Hacker News Reader

Dealing with poorly behaved surfaces (specular, luminous, reflective, deformity) in 3D reconstruction.

Figuring out human interaction intent from force measurements for cooperating with a robot in a collaborative task (moving a table together).

Both language agnostic.

View on HN

3D reconstruction is a pretty big problem. Anyone who solves that problem by just using a camera on a mobile phone and doing processing offline in real-time can make huge strides for robotics.

We have the advances in Deep learning but we're still have to make some strides before robots can infer the same way we humans do about objects we see.

Reply on news.ycombinator.com