Uber starts self-driving car pickups in Pittsburgh (Part 2)

Home > News > Content

【Summary】Uber starts self-driving car pickups in Pittsburgh

Shelly    Sep 17, 2016 6:00 PM PT
Uber starts self-driving car pickups in Pittsburgh (Part 2)

Planning for the unexpected

The autonomous Ford Fusions that Uber is now dispatching to riders appear to be, for the most part, regular cars. The most noticeable difference is an array of sensors that jut out of their roof. Additional sensors are integrated into the cars' sides.

A Lidar unit uses a laser to collect 1.4 million map points a second, resulting in a 360 degree image of the car's surroundings. Cameras and a GPS system add additional intelligence.

I came away from my ride trusting the technology. The self-driving car detected obstacles, people and even potholes, and responded intelligently. The expected is already mundane. The bigger challenge for Uber is planning for the unexpected.

Uber is first offering autonomous pickups in a few Pittsburgh neighborhoods. Within a few weeks, it will expand to the airport and a northern suburb. The slow rollout is because Uber pre-maps the roads its cars travel — a practice Carnegie Mellon University researcher Aaron Steinfeld, who is unaffiliated with Uber, assured me is totally normal. The cars receive pre-collected maps that include speed limits and other generally applicable information so they can focus on real-time detection of variables like pedestrians.

Uber logs each of its road tests and uses the data to tweak how the cars should respond in specific situations. For example, the cars know that when they arrive at a four-way stop they should drive on in order of when they arrived. But what happens when another car fails to respect that order? It knows it should stop if another car jumps the gun, but it should also know to go if another car takes too long.

Humans still abide by many social cues when they're driving. They make eye contact with other drivers and can read the subtle body language of a jogger that says they are thinking about cutting across the street. Uber's cars can predict the likelihood that a pedestrian is about to cross the road, but reading actual social cues is still just a goal.

The company plans to switch to one ride-along engineer within the next six months. Eventually, the final engineer could be replaced by a remote help center; when a car encounters a foreign situation, it contacts a human in the center for help. Uber is also researching how to prevent accidental gridlock situations and how cars should behave when there are many pedestrians in the street.

Pittsburgh's open door

Uber came to Pittsburgh for its engineering talent. Carnegie Mellon is home to a famed robotics program that has produced members of autonomous vehicle teams all over the country.

The city was quick to offer its support, too. Mayor William Peduto is an Uber rider and said the city is open to innovative companies that can bring new services and jobs to the city.

"Pittsburgh and, in particular, Carnegie Mellon University have been leaders in autonomous vehicle research for decades and this is a logical next step," Peduto said. "Under state law, automated vehicles are allowed on Pennsylvania streets as long as there is a licensed driver behind the wheel, as there will be in the Uber rollout."

Even the Uber driver who brought us to the event seemed intrigued. She wondered if she might become a self-driving car handler during the testing phase.

A few Uber employees mentioned weather as another perk for testing in Pittsburgh. While Google's cars cruising around Silicon Valley might only see the occasional rain, Pittsburgh has four seasons. It's also an old city with an irregular grid, bridges and lots of potholes.

"We like to call Pittsburgh the double black diamond of driving," ATC's Krikorian said. "If we really can master driving in Pittsburgh, then we feel strongly that we have a good chance of being able to master it in most other cities around the world."

A litmus test

At no point did Uber suggest the current technology found in its cars is ready to roll out to the masses. Like Google, Carnegie Mellon and many other labs developing self-driving technology, it is carefully logging hours and hours of road tests. Its team is slowly working its way through a long list of scenarios its cars should be prepared to respond to in the wild.

"No amount of simulation captures everything, and that's why it's important to drive on the road a lot. The Google cars collected a lot of road data at this point," Steinfeld said. "This heavy-duty testing where you conduct your research in the field in real life is a tradition … what you see comes from here in the robotics institute."

The question that will be answered rapidly is how the public responds. The drivers encountering the 14 Ford Fusions — just a part of Uber's self driving army — on the road did not opt into the experience of driving next to a robot. Uber's users can opt in to hailing an autonomous vehicle, but they are likely to be new to the experience. Still another question is how Uber drivers will feel. Maybe they'll become a ride-along engineer, or maybe they will have their job taken away.

Steinfeld noted this is the first time the world has seen such a large fleet in one city. Awareness and interest will run high enough to potentially shift public perception.

"Autonomy — typically people are a little bit nervous about it," Steinfeld said. "But once they experience it they tend to build up familiarity and become accepting of it. This experience here in Pittsburgh might give us a societal understanding of people's acceptance of autonomy across the country."

resource from: Techcrunch

Prev                  Next
Writer's other posts
    Related Content