And here we have the fruit pickers of the future. Hovering drones. đ
This fleet of drones will pick fruit for you! Fruit production has exploded over the past few years, but so has food waste! Increased demand sometimes means unpi⊠See More.
Category: robotics/AI – Page 1,866
Next Stop: The Moon for 27,000+ CAP Names
NEW: A microchip carrying more than 27,000 Civil Air Patrol names with related messages and images is set to be carried to the moon later this year aboard space robotics company Astroboticâs Peregrine lunar lander. https://www.cap.news/next-stop-the-moon-for-27000-cap-names/
A microchip carrying more than 27000 Civil Air Patrol names with related messages and images is set to be carried to the moon later this year aboard space robotics company Astroboticâs Peregrine lunar lander.
A submersible soft robot survived the pressure in the Mariana trench
A silicone robot has survived a journey to 10900 metres below the oceanâs surface in the Mariana trench, where the crushing pressure can implode all but the strongest enclosures. This device could lead to lighter and more nimble submersible designs.
A team led by Guorui Li at Zhejiang University in China based the robotâs design on snailfish, which have relatively delicate, soft bodies and are among the deepest-living fish. They have been observed swimming at depths of more than 8000 metres.
The submersible robot looks a bit like a manta ray and is 22 centimetres long and 28 centimetres in wingspan. It is made of silicone rubber with electronic components spread throughout the body and connected by wires, rather than mounted on a circuit board like most submersibles. Thatâs because the team found in tests that the connections between components on rigid circuit boards were a weak point when placed under high pressure.
Facebookâs New AI Teaches Itself to See With Less Human Help
The Facebook research builds upon steady progress in tweaking deep learning algorithms to make them more efficient and effective. Self-supervised learning previously has been used to translate text from one language to another, but it has been more difficult to apply to images than words. LeCun says the research team developed a new way for algorithms to learn to recognize images even when one part of the image has been altered.
Most image recognition algorithms require lots of labeled pictures. This new approach eliminates the need for most of the labeling.
