A driver remotely steers a modified utility vehicle through an obstacle course of barrels and cones dotting a Michigan field. A researcher tells the driver to keep the wheel straight—putting the vehicle on a collision course with a barrel. But the vehicle steers itself around the obstacle, handing control back to the driver once the danger has passed.
A new semiautonomous safety system developed by PhD student Sterling Anderson and Karl Iagnemma of MIT’s Robotic Mobility Group uses an onboard camera and laser range finder to identify nearby hazards. An algorithm analyzes the data and identifies safe zones where there’s no danger of colliding with, say, barrels in a field or other cars on the road. When a driver is in danger of leaving a safe zone, the system takes the wheel.
Anderson and Iagnemma identified safe zones by dividing a vehicle’s environment into triangles, with certain edges representing an obstacle or lane boundary. Their algorithm “constrains” obstacle-abutting edges, allowing a driver to navigate across any unconstrained triangle edge. If a driver is in danger of crossing a constrained edge—for instance, if he’s fallen asleep and is about to run into a barrier—the system, which Anderson calls an “intelligent copilot,” steers the car back into the safe zone.
The researchers hope to pare down the system so it can operate on a single cell phone.
How Facebook and Google fund global misinformation
The tech giants are paying millions of dollars to the operators of clickbait pages, bankrolling the deterioration of information ecosystems around the world.
This new startup has built a record-breaking 256-qubit quantum computer
QuEra Computing, launched by physicists at Harvard and MIT, is trying a different quantum approach to tackle impossibly hard computational tasks.
This scientist now believes covid started in Wuhan’s wet market. Here’s why.
How a veteran virologist found fresh evidence to back up the theory that covid jumped from animals to humans in a notorious Chinese market—rather than emerged from a lab leak.
DeepMind says it will release the structure of every protein known to science
The company has already used its protein-folding AI, AlphaFold, to generate structures for the human proteome, as well as yeast, fruit flies, mice, and more.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.