Last update

Robotics

New system enables intuitive teleoperation of a robotic manipulator in real-time

Imitation learning is a promising method to teach robots how to reliably complete everyday tasks, such as washing dishes or cooking. Despite their potential, imitation learning frameworks rely on detailed human demonstrations, ...

Energy & Green Tech

Machine learning framework maps global rooftop growth for sustainable energy and urban planning

A novel machine learning framework developed by IIASA researchers to estimate global rooftop area growth from 2020 to 2050 can aid in planning sustainable energy systems, urban development, and climate change mitigation, ...

Machine learning & AI

New technique to assess a general-purpose AI model's reliability before it's deployed

Foundation models are massive deep-learning models that have been pretrained on an enormous amount of general-purpose, unlabeled data. They can be applied to a variety of tasks, like generating images or answering customer ...

Security

Engineers evaluate cybersecurity risks associated with EV fast-charging equipment

Engineers at Southwest Research Institute have identified cybersecurity vulnerabilities with electric vehicles (EVs) using direct current fast-charging systems, the quickest, commonly used way to charge electric vehicles. ...

Machine learning & AI

A new neural network makes decisions like a human would

Humans make nearly 35,000 decisions every day, from whether it's safe to cross the road to what to have for lunch. Every decision involves weighing the options, remembering similar past scenarios, and feeling reasonably confident ...

Consumer & Gadgets

Open-TeleVision allows VR-type control of remote robot

A combined team of roboticists from MIT and the University of California, San Diego, has developed a new type of remote control for robots called Open-TeleVision that allows for VR-type control. The team has posted a paper ...

Hardware

Neural network training made easy with smart hardware

Large-scale neural network models form the basis of many AI-based technologies such as neuromorphic chips, which are inspired by the human brain. Training these networks can be tedious, time-consuming, and energy-inefficient ...

Energy & Green Tech

New material paves the way to on-chip energy harvesting

Researchers from Germany, Italy, and the UK have achieved a major advance in the development of materials suitable for on-chip energy harvesting. By composing an alloy made of silicon, germanium and tin, they were able to ...

Electronics & Semiconductors

A new brain-inspired artificial dendritic neural circuit

Following the rapid advancement of artificial intelligence (AI) tools, engineers worldwide have been working on new architectures and hardware components that replicate the organization and functions of the human brain.

Energy & Green Tech

Cool roofs outperform green roofs in urban climate modeling study

Painting roofs white or covering them with a reflective coating would be more effective at cooling cities like London than vegetation-covered "green roofs," street-level vegetation or solar panels, finds a new study led by ...