AI Helps Robots Manipulate Objects with Their Entire Bodies

Humans are generally good at whole-body manipulation, but robots struggle with such tasks. Now, MIT researchers have found a way to simplify this process, known as contact-rich manipulation planning.

Robot Reads Braille Twice as Fast as Humans

Although the robot braille reader was not developed as an assistive technology, the researchers say the high sensitivity required to read braille makes it an ideal test in the development of robot hands or prosthetics with comparable sensitivity to human fingertips.

Autonomous Mobile Robots Take a Direct Route to Optimization With AI

While advanced vision systems give AMRs the power of “sight,” so to speak, AI allows them to identify objects and optimizes how they navigate on a factory floor.

AI Model to Streamline Operations in a Robotic Warehouse

In the future, the researchers want to derive simple, rule-based insights from their neural model, since the decisions of the neural network can be opaque and difficult to interpret. Simpler, rule-based methods could also be easier to implement and maintain in actual robotic warehouse settings.

Amateur Drone Videos Could Aid Natural Disaster Damage Assessment

By using artificial intelligence, researchers are developing a system that can automatically identify buildings after disasters and make an initial determination of whether they are damaged and how serious that damage might be.

AI Co-Pilot Enhances Human Precision for Safer Aviation

Meet Air-Guardian: A system developed by researchers at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). As modern pilots grapple with an onslaught of information from multiple monitors, especially during critical moments, Air-Guardian acts as a proactive co-pilot; a partnership between human and machine, rooted in understanding attention.

A Soft Robotic Hand Uses AI to Improve Hand Dexterity

A first-of-its-kind robotic glove is lending a “hand” and providing hope to piano players who have suffered a disabling stroke. Developed by researchers from Florida Atlantic University’s College of Engineering and Computer Science, the soft robotic hand exoskeleton uses artificial intelligence to improve hand dexterity.

Generative AI Models Solve Multistep Robot Manipulation Problems

MIT researchers developed a machine-learning technique called Diffusion-CCSP. Diffusion models learn to generate new data samples that resemble samples in a training dataset by iteratively refining their output.

PockEngine Enables AI on Edge Devices to Keep Learning Over Time

Researchers from MIT, the MIT-IBM Watson AI Lab, and elsewhere have developed a technique that enables deep-learning models to efficiently adapt to new sensor data directly on an edge device. Their on-device training method, Pock-Engine, determines which parts of a huge machine-learning model need to be updated to improve accuracy, and only stores and computes with those specific pieces.

Executive Roundtable: Artificial Intelligence

What are the opportunities and risks AI offers in manufacturing? How can manufacturers successfully implement AI and prepare their workforce to integrate it into their processes? What’s its future outlook? Tech Briefs asked four industry experts in this roundtable.

Artificial Intelligence: How Cloud Technology and AI Drive a More Productive Future

This new era of technology eases the twin challenges of capacity and complexity and offers more flexibility than ever for businesses to respond to a fast-changing world.

Contact-Free 3D Hybrid Printing with New High-Performance Materials

Javier Ramos, CTO, and his team from Inkbit Corporation, Medford, MA, along with researchers from MIT and ETH Zurich, have developed a 3D inkjet printer that uses contact-free computer vision feedback to print hybrid objects with a broad range of new functional chemistries.

Wireless Networking Expanding the Reach of Healthcare

Devices to remotely monitor patients’ health have been around for more than 20 years, but their use is rapidly expanding now. As networking technologies such as LoRaWAN are maturing, and artificial intelligence is being embedded in “smart” sensors, the medical device industry is motivated to take advantage.

An AI-Enabled Soft Robotic Implant Monitors Scar Tissue

Research teams at University of Galway and MIT have detailed a new breakthrough in medical device technology that could lead to intelligent, long-lasting, tailored treatment for patients thanks to soft robotics and artificial intelligence.

Maneuvering Robot Control Using Machine Learning

Researchers from MIT and Stanford University have devised a new machine-learning approach that could be used to control a robot, such as a drone or autonomous vehicle, more effectively and efficiently in dynamic environments where conditions can change rapidly.

Getting EV Battery Gigafactories Up to Speed

The term “gigafactory” has become common lexicon for a manufacturing facility constructed to produce the almost incalculable number of individual battery cells required for the millions of...

Advanced Electrical Architectures Demand New Developmental Strategies

As the need for sophisticated functionality increases, high-performance computers and zone controllers could be the heart of next-generation vehicle electrical platforms.

Detecting Porosity Defects in 3D-Printed Metal Parts

A research team has made new discoveries that can expand additive manufacturing in industries that rely on strong metal parts, including aerospace.

Transferring Data with Many Colors of Light Simultaneously

Researchers have demonstrated an energy-efficient method for transferring larger quantities of data over the fiber-optic cables that connect the nodes. This new technology improves on previous attempts to transmit multiple signals simultaneously over the same fiber-optic cables.

Detecting Threats Beyond the Limits of Human, Sensor Sight

A new patented software system can find the curves of motion in streaming video and images from satellites, drones, and far-range security cameras and turn them into signals to find and track moving objects as small as one pixel.

Six Considerations When Choosing Machine Vision in Collaborative Applications

Machine vision dates back to the beginning of the modern industrial robot age in the 1980s. Augmenting cobots with vision allows them to perform with higher precision, flexibility, and intelligence. However, integration is not a one-size-fits-all process.

5G, AI Team Up to Optimize Military Fueling

Armed with 5G network technology, AI, and edge computing resources, a pilot project under development at Naval Air Station Whidbey Island aims to create an optimized refueling system designed to boost readiness for military aircraft.

Drones Navigate Unseen Environments via Liquid Neural Networks

Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have introduced a method for robust flight navigation agents to master vision-based fly-to-target tasks in intricate, unfamiliar environments.

Highly Dexterous Robot Hand Can Operate in the Dark

Researchers at Columbia Engineering have demonstrated a highly dexterous robot hand, one that combines an advanced sense of touch with motor learning algorithms in order to achieve a high level of dexterity.

A Four-Legged Robotic System Can Move on Tough Landscapes

Researchers from MIT’s Improbable Artificial Intelligence Lab have developed a legged robotic system that can dribble a soccer ball under the same conditions as humans.

Micromotor Winding Technology Uses AI to Improve Motor Performance

Achievable coils increase the capabilities of the micromotors.

Implantable Chip Uses Machine Learning to Detect Neural Disease

Boasting a 256-channel high-resolution sensing array and an energy-efficient machine learning processor, NeuralTree can extract and classify a broad set of biomarkers from real patient data and animal models of disease in-vivo.

Augmented Reality Headset Provides X-Ray Vision

MIT researchers have built an AR headset that gives the wearer X-ray vision. The headset combines computer vision and wireless perception to automatically locate a specific item that is hidden from view.

Always-On Intelligent Sensing at Microwatt Levels

An interview with Tom Doyle, CEO and Founder of Aspinity, Pittsburgh, PA, about the company's analog machine learning chip, the AML100 analog machine learning processor.