UPDATED 14:28 EDT / DECEMBER 19 2016

EMERGING TECH

Out of the warehouse, onto the street: Seegrid maps another route to self-driving cars

Seegrid Corp.’s vision-guided autonomous vehicles have been working alongside humans in the manufacturing industry – think of them as driverless pallet trucks – for 13 years now. Now, the company is looking at moving its Vision technology toward the broader self-driving car industry.

Pittsburgh-based Seegrid’s vehicles for industrial markets differ from the traditional automated guided vehicles, or AGVs, because the former require cumbersome infrastructure changes for manufacturers. Whereas AGVs followed paths laid down with tape or wires, Seegrid’s vision-guided vehicles, or VGVs, use only cameras and computers.

The Vision technology provides depth perception much like human eyes: It sees, records the route and then recognizes the space where it has been when it travels again. The algorithm in the system can analyze the chances of something getting in its way, much like people do when they walk around a busy area such as a warehouse. This technology is currently being used by companies such as BMW, Jaguar and Whirlpool, which has 54 Seegrid self-learning vehicles on its warehouse floors.

Seegrid now hopes to leverage that technology to guide self-driving cars. Seegrid has already logged around 500,000 incident-free miles in distribution centers and factories, with autonomous vehicles driving alongside humans in complex environments. “In 2017, we are aiming to expand our initial prototypes and further test the applicability of cameras on consumer cars,” Jeff Christensen, vice president of products and services at Seegrid, said in an interview with SiliconANGLE.

In 13 years, he said, Seegrid’s autonomous vehicles have navigated a steep learning curve in an industry with very strict regulations regarding worker safety. It now hopes to partner with auto equipment manufacturers and automakers to sell them its patented vision and evidence grid technology.

capture

A number of sensing technologies are already being tried out by various companies in the self-driving car market. Uber has a $250,000 multi-sensory unit. Tesla has eight monocular cameras around the perimeter of the car, while the Google vehicles have a LiDAR (Light Imaging, Detection, And Ranging) unit on the roof.

Seegrid believes it has something new to offer in the milieu of guiding vehicles. “Seegrid has tested and explored different manners of machine vision, and we’re confident in stereo vision combined with evidence grids,” said Christensen. “Cameras outpace all the other sensors combined by several orders of magnitude when you look at core density of the captured data.” Moreover, he said, cameras are solid-state systems, unlike LiDAR units, which continually rotate to collect information and are therefore more vulnerable to wear over time.

It’s like your two eyes working together, said Christensen: Stereo cameras provide accurate depth of vision even if the vehicle isn’t moving. “By taking two separate pictures and comparing the subtle differences, our vehicles can make precise determinations about their changing environment,” he said.

Understandably, most people don’t think of forklift trucks when they envision autonomous vehicles. Our minds are preset to thinking of today’s limited vehicles tentatively taking to the streets or a fully autonomous car far off in the future. Seegrid envisions the two coming together in harmony in a not-too-distant future.

“With Uber, Intel and others investing heavily in the driverless car space, Vision is the natural progression for autonomous navigation technology,” Christensen said. Seegrid’s initial testing and prototypes applying Vision technology to consumer cars are starting to bear fruit.

Seegrid sees itself as no longer limited to the factory, an environment where robots were maneuvering vehicles long before the city streets. “Now is the time,” said Christensen, “to introduce the driverless car industry to a technology that has been navigating autonomously for years.”

Photos courtesy of Seegrid

A message from John Furrier, co-founder of SiliconANGLE:

Your vote of support is important to us and it helps us keep the content FREE.

One click below supports our mission to provide free, deep, and relevant content.  

Join our community on YouTube

Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.

“TheCUBE is an important partner to the industry. You guys really are a part of our events and we really appreciate you coming and I know people appreciate the content you create as well” – Andy Jassy

THANK YOU