Robotics & Automation News

Market trends and business perspectives

researchers

Deep learning networks prefer the human voice – just like we do

by Leave a Comment

Columbia engineers demonstrate that AI systems might reach higher performance if programmed with sound files of human language rather than with binary data labels. (See video below.)

The digital revolution is built on a foundation of invisible 1s and 0s called bits.

As decades pass, and more and more of the world’s information and knowledge morph into streams of 1s and 0s, the notion that computers prefer to “speak” in binary numbers is rarely questioned.

According to new research from Columbia Engineering, this could be about to change. [Read more…] about Deep learning networks prefer the human voice – just like we do

MIT CSAIL’s robo-starfish enables closer study of aquatic life

by Leave a Comment

Scientists have invented a ‘robo-starfish’ which give us more insights into aquatic life, as Adam Conner-Simons, or MIT CSAIL, reports. (See video below.)

Biologists have long experienced the challenges of documenting ocean life, with many species of fish proving quite sensitive to the underwater movements of humans.

As a possible solution, computer scientists have been developing special marine robots that can stealthily move among their carbon-based counterparts. In 2018, for example, a team from MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) fabricated a soft robotic fish that autonomously swam with real fish along the coral reefs of Fiji.

However, the complex dynamics of how water moves – and its ability to quickly ruin some perfectly good electronics systems – have made underwater robots especially difficult to develop compared to ones for air or land. [Read more…] about MIT CSAIL’s robo-starfish enables closer study of aquatic life

Artificial skin brings robots closer to ‘touching’ human lives

by Leave a Comment

Modern-day robots are often required to interact with humans intelligently and efficiently, which can be enabled by providing them the ability to perceive touch.

However, previous attempts at mimicking human skin have involved bulky and complex electronics, wiring, and a risk of damage.

In a recent study, researchers from Japan sidestep these difficulties by constructing a 3D vision-guided artificial skin that enables tactile sensing with high performance, opening doors to innumerable applications in medicine, healthcare, and industry. [Read more…] about Artificial skin brings robots closer to ‘touching’ human lives

Swiss university developing mobile robot that learns on the job

by Leave a Comment

A team from the Autonomous Systems Lab at the public research university ETH Zurich in Switzerland is creating robots and intelligent systems that are able to learn on the job. (See video below.)

The team’s machine – which consists of a robotic arm mounted on a mobile platform – can “autonomously operate in complex and diverse environments”, says an article on Clearpath Robotics’ website.

Using a Clearpath Ridgeback as a base and equipped with a Franka Emika Panda manipulator arm (called RoyalPanda, that is Ridgeback + Panda), the team is experimenting with a series of different scenarios to develop best practices of how a robot could “learn”. [Read more…] about Swiss university developing mobile robot that learns on the job

Showing robots how to drive a car… in just a few easy lessons

by Leave a Comment

USC researchers have developed a method that could allow robots to learn new tasks, like setting a table or driving a car, from observing a small number of demonstrations.

Imagine if robots could learn from watching demonstrations: you could show a domestic robot how to do routine chores or set a dinner table. In the workplace, you could train robots like new employees, showing them how to perform many duties. On the road, your self-driving car could learn how to drive safely by watching you drive around your neighborhood.

Making progress on that vision, USC researchers have designed a system that lets robots autonomously learn complicated tasks from a very small number of demonstrations – even imperfect ones. The paper, titled Learning from Demonstrations Using Signal Temporal Logic, was presented at the Conference on Robot Learning (CoRL). [Read more…] about Showing robots how to drive a car… in just a few easy lessons

IBM launches new industrial chemistry robot to enable lab automation

by Leave a Comment

IBM has launched a new industrial chemistry lab robot called RoboRXN, describing it as “the first remotely accessible, autonomous chemical laboratory”. (See video below.)

The computing giant says the RXN machine is “revolutionizing industrial chemistry, by transforming it into a high tech business”.

RXN uses a combination of artificial intelligence, automation and cloud computing to relieve the chemist from tedious repetitive tasks, allowing more time and space for design and innovation. [Read more…] about IBM launches new industrial chemistry robot to enable lab automation

CMU researchers train autonomous drones using cross-modal simulated data

by Leave a Comment

To fly autonomously, drones need to understand what they perceive in the environment and make decisions based on that information. (See video below.)

A novel method developed by Carnegie Mellon University researchers allows drones to learn perception and action separately.

The two-stage approach overcomes the “simulation-to-reality gap”, and creates a way to safely deploy drones trained entirely on simulated data into real-world course navigation. [Read more…] about CMU researchers train autonomous drones using cross-modal simulated data

Heraeus and Aachen University develop ‘fastest-ever’ artificial synapses

by Leave a Comment

The boffins say that the secret is ‘foreign atoms in the oxide layer’ which have so far gone unnoticed by experts

Scientists and researchers from the materials science-oriented technology group Heraeus and the Jülich Aachen Research Alliance have developed what they describe as “artificial synapses” similar to the ones found in the human brain.

The collective of brainboxes say that their discovery could be useful in the development of branches of artificial intelligence, such as machine learning and deep learning.

The boffins discovered how the switching properties of artificial synapses can be specifically influenced. [Read more…] about Heraeus and Aachen University develop ‘fastest-ever’ artificial synapses

Scientists develop ‘flexoskeletons’ that cost a dollar to 3D print

by Leave a Comment

Engineers at the University of California San Diego have developed a new method that doesn’t require any special equipment and works in just minutes to create soft, flexible, 3D-printed robots. (See video below.)

The innovation comes from rethinking the way soft robots are built: instead of figuring out how to add soft materials to a rigid robot body, the UC San Diego researchers started with a soft body and added rigid features to key components.

The structures were inspired by insect exoskeletons, which have both soft and rigid parts – the researchers called their creations “flexoskeletons”. [Read more…] about Scientists develop ‘flexoskeletons’ that cost a dollar to 3D print

Columbia engineers develop ‘tactile robot finger with no blind spots’

by Leave a Comment

Researchers at Columbia Engineering say they have developed a new type of robotic finger with a sense of touch. Their finger can localize touch with very high precision – less than 1 mm – over a large, multicurved surface, much like its human counterpart. (See video below.)

Matei Ciocarlie, associate professor in the departments of mechanical engineering and computer science, says: “There has long been a gap between standalone tactile sensors and fully integrated tactile fingers–tactile sensing is still far from ubiquitous in robotic manipulation.”

Ciocarlie led this work in collaboration with Electrical Engineering Professor Ioannis Kymissis. [Read more…] about Columbia engineers develop ‘tactile robot finger with no blind spots’

By continuing to use the site, you agree to the use of cookies. more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.

Close