Search results

Well, there's a lot of possibilities and nobody has made a real industry standard way that everyone follows. Like anything else there's a spectrum of possibilities from low-end to ultra-futuristic-cool. On the low end you have a perception system that uses SLAM to map out what is immediately...

Re: the above truck picture, we've all been there in the northern states. Not like Kentucky. There's a textbook approach autonomy uses called Simultaneous Localization and Mapping (SLAM), where perception data is compared with previously generated models and live data to perform both...

landfill automation would be goofy. I don't know anything about landfills, but I imagine you'd have to carefully model deformable terrain while driving on it. No idea how much a landfill operator intuitively understands that by knowing generally what's in the garbage he's driving over.

On and re: GPS, with current tech you can expect that 3 meter bubble, but that can be heavily reduced with different methods of what's called differential GPS correction. Most error is atmospheric, so if you know what the current error is in a given location you can offset based on that...

Yes. Certain types of Ground Penetrating Radar can find ground beneath snow. MIT Lincoln Laboratory: News: Lincoln Laboratory demonstrates highly accurate vehicle localization under adverse weather conditions Ground Penetrating Radar Equipment for Ice and Snow Surveys - GSSI Ice and Snow -...

Yes, you'd absolutely need a fairly accurate world model generated from pre-snow data. That's what Ford is doing to do accurate localization (figuring out where the vehicle is) after heavy snowfall when there are no lane markings. Once you have that, you've got a optimization problem of trying...

Yeah it's much harder than that. Everytime you plow it'll require a different solution and you'll need a very smart system that can handle it an uncontrolled environment with a lot of precision.

Autonomous snow plows is a really, really hard problem. A good plow driver moves snow with a 3 ton truck with surgical precision, and can only do so because he's plowed that area many times and knows where all the curbs, bumps and gaps are buried beneath the snow. They have to operate with an...

@jihodj remind me new years day in 2019 about this bet

No idea how correct the above is, I'm sure those elements of AI are used at different levels, but I expect the truth is much more complex and less elegant than what they publish (and that's ok). I'm fine with extending it to Dec 31, 2018. Let me know what you want the duration of the avatar to...

The four spinny things on top are Velodyne HDL32 lidar, about $32k each (Ford gets an unknown discount I'm sure). Ford is working hand in hand with Velodyne to develop the next gen lidar. The course they are on is Univ Michigan's MCity autonomous testing course. I toured it when it opened and...

Ford is working on winter driving. Part of the problem is that the people speaking about vehicular autonomy are selling a product/brand, or are researchers trying to get grant money. All the automotive companies are in the dust compared to Google, and they're all trying to step up their game...

I don't think Tesla will make that because: 1. They haven't demonstrated much yet. 2. They're generally late (and that's ok). I'm excited to see what they put out though. Let's do an avatar bet that Tesla doesn't have a level 5 autonomous car in the hands of consumers by Q1 2018. Note that...

What's funny is the evening after I made this post I was approaching a red light during a sunset. As it turned green the car traveling perpendicularly to me and toward the sun screeched to halt in the middle of the intersection. He backed up and gave me a sheepish look as I safely turned on his...

In five years youll probably see freightliner, peterbilt and some others with very limited releases of freeway driving trucks being tested.