One of the most promising approaches to teaching robots how to complete manual tasks such as cleaning dishes or preparing food is known as imitation learning. End-to-end imitation learning typically entails training a deep learning algorithm on raw videos, images...
TECHXPLORE
Shrinking AI for personal devices: An efficient small language model that could perform better on smartphones
Large language models (LLMs), such as Open AI's renowned conversational platform ChatGPT, have recently become increasingly widespread, with many internet users relying on them to find information quickly and produce texts for various purposes. Yet most of these...
Integrated multi-modal sensing and learning system could give robots new capabilities
To assist humans with household chores and other everyday manual tasks, robots should be able to effectively manipulate objects that vary in composition, shape and size. The manipulation skills of robots have improved significantly over the past few years, in part due...
Optoelectronic device mimics human vision for diversified in-sensor computing
To make sense of the world, most humans rely in great part on their vision. Recent research suggests that the human visual system is hierarchical, meaning that it processes information on different levels, ranging from the low-level processing of sensory stimuli to...
A nervous system-inspired framework to deploy self-organizing robot swarms
The deployment of robot teams could allow humans to complete various real-world tasks faster and more efficiently. For instance, multiple co-operating robots could help to quickly find and rescue survivors of natural disasters or monitor pollution across large...
Seatbelt-integrated biosensor could reliably track the alertness and stress of pilots and drivers
Over the past decades, electronics and biomedical engineers have developed increasingly sophisticated biosensors, devices that can pick up biological signals from human users. These sensors, which are generally embedded in wearable or implantable technologies, often...
LEDs based on transition metal dichalcogenides display reduced efficiency losses
Light-emitting diodes (LEDs), semiconductor-based devices that emit light when an electric current flows through them, are key building blocks of numerous electronic devices. LEDs are used to light up smartphone, computer, and TV displays, as well as light sources for...
First practical application of viscous electron flow realizes terahertz photoconductivity in graphene
When light hits the surface of some materials, namely those exhibiting a property known as photoresistance, it can induce changes in their electrical conductivity. Graphene is among these materials, as incident light can excite electrons within it, affecting its...
Creating compact near-sensor computing chips via 3D integration of 2D materials
Three-dimensional (3D) integration has opened new possibilities for the development of denser circuits with more interconnected electronic components. 3D integration approaches entail stacking multiple layers of electronic circuits together, ultimately producing more...
One-step electrochemical regeneration of CO₂ from (bi)carbonates enhances carbon capture efficiency
While systems that can generate energy from renewable sources are becoming increasingly widespread, it might take a while before these systems fully replace solutions that rely on the burning of fossil fuels. In the meantime, researchers have been trying to develop...