/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.


Max message length: 6144

Drag files to upload or
click here to select them

Maximum 5 files / Maximum size: 20.00 MB


(used to delete files and postings)

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

Self-driving cars AI + hardware Robowaifu Technician 09/11/2019 (Wed) 07:13:28 No.112
Obviously the AI and hardware needed to run an autonomous gynoid robot is going to be much more complicated than that required to drive an autonomous car, but there are at least some similarities, and the cars are very nearly here now. There are also several similarities between the automobile design, production and sales industries and what I envision will be their counterparts in the 'Companion Robot' industries. Practically every single advance in self-driving cars will eventually have important ramifications for the development and production of Robowaifus.

ITT: post ideas and news about self-driving cars and the hardware and software that makes them possible. Also discuss the technical, regulatory, and social challenges ahead for them. Please keep in mind this is the /robowaifu/ board, and if you have any insights about how you think these topics may crossover and apply here would also be welcome.

https: // www.nvidia.com/object/drive-px.html
How about it be about all autonomous vehicles, not just cars. Trucks, trains, boats, planes things like that. The AI and other parts behind all these probably have many similarities.
I think as long as the frequency of these types of fatal accidents remains low, then the lugenpress won't feel they can drum up much public outcry against AI car manufacturers. This report is 500 pages long.


I imagine the same lugenpress will have a field day when the first robowaifu-attributable owner death occurs.
Open file (771.09 KB 2560x1668 0705055926982_21_Stanley.jpg)
This is the software behind Stanford's car that won the first DARPA Grand Challenge.

there is also a different robot car they worked on for the later DARPA Urban Challenge also uses this code.


BTW, this code relies on the Robotics Operating System
Apparently electric cars can be recharged wirelessly while they are moving down the road.


Can this idea be translated to your home (or out in public even) environment /robowaifu/? And will your waifu ever even run out of juice if we can?
Tired of the Western POZfest in autodriving cars? Why not support the iron fist of Eastern Communism instead?

Baidu (the state-run chink version of Jewgle) is working on this stuff too.
Now the Swedes are trying to get in on this.
GM and Cruise announce first mass-production self-driving car

When can I just have my robowaifu chauffeur me around?
While not exactly self-driving topic, the battery part must be important here.
>Waymo now testing its self-driving cars on public roads with no one at the wheel

The robot revolution is coming lads.
Open file (9.58 KB 480x360 0.jpg)
simple and cheap avionics and control systems you say?

Open file (18.69 KB 480x360 0(1).jpg)
Check my dubs :^)
Now if we can only get it to play the Ride of the Valkyries

From the No Starch imprint. Details reverse-engineering automotive embedded electronics, ostensibly to improve them. White/Gray hat stuff. This certainly has import for developers of robowaifus, whose CnC is actually much more complicated in the end.

