outdated version of Linux Mint like he might be in the video.

>>19428 More interesting development based around the RK3588's NPU. Useful Sensors have created a good library for using Transformer models on the NPU efficiently, called Useful Transformers. https://github.com/usefulsensors/useful-transformers Link to useful sensors https://usefulsensors.com/ Video demo of voice recognition and offline LLM response. https://youtu.be/K6qgN_QXH6M

>>26099 Hey that's probably a good idea, NoidoDev. >>26254 >Transformer models on the NPU efficiently Interesting.

There's progress in connecting (old) AMD GPUs to Raspis. This might become useful to run small models in mobile systems, I guess. https://youtu.be/BLg-1w2QayU - Work in progress, there are still issues.

>>26613 >There's progress in connecting (old) AMD GPUs to Raspis. Very cool. Lack of GPU dev for that Broadcom chipset has always been a shortcoming of the Pi. Maybe this will eventually turn into something important for this field. Appreciated, NoidoDev.

I've been thinking lately, Assuming that you're trying to build a full size humanoid body. Would it be better to have these single boards placed all over the body parts? Instead of having one powerful centralized board to micromanaged everything, your robowaifu will be a supercomputer, decentralized with many single boards throughout the humanoid body, Maybe this could solves the heat issue that generates from cpu? I'm not sure about the latency performance from this design though, I think there will be a hub somewhere that connects every single boards into one central board.

>>27359 There might be some merits to a system like you're describing, but there are some complicating factors. Firstly, each and every board will have to be powered one way or another. How they're powered will greatly affect the logistics of the setup. If they're powered by USB, then you have to either ensure that the central board can supply power to each peripheral board, or install a powered hub if that's not possible. Some might be powered by basic power outputs that exist on the central SBC. If so, you'll need to wire each one properly and ensure that the central board can even power everything. If not, you'll need a power supply. Similar problems exist with other powering schemes. You're adding a whole lot of cables that'll have to be managed. Depending on how the internal workings of the waifu are planned (and there are varying schools of thought here), this could get messy pretty quickly. You could opt for using PoE boards, ensuring that you only need one cable per board, but this is more expensive. You'll also need to install a PoE switch, which needs a whole bunch of power and may run hot if it's not cooled properly. Speaking of power, each board will likely have redundant components that will consume power without doing much. I doubt such a setup would consume less power than just having one board managing everything all the time (not even accounting for seperate power supply schemes). If you're planning on having a battery-powered waifu, this is a huge tradeoff to make. Every watt counts. If you're planning on having a tethered waifu (like me), then your main focus will be on placing as many components outside of the waifu as possible. It's better to have a beefier computer managing everything while it sits in its designated corner. If heat is your main concern, the motor controllers and power supply should be your main concerns anyway. All of that will put out far more heat than a laptop board when under significant load. Just think about how many motors you'll need for a waifu to work. Pretty much everyone here is cutting back on articulation in some way or another using various methods, but almost all of us still end up with relatively high figures because we want the most posability out of our waifus as we can manage. Seriously, think about it. Imagine any one physical activity you'd want to do with your waifu. Hugging? That'll need at least four points of articulation. A good hug? Triple that. Handholding? Add another five. Per hand. Don't forget the sensors, either. Even with a demultiplexer, you're looking at some hefty motor requirements unless you want your waifu to only be able to move one point of articulation at a time. Swapping out a single baked potato for a tray of fries won't change the fact that they're sitting in an oven.

>>27359 Yes there are a number of design tradeoffs for a distributed, onboard compute network for our robowaifus. I certainly increases the complexity from a systems-engineering perspective, but perhaps in some contexts the benefits are worth the pain! :D Good thinking, Anon. Thanks for sharing it. Cheers. :^) >>27360 Good, straightforward analysis Anon. >Swapping out a single baked potato for a tray of fries won't change the fact that they're sitting in an oven. Lel'd. :^) >=== -add'l reply -sp edit

>>27360 I like the idea of having all the internal electronic parts including the board fully submerged with water. I guess you might have seen a desktop pc motherboard running in dekstop casing that were filled with water. I forgot how the theory works. I think it has to do with electrolite like how an old car battery would run. Perhaps this technique could help cool down your robowaifu.

