Researchers at the Skolkovo Institute of Science and Technology (Skoltech) in Russia have recently introduced a new strategy to enhance interactions between humans and robotic swarms, called SwarmTouch. This strategy, presented in a paper pre-published on arXiv,...
TECHXPLORE
Teaching AI agents navigation subroutines by feeding them videos
Researchers at UC Berkeley and Facebook AI Research have recently proposed a new approach that can enhance the navigation skills of machine learning models. Their method, presented in a paper pre-published on arXiv, allows models to acquire visuo-motor navigation...
Telescope: a tool to manage bioinformatics analyses on mobile devices
A team of researchers at UCLA, the University of São Paulo, the Federal University of São Carlos and the University of Southern California has recently developed an interactive tool for managing large-scale bioinformatic analyses in real-time and from portable...
Testing a connected eco-driving system in field trials with heavy-duty trucks
Currently, 90 percent of fuel used for transportation is petroleum-based, making it one of the key contributors to air pollution worldwide. Recent technological advances, however, are finally enabling the development of new tools to reduce energy consumption and...
REPLAB: A low-cost benchmark platform for robotic learning
Researchers at UC Berkeley have developed a reproducible, low-cost and compact benchmark platform to evaluate robotic learning approaches, which they called REPLAB. Their recent study, presented in a paper pre-published on arXiv, was supported by Berkeley DeepDrive,...
ROBOSHERLOCK: a system to enhance robot performance on manipulation tasks
Over the past decade or so, advancements in machine learning have enabled the development of systems that are increasingly autonomous, including self-driving vehicles, virtual assistants and mobile robots. Among other things, researchers developing autonomous systems...
A vision for the creation of 6G communications
Now that the standardization of fifth-generation (5G) communications has been accomplished, with the 5G network set to be launched this year, researchers have already started thinking about what a 6G network could look like. An interesting perspective on the future...
Selecting the best features for phishing attack detection algorithms
In recent decades, phishing attacks have become increasingly common. These attacks allow attackers to obtain sensitive user data, such as passwords, usernames, credit card details, etc., by tricking people into disclosing personal information. The most common type of...
SentiArt: a sentiment analysis tool for profiling characters from world literature texts
Arthur Jacobs, a professor and researcher at Freie Universität Berlin, has recently developed SentiArt, a new machine learning technique to carry out sentiment analyses of literary texts, as well as both fictional and non-fictional figures. In his paper, set to be...
ShapeBots: a swarm of shape-shifting robots that visually display data
Researchers from the University of Colorado Boulder's ATLAS Institute have recently developed a swarm of little shape-changing robots, called ShapeBots. These self-transformable robots, presented in a paper pre-published on arXiv, can change both their individual and...









