Collaborating Authors

Digging into Autonomous Truck Tech on HDT Talks Trucking Podcast


Vijaysai (Vijay) Patnaik, the Product Lead for Waymo's self-driving trucks program, tells HDT Talks Trucking podcast host Jim Park that he's confident the company will be able to safely and responsibly deploy this technology on public roads. These special reports are mid-season special-interest podcasts covering a single topic from several perspectives. He says he's confident the company will be able to safely and responsibly deploy this technology on public roads. In the interview, Vijay explains some of the intricacies of the autonomy that controls the trucks and how it interacts with other road users. He talks about how the autonomy handles some unique situations, and how public perceptions of the technology are changing for the better.

Waymo open-sources data set for autonomous vehicle multimodal sensors


Waymo, the Alphabet subsidiary that hopes to someday pepper roads with self-driving taxis, today pulled back the curtains on a portion of the data used to train the algorithms underpinning its cars: The Waymo Open Dataset. Waymo principal scientist Dragomir Anguelov claims it's the largest multimodal sensor sample corpus for autonomous driving released to date. "[W]e are inviting the research community to join us with the [debut] of the Waymo Open Dataset, [which is composed] of high-resolution sensor data collected by Waymo self-driving vehicles," wrote Anguelov in a blog post published this morning. "Data is a critical ingredient for machine learning … [and] this rich and diverse set of real-world experiences has helped our engineers and researchers develop Waymo's self-driving technology and innovative models and algorithms." The Waymo Open Dataset contains data collected over the course of the millions of miles Waymo's cars have driven in Phoenix, Kirkland, Mountain View, and San Francisco, and it covers a wide variety of urban and suburban environments during day and night, dawn and dusk, and sunshine and rain.

Google's self-driving car project buys British AI firm Latent Logic

The Guardian

It was founded in 2017 by the academics Shimon Whiteson and João Messias. Waymo hopes the company's expertise can be put to use teaching AI drivers how to deal with complex behaviour such as a car cutting off another at a roundabout, a pedestrian emerging from a parked car, or a cyclist skidding in rain. The Alphabet subsidiary is also intending to use its new base in Oxford to build a second pool of AI talent outside its headquarters in Mountain View, California. The UK is a world leader in AI research, including autonomous vehicles, and many talented researchers will not or cannot relocate to the US – no matter how deep the recruiter's pockets. Whiteson, who will continue to work as a professor of computer science at Oxford, added: "By joining Waymo, we are taking a big leap towards realising our ambition of safe, self-driving vehicles. In just two years, we have made significant progress in using imitation learning to simulate real human behaviours on the road. I'm excited by what we can now achieve in combining this expertise with the talent, resources and progress Waymo have already made in self-driving technology."

Waymo and Uber propose AI techniques to improve self-driving systems


During a workshop on autonomous driving at the Conference on Computer Vision and Pattern Recognition (CVPR) 2020, Waymo and Uber presented research to improve the reliability -- and safety -- of their self-driving systems. Raquel Urtasun, chief scientist at Uber's Advanced Technologies Group, demonstrated a pair of technologies that leverage vehicle-to-vehicle communication for navigation, traffic modeling, and more. It learns 3D geometry from image sequences -- i.e., frames captured by car-mounted cameras -- by exploiting motion parallax, a change in position caused by movement. Given a pair of images and lidar data, ViDAR can predict future camera viewpoints and depth data. According to Anguelov, ViDAR uses shutter timings to account for rolling shutter, the camera capture method in which not all parts of a scene are recorded simultaneously. Along with support for up to five cameras, this mitigating step enables the framework to avoid displacements at higher speeds while improving accuracy.

Waymo Doesn't Want to Put On a Show


The company insists it will not be rushed. That's a glaring contrast to Uber's hard-charging efforts, which skidded to a halt after one of its self-driving test cars killed pedestrian Elaine Herzberg in Tempe, Arizona, in 2018. It's also notably different from Tesla, which incrementally updates its "Autopilot" software for cars that are already on the road, while casually reminding drivers that "Autopilot" doesn't mean the car is fully autonomous. Waymo's more measured approach could indeed be a savvy move: The Edelman Trust Barometer shows that consumer confidence in autonomous vehicles is low. In this year's edition of the survey, only 54 percent of respondents in 27 markets worldwide said they trust AVs.