[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/vt/ - Virtual Youtubers

Search:


View post   

>> No.75105484 [View]
File: 496 KB, 1401x928, file.png [View same] [iqdb] [saucenao] [google]
75105484

>>75104641
well robot vacuums do but they don't integrate object recognition into it and you'll have to label the map yourself, but yea they'll produce an actual map of your house as they putz around and can then pathfind from point to point using the map, updating it as they go with any changes they detect. google SLAM navigation if you want to read up a bit on it

i'm sure the actual military/industrial robots do have the type of object recognition that tesla and other self driving cars are still trying to figure out but i don't know what the state of the art is there. it's interesting though, if you drop the realtime latency requirements we've seen neuro's vision component do a really good job figuring out what's what, it's (very very theoretically) possible that a robonur could pause every couple steps to assess what she's looking at and construct an actual labeled map she could navigate with

Navigation
View posts[+24][+48][+96]