Name: Three Tasks Driverless Cars Need to Learn
Uploaded: undefined
Duration: undefined

Nova

To match human drivers, an automated vehicle needs to learn how to handle three distinct tasks: seeing everything around the car, understand what it’s seeing, and planning the car’s path.

There’s a lot going on ‘under the hood’ of a self-driving car.

Three Tasks Driverless Cars Need to Learn

NOVA Science Trust Logo

To match human drivers, an automated vehicle needs to learn how to handle three distinct tasks: seeing everything around the car, understand what it’s seeing, and planning the car’s path.

There’s a lot going on ‘under the hood’ of a self-driving car.

Tech & Engineering

Three Tasks Driverless Cars Need to LearnPublished: October 18, 2019Chris Gerdes: Trying to develop an automated vehicle that can do everything that a human driver can do is a huge problem, and it requires an awful lot of interlocking pieces. Narrator: To even match human drivers, a self-driving car needs to learn to handle not just one, but three distinct tasks nearly flawlessly. The first: seeing everything that’s around the car; second, understanding what it’s seeing; and third, planning the car’s path and controlling its acceleration, braking, and steering along the way.First, seeing: most self-driving cars rely on cameras, radar and LIDAR. Each has weaknesses. Cameras work poorly at night, radar doesn’t distinguish very well between different types of objects, and LIDAR can fail completely in rain, snow or fog. But even when sensors are working nearly perfectly, there’s still the second big challenge: understanding what they are seeing.For us, taking in sensory information and making best guesses about the real world are second nature. For a computer, making meaning out of visual data is fiendishly difficult. In each case, it’s the task called “perception.”Amnon Shashua: The human brain is an expert in perception, but for machines, it’s not natural. So this is one big challenge, that if you want to drive autonomously, you need to perceive the world just like humans do. Narrator: Until recently, no computer could come close, but since 2010, a big leap forward in a branch of A.I. called “machine learning” has come a long way to closing the gap.Daniela Rus: Machine learning, it’s about, uh, giving machines the ability to look at data, identify patterns and make predictions. Narrator: Even if the car can see and make sense of its surroundings with unmatched perfection, it could still be a lethal hazard if it fails to handle its third crucial task: planning; yet another daunting challenge, because the planning software has to anticipate what’s likely to happen, then plot the car’s pathway and speed, ready to change both in a split second if the sensors spot trouble.Just like the car’s perception software, its planning software also needs to be trained.

United States

Northern Mariana Islands

Puerto Rico

American Samoa

Guam

U.S. Virgin Islands

U.S. Minor Outlying Islands

US & Territories

Colossal explosions shake a remote corner of the Siberian tundra, leaving behind massive craters. In Alaska, a huge lake erupts with bubbles of inflammable gas. Scientists are discovering that these mystifying phenomena add up to a ticking time bomb, as long-frozen permafrost melts and releases vast amounts of methane, a potent greenhouse gas. What are the implications of these dramatic developments in the Arctic? Scientists and local communities alike are struggling to grasp the scale of the methane threat and what it means for our climate future. (Premiered February 2, 2022)

In the Arctic, enormous releases of methane, a potent greenhouse gas, threaten the climate.

Arctic Sinkholes

The top half of Jupiter in blue and green against a night sky

A composite image of Jupiter using images captured by the James Webb Space Telescope. Image Credit: NASA, ESA, CSA, Jupiter ERS Team; image processing by Judy Schmidt.

Explore the cosmos, delve into ancient history, and follow an extreme rescue with NOVA’s most-watched documentaries released in 2022.

NOVA’s most popular science documentaries of 2022

Four bright orange loops brand off of a dark blue blob

A transmission electron micrograph of HIV-1 virus particles (orange) replicating from the plasma membrane of an infected H9 T cell. Credit: NIAID, Flickr

Scientists have cured a handful of people of HIV by piggybacking on treatments they received for blood cancer. But does that bring a widespread cure any closer?

Three Tasks Driverless Cars Need to Learn

Funded By

Explore More

Look Who's Driving

Google's Self-Driving Car May Soon Be Considered a Legal Driver

Ethics and Self-Driving Cars

Transcript

Credits

Funded By

Explore More

Look Who's Driving

Google's Self-Driving Car May Soon Be Considered a Legal Driver

Ethics and Self-Driving Cars