Open file (1.12 MB 2000x1500 NVIDIA Orin press.jpg)
Pretty remarkable new SoC from (((Nvidia))) for autonomous vehicles (cars & robots). 17B transistors. nvidianews.nvidia.com/news/nvidia-introduces-drive-agx-orin-advanced-software-defined-platform-for-autonomous-machines?nvid=nv-int-cwmfg-30041#cid=gtcev_nv-int-cwmfg_en-us
<"...we arrive at a combined torque rating at the shaft of around 1,000 lb-ft, or 1,356 Newton-meters." >ywn a robowaifu monster super truck I just want my RoboHummerEVWaifu! Is that too much to ask? https://www.motor1.com/news/450217/gmc-hummer-ev-torque/
Wow what a huge difference they've made at Tesla since this thread was first made back in the day on 8ch. Has anyone else seen the demonstrations of the vector-space renderings of the FSD neural nets on the Tesla. I was skeptical, but they really are beginning to emulate human ability for the perceive/respond cycle, and according to them at about 30Hz.
Open file (1.15 MB 930x1478 1619378083486.png)
I'll admit that I don't really know shit about self-driving cars or AI, but I keep thinking about this, so I might as well dump it here. It occurred to me that the safest way to drive (not the most efficient or most convenient) would be to assume that everything around the car is completely stationary. In other words, if it were driving 80 mph on a highway, and there's a car visible in front of it, assume the car is going to instantly stop as if it hit a wall and comfortably decelerate to prevent hitting it long before that becomes a risk. The closer it is to something that it's driving towards, the slower it has to get, but driving away from something, it can accelerate as fast as the driver is comfortable with, until it starts approaching something else. If it were parking then getting just shy of touching a wall would be ideal, but while driving it's best to at least keep enough distance to drive around the car in front of it. Perpendicular movement is tricky, since cars can easily pass each other in opposite lanes inches from each other without accidents being common, but just the same if it were driving alongside a wall and something walked out from a doorway in that wall, it could be immediately in front of the car without warning, so the safest behavior is simply to drive slower, so driving perpendicular to something is no different than driving towards it, especially when on a winding road where you never know what's around the corner. Obstacle avoidance could be based on the whatever direction it can safely move in the fastest. I think you could even apply the same logic to flying and higher speeds at higher altitudes, although with regular cars you'd need to slow or steer as it approaches potholes or ditches on the side of the road. Or maybe I'm just a retard with Dunning–Kruger effect and driving safely is really a lot more complicated than that. Regardless, I'd love to see a simple simulation with a bunch of cars driving around following that simple logic, even with perfect omnidirectional vision not being realistic, I think the real-world hardware would amount to cameras on the bumpers and sides of the car, and the closer it gets to anything, the lowest value determines the max speed the car can go. There'd need to be a lot more added before it'd anything more than a glorified always-on parking assist. Though I this kind of driving behavior would only really be safe if every other car on the road drove the same way, since humans are reckless and impatient assholes, but flashing your blinkers a lower speeds could be enough to help occasionally.
>>13176 Lol, that would be worse than my Grandma's driving honestly. Such hyper-timidity would create countless automobile accidents and be directly responsible for a massive rise in roadway deaths. Society on the highways simply wouldn't function with widespread adoption of such behavior IMO. Tesla actually deals with exactly the kind of concerns you brought up Anon (and many others as well). Maybe you give their Tesla AI Day video a go?
>>13204 The movement speed perpendicular to objects probably needs tuning due to things like tunnels and guard rails, but otherwise I think it could work great. That hyper-timid driving style might seem excessive, but you've got to consider that the biggest concern people seem to have with autonomous cars is the safety. And if it's really an issue I guess it could still be made to still decelerate safely but not necessarily comfortablely, so the gap between cars can be smaller. There are some places and times where you can go straight on a highway for hours without ever seeing another car and there there's rush hour in New York where bumper to bumper traffic keeps anyone from moving. In the case of the former, the timidness isn't really a significant negative and would mostly just stop it from hitting a deer or anything else that wanders onto the road, hence my analogy of something popping out from a wall. But it would actually help alleviate traffic jams since the reaction time to the change in the speeds of the cars around it could be really high, and if a significant number of cars followed this method, then there'd be a large group of cars all slowly creeping while leaving enough room to pass and merge lanes instead of idling and random accelerating/decelerating and people trying to figure out how to merge. Traffic would be slow, but it would stay moving efficiently. I think this video really does a good job at showing the problem it'd solve: https://www.youtube.com/watch?v=iHzzSao6ypE and at the chicken crossing the road part at 1:08, if you think of it as there being no road, just cars going in a straight line, the cars would slow as the chicken approaches to cross them, and start speeding up again as the chicken leaves, I think it could solve the problem without the cars needing to communicate with each other or eliminating human drivers entirely. The consistent driving behavior would keep the cars "in the middle" without needing to consider cars behind them.

Report/Delete/Moderation Forms

no cookies?