Daimler and Bosch Will Launch a Pilot Robotaxi Program in San Jose in 2019

I don't know the way in San Jose, my car has a brain and won't go wrong and lose its way

2 min read
A gray car with a slogan 'Urban Automated Driving' printed on the side is shown in motion on a road.
San José will be the pilot city for Daimler and Bosch's automated on-demand ride-hailing service.
Photo: Daimler

Daimler and Bosch say they’ll offer a self-driving ride-hailing service to selected users in part of San Jose, beginning in the second half of 2019.

The service resembles the one that Waymo’s been conducting for a year in Chandler, a suburb of Phoenix, Ariz. Waymo has already begun to experiment with charging a fee for the service, although only pre-selected users are allowed to pay it. That means it isn’t quite commercial yet, though that step is expected to follow in 2019.

And, although San Jose is a much larger town than Chandler, those Mercedes robotaxis will ply only a main corridor and some nearby areas. In a word, they’ll be heavily geofenced. Other constraints, such as the time of day and the state of the weather, may also be added, Bernhard Weidemann, a spokesman for Daimler in Stuttgart, tells IEEE Spectrum. Such constraints would be relaxed later on, as the pilot program progresses.

General Motors subsidiary GM Cruise is also slated to start a commercial pilot in 2019, a commitment that chairman Mary Barra recently reiterated. And just last week, Volkswagen and Intel’s robocar subsidiary Mobileye announced that in 2019 they will begin an experimental pilot program in Israel, apparently in Tel Aviv.

The Daimler-Bosch project will be based on a top-of-the-line Mercedes-Benz S class car modified with sensors, including lidar. It will do most of the processing on a Nvidia Drive Pegasus chipset, augmented by hardware from Bosch and using algorithms that Daimler and Bosch are already developing together in a pilot in Germany. Some of the sensors may also be sourced from third parties. The high-definition mapping will be supplied by Here, a company in which Daimler is a major stakeholder.

GM Cruise plans on basing its service on a Chevrolet Bolt that’s had the steering wheel removed. I asked Weidemann if the Mercedes S class will come that way, too.

“For the pilot phase, we will have a steering wheel,” he says, sounding a little surprised by the question. “The safety driver needs to take control if something goes wrong.”

The Conversation (0)

Self-Driving Cars Work Better With Smart Roads

Intelligent infrastructure makes autonomous driving safer and less expensive

9 min read
A photograph shows a single car headed toward the viewer on the rightmost lane of a three-lane road that is bounded by grassy parkways, one side of which is planted with trees. In the foreground a black vertical pole is topped by a crossbeam bearing various instruments. 

This test unit, in a suburb of Shanghai, detects and tracks traffic merging from a side road onto a major road, using a camera, a lidar, a radar, a communication unit, and a computer.

Shaoshan Liu

Enormous efforts have been made in the past two decades to create a car that can use sensors and artificial intelligence to model its environment and plot a safe driving path. Yet even today the technology works well only in areas like campuses, which have limited roads to map and minimal traffic to master. It still can’t manage busy, unfamiliar, or unpredictable roads. For now, at least, there is only so much sensory power and intelligence that can go into a car.

To solve this problem, we must turn it around: We must put more of the smarts into the infrastructure—we must make the road smart.

Keep Reading ↓Show less