Nvidia teaches robots how to mimic human actions with new deep learning process

ronjor · May 21, 2018

By Greg Synek

Robots learn after just one observation period
Click to expand...

guest · Jul 3, 2018

Nvidia aims to run neural nets faster, more efficiently
July 3, 2018
https://www.zdnet.com/article/nvidia-aims-to-run-neural-nets-faster-more-efficiently/

Artificial intelligence is having a real impact on many industries. It now exceeds humans at some image recognition and speech recognition tasks, it is approaching human levels for language translation, and it is beating experts at all sorts of games.

[...] Bill Dally, Nvidia's Chief Scientist and head of research, said at the recent VLSI Symposia. "Every aspect of human life and commerce is going to be deeply impacted by AI."

Despite these advances, deep learning remains "completely gated by hardware" because the jobs are getting bigger. Dally discussed some of the way that circuit design can increase efficiency of training and inference to meet these growing requirements.
Click to expand...

guest · Jul 7, 2018

The End is Nigh: Robot Learns to Mimic Human Behavior
July 5, 2018
https://www.geek.com/tech/the-end-is-nigh-robot-learns-to-mimic-human-behavior-1745125/

Researchers at UC Berkeley have taught an android to mimic human skills, advancing machines another step toward global domination.
Learning a new skill by observing others is a “key part” of intelligence in humans and animals, the BAIR blog said.

“Such a capability would make it dramatically easier for us to communicate new goals to robots,” according to undergrad Tianhe Yu and PhD student Chelsea Finn. “We could simply show robots what we want them to do, rather than teleoperating the robot or engineering a reward function.”

“We hope that these models will be able to achieve broader generalization, allowing robots to quickly develop strategies for new situations,” the blog said.
Click to expand...

guest · Oct 29, 2018

Nvidia researchers make it easier to train robots to pick up stuff
October 29, 2018
https://www.zdnet.com/article/nvidia-researchers-make-it-easier-to-train-robots-to-pick-up-stuff/

To find and pick up an object in the real world -- even if it's misplaced -- a robot needs a computer vision algorithm that can identify the 3D position and orientation of an object in a scene -- what's known as the " 6-DoF (degrees of freedom) pose."

This week at the Conference on Robot Learning in Zurich, a team of Nvidia researchers is presenting a novel deep learning-based system that may offer a solution.
[...] by using a unique combination of synthetic images, the Nvidia team has trained an algorithm that can actually outperform a network trained on real images.

This represents the first time an algorithm trained only with synthetic data has been able to beat a network trained on real images for object pose estimation on several objects of a standard benchmark. This will make training algorithms for robots much easier.
Click to expand...

Log in or Sign up

Nvidia teaches robots how to mimic human actions with new deep learning process

ronjor Global Moderator

guest Guest

guest Guest

guest Guest

Log in or Sign up

Nvidia teaches robots how to mimic human actions with new deep learning process

ronjor Global Moderator

guest Guest

guest Guest

guest Guest

Useful Searches