MIT Is Improving Object Recognition For Robots 9
jan_jes writes: MIT have demonstrated their monocular SLAM supported approach that is able to achieve stronger performance against the classical frame based approach [where misclassifications occur occasionally]. The system is able to detect and robustly recognize objects in its environment using a single RGB camera. They have presented their paper at the Robotics Science and Systems conference last week. The system uses SLAM information to augment existing object-recognition algorithms. Robot with camera provide the improved object predictions in all views.
Re: (Score:1)
Robots will do a better job and not require Cheetos or a soft drink.
What do you mean soon old-timer?
Samzenpus is a Editor bot v.0.01 (Eliza v.9.01) - you insensitive clod. Cutting edge.
Oh wait... I misread the clock. It's 2015 not 2005. Samzenpus is an out-of-date Editor bot. Dice has been cost-cutting again.
SLAM is not new (Score:1)
Where are the news here?
Re: SLAM is not new (Score:2)
I think the gist is that MIT has improved SLAM via better use of object recognition, not that they've improved object recognition. And at best this news is evolutionary, not revolutionary.
Why this is useful (Score:5, Insightful)
As a researcher in this field not affiliated with this work, the merit is that most SLAM methods (that's essentially mapping an environment and tracking your position within it) have generally had very little understanding of the map that results. The world is most commonly a fuzzy blob of pixels or voxels.
In contrast, a human might "map" an environment in terms of salient objects, like "The potted plant" or a set of office chair. Such a semantic map has several possible advantages--- it could support more natural interactions with people, and it can serve as a powerful regularizer that prevents the robot from learning incorrect maps.
The particular method described in this paper is pretty well executed, and making a system that runs in real time with such a large amount of data is not easy. Of course, many researchers are looking at building semantic maps.
SLAM? (Score:2)
I thought SLAM was a program to deny food to poor people.. "Suspected of Living Above Means".
SLAM: Simultaneous Location And Mapping (Score:3)
Psst, hey, editors -- it's always a good idea to spell out acronyms when they're first used if they're unfamiliar to those outside the article's specialty.