Skip to main content

MIT’s shadow-watching tech could let autonomous cars see around corners

Whether it’s cyclists about to lurch into the wrong lane or a pedestrian getting ready to cross the street, self-driving cars need to be hyperaware of what is going on around them at all times. But one thing they can’t do is to see around corners. Or can they? In a paper presented at this week’s International Conference on Intelligent Robots and Systems (IROS), Massachusetts Institute of Technology researchers have shown off technology which could allow autonomous vehicles or other kinds of robots to do exactly that — by looking for changes in shadows on the ground to reveal if a moving object is headed their way.

“ShadowCam operates by detecting small differences in shadows and using this information to detect possible static and dynamic objects that are otherwise out of your line of sight,” Alexander Amini and Igor Gilitschenski, two MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) researchers who worked on the project, told Digital Trends via email. “First of all, we need to focus on the same region of interest as we move, which we achieve by integrating a visual motion estimation technique into ShadowCam. Based on this stabilized image of the region of interest, we [then] use color amplification combined with a dynamic threshold on the intensity changes.”

In tests, the system has shown that it could increase the stopping ability of automated vehicles by more than 0.5 of a second compared to regular Lidar technology. While half a second sounds like only the most incremental of improvements, these kind of hair-trigger reactions could potentially mean the difference between colliding with another vehicle and stopping in time.

So far, the technology has only been tested in indoor settings. As with any robot-based system, lab conditions can be deceptive since they make it easier to control variables. In this case, it means more consistent lighting, which helps the system to better analyze shadows. Nonetheless, as with self-driving cars themselves (which, not too long ago, seemed like they would remain research projects only), tech continues to advance at an astonishing rate. With that in mind, we wouldn’t bet against technology like ShadowCam popping up as an assistive driving staple before too much longer.

Editors' Recommendations

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Robotaxi firm Cruise ordered to halve fleet following incidents
A Cruise autonomous car.

Autonomous car company Cruise has been told by regulators to halve its robotaxi fleet in San Francisco following a crash with a fire truck on Thursday in which the driverless car's passenger suffered minor injuries.

The regulator -- the California Department of Motor Vehicles (DMV) -- said that it’s looking into “recent concerning incidents” involving self-driving Cruise cars operating on the city’s public roads.

Read more
An autonomous car in San Francisco got stuck in wet concrete
A Cruise autonomous car.

A self-driving car operated by General Motors-backed Cruise got stuck on Tuesday when it drove into a patch of wet concrete.

The incident happened in San Francisco and occurred just days after California's Public Utilities Commission made a landmark decision when it voted to allow autonomous-car companies Cruise and Waymo to expand their paid ridesharing services in the city to all hours of the day instead of just quieter periods.

Read more
Waymo taps the brakes on its autonomous-trucking project
A Waymo autonomous trick undergoing testing on a highway.

Six years after launching its autonomous-truck program, Waymo has said it’s decided to focus more on developing its ridesharing ambitions using its self-driving cars and minivans.

The California-based, Alphabet-owned company said its decision to effectively put autonomous trucking on the back burner is down to the “tremendous momentum and substantial commercial opportunity” that it’s seeing with the pilot ridesharing service it launched in Arizona in 2018 before taking it to several other states. Customers involved in the program can use an app to call a Waymo driverless car in the same way they would book an Uber.

Read more