Every large social network has fairly advanced mass screening setups for advertiser-sensitive topics. They just need to change the configs. On YouTube for example they will transcribe audio and run OCR on text to flag sensitive topics using MLP in order to flag certain topics (ex: Palestine/Israel), and prevent most ads from being shown (and demonetize and down rank).
Basically every large advertiser requires this so it's pretty trivial to turn on.
As far as I can tell cheapish 2D lidar for mapping and robot navigation were a bit earlier than the XV-11; they were made by Hokuyo in 2006. I remember that their lidar module was made by some other (American?) company that in turn competed with Hokuyo, people would take them out and use for their own projects.
It's ultimately not very complicated - it's a laser rangefinder that you spin on a motor. It's such a simple - and old! - technology which would obviously get significantly cheaper with time, it was definitely the right horse to bet on. I never understood iRobot's vision strategy.
I think the XV-11 was the first affordable (as in, affordable enough to be part of the COGS and reliable enough to be in a product) for consumers. It helped how there was a cult like following (understandably so) and everything got reversed engineered from schematic to firmware. By principle, a lidar is simple but most things are. The hard part is how to make a product out of it. One of the main things Chinese suppliers improved on 2D LiDAR is having the laser portion completely wireless. Induction powered, and LED light pipe for data communication. This removes the need for the slip ring which wears out and is hard to package.
There is not much tech to steal here. 2D lidar mapping is something a high schooler could do 10+ years ago, and that was their core tech. The value was in executing earlier and better, and applying existing tech to robovacuums. If they could have sued they likely would, this is a valuable market.
There is not that much more to it than lidar and 2D slam as far as the core technology. There are a lot more features yes but they are not nearly as valuable. I agree they are better, but that's for reason of execution and non-enshitiffication, not core tech.
Unintentional I’m sure, but that’s a goalpost shift.
What made cloudless Neato amazing was how many real-life edge cases it handled well. That’s where the innovation was.
It’s the integration of the vacuum and sensors along with great software that allowed it to handle furniture shifts and creeping up to stairs without being confused.
I think of it this way: Tesla’s core tech were batteries and electric motors. Nothing groundbreaking. But integrating the core tech as a vehicle took real effort and trial-and-error; then more, in order to make a manufacturing pipeline.
Sorry if I sound bitter. I fell in love with the product on my first purchase and was mortified when the market utterly failed to reward them for the innovation.
iRobot's failure is that they made a bet to use CV instead of Lidar for their mapping robots for a long time until it was too late. That made their affordable, non-mapping robots far far worse than only slightly higher priced lidar robots, while their mapping robots were too expensive for mass appeal and were still worse at navigation than up-market lidar based robots. Ultimately they were simply outcompeted.
Neato, which had a robot vacuum with LIDAR, shut down in 2023. That's not the key problem.
Binocular vision ought to be good enough for a vacuum. It's short range compared to the inter-camera distance. Vehicle object ranging at distance is much tougher and can be fooled.
> Binocular vision ought to be good enough for a vacuum.
It could be, but it just is not. VSLAM robots were practically significant worse. There are a lot of limitations to multi-ocular vision for a robot vacuum, for example the relatively featureless walls and few features across the horizontal binocular axis.
Neato was never as big as iRobot. They didn't fail from commanding heights, they never were that successful to begin with, for entirely different reasons. If they had managed to get to iRobot's level of ubiquity and distribution they would have had a much better shot of still being around nowadays.
Right. The cheap solution to that is projecting a pattern of IR dots on the walls to give them some features. One version of Microsoft's Kinect did that.
Why do you need to handle DDR5? You can use DDR3 to play the vast majority of competitive video games. It's not hard to find an FPGA that can handle DDR3 or DDR4.
You also don't need to sniff the entirety of the traffic. You just need to introduce aliasing. That is much harder to do for DDR5 but you don't need it to be reliable or stable for a long time, because you won't be sniffing for very long. And you don't need to do 6000+MT/s either.
As far as I know there are very few systems that support Windows 11 with DDR3.
I think his point was more that if you drop the link rate on ddr5 to sniff then the performance penalty will be very bad. DDR5 starts at 3000
There are DDR4 interposers you can buy for 50$. The basic thing is that you don't need all of the ram all of the time, you just need to find an address which you can then rewrite to make two valid references to the same physical memory (see: badRAM/battering ram). Then you can use an IOMMU compliant DMA to access that memory.
Or you can use an FPGA to interpose the RAM and intercept the network traffic for a couple hundred bucks.
Indeed, you can buy a piece of fiberglass shaped correctly for 50$. That's not the hard part. Just the probe you are supposed to connect to such a PCB is > 1k USD per pin you need to sample. The oscilloscope / logic analyzer to sample it is likely 6-7 figures.
> Or you can use an FPGA to interpose the RAM and intercept the network traffic for a couple hundred bucks.
What FPGA solution do you have for a couple hundred bucks could interpose DDR4 RAM at any frequency? This number seems completely made up to me.
I do think a large portion of the huge price for this equipment is that it is very niche and only a few mfg's eg keysight/agilent make this kind of stuff.
Im sure if the DMA market goes way of the RAM bus sniffing its will be a year or two before mass produced products are on the market that can sniff the traffic without much reduction in signal quality and maximum data rate.
reply