Menu

AUTONOMOUS VEHICLE FEATURE NEWS

Edge Case Research and Kaarta Accelerate Autonomous Vehicle Safety

By Ken Briodagh April 05, 2018

According to a recent announcement, Edge Case Research (ECR), an autonomous vehicle safety company, is collaborating with Kaarta, real-time 3D reality capture developer, on autonomous vehicle road testing. ECR reportedly has kicked off an initiative to map Pittsburgh’s streets using Kaarta 3D mapping and localization technology.

These maps will inform the pilot of ECR’s Hologram platform, a tool designed to maximize the value of every mile by using each recorded scenario as a test case for real executions. Hologram will, if all goes according to plan, intelligently and quickly identify issues for manufacturers, enabling them to improve testing and time to market for safe autonomous vehicles.

Autonomous vehicle companies are currently reporting miles driven and number of disengagements as metrics to demonstrate safety, but ECR says that even billions of simulation miles won't necessarily expose cars to realistic life-threatening situations. Hologram consumes data recorded during field testing and then uses that real-world data to generate potential edge-case scenarios by adjusting variables like lighting, weather effects, and the location of cars and pedestrians. By combining these factors, Hologram automatically produces and tests realistic scenarios in order to validate the safety of autonomous perception systems.

“Safe perception is critical for safe autonomous vehicles, and that’s why we’re building Hologram,” said Michael Wagner, CEO, Edge Case Research. “Hologram’s ability to create millions of unique test cases in a given street or environment means that developers of perception systems can train and validate their machine learning systems far more efficiently.”

Using Kaarta technology to collect data of Pittsburgh’s bustling downtown, Hologram has successfully identified cases in which leading pedestrian-detection algorithms lose track of people crossing the street. The City of Pittsburgh’s unique and challenging urban environment is the only urban location designated by the U.S. Department of Transportation as an automated vehicle proving ground.

“Kaarta’s mapping technology turns raw sensor data into intelligent 3D environment models in real time,” said Kevin Dowling, CEO, Kaarta. “These models provide high dimensional fidelity of the real world for immediate testing. This work ECR and Kaarta are doing is proving to be very fruitful for both companies and for the autonomous vehicle industry as a whole.”


Ken Briodagh is a writer and editor with more than a decade of experience under his belt. He is in love with technology and if he had his druthers would beta test everything from shoe phones to flying cars.

Edited by Ken Briodagh

Editorial Director

SHARE THIS ARTICLE
Related Articles

Edge Case Research and Kaarta Accelerate Autonomous Vehicle Safety

By: Ken Briodagh    4/5/2018

ECR delivers on commitment to safety with Hologram, an intelligent testing platform to prepare autonomous cars for the road.

Read More

Continental Uses IoT to Make Truck Tires Intelligent

By: Ken Briodagh    4/5/2018

Continental leverages Vodafone's Internet of Things (IoT) for connected truck tires, collecting tire data whenever trucks return to the fleet terminal…

Read More

IoT Events Feature Healthcare, Smart City, Autonomous Vehicles and IIoT

By: Ken Briodagh    3/26/2018

The IoT is expanding in hundreds of new vertical directions, and upcoming events are focusing on some of the hottest: Smart City IIoT, Autonomous Vehi…

Read More

Globalstar Launches Automotive Team to Connectivity to Autonomous Vehicles

By: Ken Briodagh    3/14/2018

Company to Leverage Existing Global Network for Safety Services, Delivery of Over-the-Air Updates and Enhanced Navigation and Mapping

Read More

What challenges will the automotive sector face in 2018?

By: Special Guest    3/1/2018

Everyone involved in the automotive sector, wherever they are in the world, has set their sights on the same target: the autonomous car.

Read More