>>27359 Think about it slightly different. You want the heat to have a warm body. You have to either distribute electricity or the heat. Distributing the latter might only be possible through liquid, especially since it would have to go for a longer distance. I think it's probably easier to make a coupler in the joints for electricity than for liquid. >>27378 I think they're rather using some plant oil or some oil derivative. I don't think it's such a good idea. We won't need it and it would add difficulties. I think this is mainly useful for overclocking.

>Explore the groundbreaking Coral AI mini PCIe accelerator by Google, a game-changer for home automation and DIY projects, in my latest video where I integrate this innovative chip with the ZimaBoard and Zima Blade for superior performance and cost-effectiveness. Discover how this setup outperforms others, like the Raspberry Pi 5, in speed and thermal efficiency, and follow my journey from troubleshooting software issues to successfully running Frigate, an advanced home lab computer vision system. Learn how this affordable, under $100 setup can revolutionize your home tech projects! https://youtu.be/mdOEaNV8NXw

>>27359 It is most efficient to keep everything as centralized as possible. Remember, it is trivial to route power and data throughout a body. >Heat issue If this is a problem, your design has failed, make something better. I've designed and implemented several systems and heat has never been a problem because, I don't allow it to be. >>27360 >Power logistics This is an important factor. Minimize the range of voltages needed, ideally everything requires voltage within the standard discharge curve of your battery. Always strive to reach this ideal state. >USB Not recommended for internal components unless there is a need. For instance, an internal USB can be used for adding special components like SDR, GPS, Video Capture, and other special need components which don't make sense for a base model. >PoE Expensive, makes sense for charging her while transferring data. Great idea for an external connection. Internally, there's no reason not to just use wires. I trust you already knew all of this, just wanted to add clarity for other Anons. >>27378 >Submersion cooling Mineral oil is better for this. Still used for high performance computers. You need to actively filter the oil and replace it yearly. It is completely unnecessary and only ever makes sense as an aesthetic choice. >>27474 >Heating her skin Connecting her heat sinks to her skin is a great idea. Huge surface area to dissipate heat while making her feel more alive. >>27478 Looking forward to stronger accelerators. These are good to offload object recognition and/or word recognition for low compute platforms. Could be useful to slap into an old Thinkpad to give her eyes and ears.

>>27525 All very good points, and that's kinda what I was getting at in regards to his idea of putting small boards everywhere. Not all of them are designed to get their power the same way. I could have made that a bit more clear, though. Since mai waifu's going to be a tethered TENV system, I'm always thinking about how to make that specific kind of waifu work. However, I still maintain that the number-crunching is best kept remote, even (or especially) for a battery powered system. Modern day WiFi is fantastic, so I don't see much reason to have a larger computer using up space and power in your V1 waifu unless you actually plan on having her be especially mobile from the get-go. Just stick a desktop in the corner and let it chug away.

>>27526 >pic >tfw i have the original of that somewhere...

>>27525 >Mineral oil She will be able to piss and drink a fresh mineral oil as a part of its self routine maintenance cycle ^_^. Just wondering though, is there a reason to choose mineral oil instead of any other type of non conductive chemical substance?

>>27552 I don't see why you couldn't go with something else that's both electrically insulative and thermally conductive, but you'll have to be careful that whatever you use doesn't cause rot, corrosion, dissolution, or leave any film or substrate behind on the surfaces it's interacting with. At least, not enough to make any difference over a decade or so. One of these is bound to happen eventually when you have a liquid mechanically interacting with a surface. Also, be sure to watch out for your own health. Don't get anything toxic, even if you think she'll be well sealed (leaks happen...). All that being said, flushing might not even be necessary (at least, not on a regular basis) if you seal everything properly. The reason mineral oil coolers need to refilled is because the oil evaporates over time. Those systems are rarely completely sealed because they're only designed to operate upright. If your waifu is only ever going to be standing or sitting, then this is probably fine, but if you want her to operate in any orientation, then she'll need her cooling system to be perfectly sealed.

>>27555 You can add should use a water cooling line if you want liquid cooling. Mineral oil is simply ideal for immersion liquid cooling. They are entirely different concepts which should be considered as having nothing in common. Aside from a liquid carrying heat. If you'd like her to drink and pee, a soft line water cooling system is recommended. If you'll drink her pee, please incorporate a filter near her urethra.

Your waifu will be on the cloud or locahost and you will be happy