Machine learning

MIT and Toyota researchers have designed a new model that weighs various uncertainties and risks to help autonomous vehicles determine when it’s safe to merge into traffic at intersections with objects obstructing views, such as buildings blocking the line of sight.

Better autonomous “reasoning” at tricky intersections

Model alerts driverless cars when it’s safest to merge into traffic at intersections with obstructed views.

November 4, 2019

For last-mile delivery, robots of the future may use a new MIT algorithm to find the front door, using clues in their environment.

Technique helps robots find the front door

Navigation method may speed up autonomous last-mile delivery.

November 4, 2019

In a study using machine-generated art to understand what makes a picture memorable, researchers found that the images people remembered best had bright colors, simple backgrounds, and subjects centered prominently in the frame.

What makes an image memorable? Ask a computer

An artificial intelligence model developed at MIT shows in striking detail what makes some images stick in our minds.

November 1, 2019

Bryan Reimer, an AgeLab research scientist and the associate director of the New England University Transportation Center, was honored for his work developing a better understanding of how people engage with vehicle automation.

Bryan Reimer receives human factors innovator award

MIT AgeLab research engineer directs a team that studies in-vehicle automation, robotics, AI, and the mechanics of driver attention, among other topics.

October 30, 2019

MIT engineers have developed a system for autonomous vehicles that senses tiny changes in shadows on the ground to determine if there’s a moving object coming around the corner, such as when another car is approaching from behind a pillar in a parking garage.

Helping autonomous vehicles see around corners

By sensing tiny changes in shadows, a new system identifies approaching objects that may cause a collision.

October 27, 2019

Using a supercomputing system, MIT researchers developed a model that captures what global web traffic could look like on a given day, including previously unseen isolated links (left) that rarely connect but seem to impact core web traffic (right).

Supercomputer analyzes web traffic across entire internet

Modeling web traffic could aid cybersecurity, computing infrastructure design, Internet policy, and more.

October 27, 2019

A key to compiling the novel Omnipush dataset was building modular objects (pictured) that enabled the robotic system to capture a vast diversity of pushing behavior. The central pieces contain markers on their centers and points so a motion-detection system can detect their position within a millimeter.

Pushy robots learn the fundamentals of object manipulation

Systems “learn” from novel dataset that captures how pushed objects move, to improve their physical interactions with new objects.

October 21, 2019

At left, EdgeConv, a method developed at MIT, successfully finds meaningful parts of 3D shapes, like the surface of a table, wings of an airplane, and wheels of a skateboard. At right is the ground-truth comparison.

Deep learning with point clouds

Research aims to make it easier for self-driving cars, robotics, and other applications to understand the 3D world.

October 21, 2019

Computer science in service of medicine

Senior Kristy Carpenter aims to leverage artificial intelligence and other computational tools to develop new, more affordable drugs.

October 18, 2019

A novel model developed at MIT recovers valuable data lost from images and video that have been “collapsed” into lower dimensions. It can, for instance, recreate video from motion-blurred images or from cameras that capture people’s movement around corners as vague one-dimensional lines.

Recovering “lost dimensions” of images and video

Model could recreate video from motion-blurred images and “corner cameras,” may someday retrieve 3D data from 2D medical images.

October 16, 2019

A new technique for training video recognition models is up to three times faster than current state-of-the-art methods while improving runtime performance on mobile devices. The work was recently highlighted by Dario Gil (above), director of IBM Research, at the MIT-IBM Watson AI Lab’s AI Research Week in Cambridge, Massachusetts.

Faster video recognition for the smartphone era

MIT and IBM researchers offer a new method to train and run deep learning models more efficiently.

October 11, 2019

Left to right: senior research scientist David Clark, graduate student Cecilia Testart, and postdoc Philipp Richter

Using machine learning to hunt down cybercriminals

Model from the Computer Science and Artificial Intelligence Laboratory identifies “serial hijackers” of internet IP addresses.

October 8, 2019

Traditional structure-based representations of the many forms of zeolites, some of which are illustrated here, provide little guidance as to how they can convert to other forms, but a new graph-based system does a much better job.

A new mathematical approach to understanding zeolites

Study of minerals widely used in industrial processes could lead to discovery of new materials for catalysis and filtering.

October 7, 2019

MIT Associate Professor of Materials Science and Engineering Juejun (JJ) Hu

3 Questions: How artificial intelligence is supercharging materials science

Associate Professor Juejun Hu shines a light on the impact machine learning and AI are having on materials science and engineering.

October 3, 2019

A system designed by researchers at MIT and elsewhere enables interconnected smart devices to cooperatively pinpoint their positions in noisy environments where GPS usually fails, which is useful for emerging “localization-of-things” applications.

System helps smart devices find their position

Connected devices can now share position information, even in noisy, GPS-denied areas.

October 2, 2019

MIT News | Massachusetts Institute of Technology

Browse By

Topics

Departments

Centers, Labs, & Programs

Schools

Topic