Pushy robots learn the fundamentals of object manipulation

Researchers have compiled a dataset that captures the detailed behavior of a robotic system physically pushing hundreds of different objects. Using the dataset — the largest and most diverse of its kind — researchers can train robots to 'learn' pushing dynamics that are fundamental to many complex object-manipulation tasks, including reorienting and inspecting objects, and uncluttering scenes.

Read more

Giving robots a faster grasp

Engineers have found a way to significantly speed up the planning process required for a robot to adjust its grasp on an object by pushing that object against a stationary surface. Whereas traditional algorithms would require tens of minutes for planning out a sequence of motions, the new team's approach shaves this planning process down to less than a second.

Read more

Clingfish biology inspires better suction cup

A team of engineers and marine biologists built a better suction cup inspired by the mechanism that allows the clingfish to adhere to both smooth and rough surfaces. Researchers reverse engineered the clingfish's suction disk and developed devices that cling well to wet and dry objects both in an out of water. The devices can hold up to hundreds of times their own weight.

Read more

Robotic hand solves Rubik’s Cube by learning how to learn about it

Credit to Author: Lisa Vaas| Date: Thu, 17 Oct 2019 10:14:37 +0000

The system figured out how to overcome little hurdles, like being nudged by a stuffed giraffe when trying to do important robot work.<img src=”http://feeds.feedburner.com/~r/nakedsecurity/~4/veD4J8v7FpI” height=”1″ width=”1″ alt=””/>

Read more

Researchers build a soft robot with neurologic capabilities

In work that combines a deep understanding of the biology of soft-bodied animals such as earthworms with advances in materials and electronic technologies, researchers have developed a robotic device containing a stretchable transistor that allows neurological function.

Read more