Home Transports WaveSense’s Innovative Radars Could make Autonomous Vehicles Safer

WaveSense’s Innovative Radars Could make Autonomous Vehicles Safer

Autonomous cars from Google spinoff Waymo, GM’s Cruise Automation, and Uber among other brands use various components including cameras, lidar, and radar to make sense of their environment.

Nevertheless, Tarik Bolat, the CEO of WaveSense, is convinced that such systems have a blindspot.

According to Bolat, there is a looming massive transformation in mobility and transportation across the globe, especially as the autonomous driving systems become better at an exceptional pace.

However, he said that before the widespread adoption of self-driving cars can commence, reliability and navigation safety have to be improved considerably. Such upgrades will allow self-driving cars to combat adverse weather conditions such as fog, snow, and rain.

WaveSense ’s ground-penetrating radars(GPR) are set to make self-driving cars safer. They utilize a 12-element antenna array in sending very high-frequency electromagnetic pulses up to a maximum of 10 feet underneath the ground.

In turn, the waves reflect off of underground elements such as dirt, roots, pipes, and rocks. This ability allows the creation of a base map that an onboard computer can correlate into a 3D, GPS-tagged subterranean database.

The radars have the potential to penetrate snow, dust, fog, and rain, which makes them suitable for dealing with inclement weather.

What’s more, they can use WaveSense’s algorithm and underground maps to pinpoint a vehicle ’s location when in motion. These radars may one day be utilized in alerting municipalities when roads require maintenance.

The technology used by WaveSense was drawn from Massachusetts Institute of Technology’s Lincoln Laboratories, specifically for the US Department of Defense.

At the university, it was developed for those military vehicles that were deployed in areas with nonexistent or poor road markings.

Lincoln Laboratory researchers went ahead to commercialize the tech in 2016, when they showed that a sports utility car fitted with the system could remain within centimeters of its track, primarily on a road that was freshly covered with snow.

According to Bolat, WaveSense is not calling for the replacement of existing systems like cameras, lidar and radar by GPR. Instead, he acknowledged their excellent job when it comes to object detection and mapping tasks.

The company is positioning its GPR solution as a complement to the already existing sensors as well as a plan B for when such systems fail, for instance, in heavy rains, dust storms, sand, and fog.

Bryon Stanley, WaveSense’s CTO and co-founder, said that the GPR technology successfully used in protecting the US troops in Afghanistan from risky situations would expedite the commercialization of self-driving cars.

He added that the technology would minimize civilian self-driving car fatalities considerably.

Even with GPR’s advantages, the technology may not be an easy sell. In fact, getting the kind of localized tracking set up in major cities that Bolat describes would be a huge undertaking since each road would require individual scanning.

Additionally, there are competing solutions that exist in various forms such as NIRA Dynamics’ Road Surface Information, which utilizes machine learning algorithms to bring together data from car camera feeds, controllers, sensors as map layers.

Source VentureBeat

Subscribe to our newsletter

Signup today for free and be the first to get notified on the latest news and insights on artificial intelligence

KC Cheung
KC Cheung has over 18 years experience in the technology industry including media, payments, and software and has a keen interest in artificial intelligence, machine learning, deep learning, neural networks and its applications in business. Over the years he has worked with some of the leading technology companies, building and growing dynamic teams in a fast moving international environment.
- Advertisment -


AI Model Development isn’t the End; it’s the Beginning

AI model development isn’t the end; it’s the beginning. Like children, successful models need continuous nurturing and monitoring throughout their lifecycle. Parenting is exhilarating and, if...