Category Physics

A compact, lightweight sensor system with infrared imaging capabilities developed by an international team of engineers could be easily fitted to a drone for remote crop monitoring.

This flat-optics technology has the potential to replace traditional optical lens applications for environmental sensing in a range of industries.

This innovation could result in cheaper groceries as farmers would be able to pinpoint which crops require irriga...

With the rapid advancement of artificial intelligence, unmanned systems such as autonomous driving and embodied intelligence are continuously being promoted and applied in real-world scenarios, leading to a new wave of technological revolution and industrial transformation. Visual perception, a core means of information acquisition, plays a crucial role in these intelligent systems. However, achieving efficient, precise, and robust visual perception in dynamic, diverse, and unpredictable environments remains an open challenge.

In open-world scenarios, intelligent systems must not only process vast amounts of data but also handle various extreme events, such as sudden dangers, drastic light changes at tunnel entrances, and strong flash interference at night in driving scenarios.

Floating solar photovoltaic panels could supply all the electricity needs of some countries, new research has shown.

The study, by researchers from Bangor and Lancaster Universities and the UK Centre for Ecology & Hydrology, aimed to calculate the global potential for deploying low-carbon floating solar arrays. The researchers calculated the daily electrical output for floating photovoltaics (FPV) on nearly 68,000 lakes and reservoirs around the world, using available climate data for each location.

The researchers’ calculations included lakes and reservoirs where floating solar technology is most likely to be installed. They were no more than 10km from a population centre, not in a protected area, didn’t dry up and didn’t freeze for more than six months each year...

With generative AI models, researchers combined robotics data from different sources to help robots learn better. MIT researchers developed a technique to combine robotics training data across domains, modalities, and tasks using generative AI models. They create a combined strategy from several different datasets that enables a robot to learn to perform new tasks in unseen environments.

Let’s say you want to train a robot so it understands how to use tools and can then quickly learn to make repairs around your house with a hammer, wrench, and screwdriver...