Tag Archives: Transportation/Self-Driving

Virtual Car Sharing Combines Telepresence Robots and Autonomous Vehicles

Post Syndicated from Evan Ackerman original https://spectrum.ieee.org/cars-that-think/transportation/self-driving/virtual-car-sharing-combines-telepresence-robots-and-autonomous-vehicles

5G connectivity and a remotely projected human help autonomous vehicles be safer and more flexible

One of the remaining challenges for autonomous cars is figuring out a way to handle that long tail of weird edge cases that can randomly happen in the real world. Another challenge that remains is figuring out how to handle that huge population of weird beings called humans, who behave pseudorandomly in the real world. 

We’ve seen potential solutions to both of these problems. The first, meant to cover the long tail of situations that are outside the experience and confidence of an autonomous system, can involve a remote human temporarily taking over control of the vehicle. And with the right hardware, that human can solve the challenge of interacting with other humans at the same time.

One Driver Steers Two Trucks With Peloton’s Autonomous Follow System

Post Syndicated from Tekla S. Perry original https://spectrum.ieee.org/view-from-the-valley/transportation/self-driving/will-autonomous-following-be-a-game-changer-for-trucking

The technology is currently being tested on closed tracks, the company says

A host of companies are working to develop autonomous driving technology, but Silicon Valley startup Peloton has put its focus on autonomous following. The company today announced technology that uses computers, sensors, and vehicle-to-vehicle (V2V) communications to allow one driver to drive two separate trucks. 

Last year, Peloton began selling technology that enabled closer and safer truck platooning, using sensors, V2V communications, and automatic powertrain control and braking. That version of its product, Platoon Pro, requires a driver in the second truck to steer. The new version will take the second driver out of the equation.

Here’s how it works: In the front truck, the driver drives normally. Whenever he adjusts his foot on the throttle, touches the brakes, or maneuvers the steering wheel, digital details describing that action are wirelessly transmitted to the computer in the following truck. Using that information, along with data gathered from its own collection of radars, cameras, and other sensors, the second truck can safely trail close behind the first, forming a single-driver platoon.

The Self-Driving Car Is a Surveillance Tool

Post Syndicated from Mark Anderson original https://spectrum.ieee.org/cars-that-think/transportation/self-driving/surveillance-and-the-selfdriving-car

In the coming age of autonomous vehicles, users may have to pay extra to keep their whereabouts private

Most drivers today can still remember when GPS was provided by a portable device plugged into the car’s cigarette lighter and mounted on the windshield with a suction cup. But soon after the iPhone arrived, GPS (or Sat Nav for U.K. readers) became just another app.

Now, an American geography researcher is arguing that GPS’s transition from dedicated hardware to smartphone software was even more significant than we realize. He says mobile mapping apps also foreshadow the ultimate transformation of car companies from purely “hardware” manufacturers to hybrid hardware, software, and service providers.

With that tectonic shift, he says, will come another shift toward a transportation economy in which the prime commodity is not just the car, but also the driver (his example echoes a larger trend which the sociologist Shoshana Zuboff calls “Surveillance Capitalism”).

“What we have with smartphones is, now [GPS] data can be monetized in other ways,” says Luis Alvarez León, assistant professor of geography at Dartmouth College. “Information companies are providing the mapping service as an ancillary way of refining their search algorithms, of collecting more data about the consumers… [and] of repackaging it for other third parties.”

Ultrafast Motion-Planning Chip Could Make Autonomous Cars Safer

Post Syndicated from Evan Ackerman original https://spectrum.ieee.org/cars-that-think/transportation/self-driving/realtime-robotics-motion-planning-chip-autonomous-cars

Realtime Robotics’ motion-planning processor helps autonomous cars make better decisions

About two years ago, we covered a research project from Duke University that sped up motion planning for a tabletop robot arm by several orders of magnitude. The robot relied on a custom processor to do in milliseconds what normally takes seconds. The Duke researchers formed a company based on this tech called Realtime Robotics, and recently they’ve been focused on applying it to autonomous vehicles.

The reason that you should care about fast motion planning for autonomous vehicles is because motion planning encompasses the process by which the vehicle decides what it’s going to do next. Making this process faster doesn’t just mean that the vehicle can make decisions more quickly, but that it can make much better decisions as well—keeping you, and everyone around you, as safe as possible.