Follow
Subscribe

Velodyne CTO Explains Features of the New High-Resolution VLS-128 LiDAR

Home > News > Content

【Summary】Velodyne, an industry leader in LiDAR technology has announced its latest product, the VLS-128 high resolution LiDAR for autonomous vehicles. FutureCar reached out to Velodyne's CTO Anand Gopalan, who provided some more information about the company’s latest LiDAR for self-driving cars.

Original Eric Walz    Dec 07, 2017 6:04 PM PT
Velodyne CTO Explains Features of the New High-Resolution VLS-128 LiDAR
author: Eric Walz   

SAN JOSE, Calif., — Velodyne, an industry leader in LiDAR technology has announced its latest product, the VL-128 high resolution LiDAR for autonomous vehicles. LiDAR is a radar technology essential to self-driving cars. Using LiDAR, a self-driving cars can "see" its surroundings, including other cars and pedestrians.

FutureCar was eager to learn more about Velodyne's new VLS-128 LiDAR, so we reached out to Velodyne CTO Anand Gopalan, who offered to answer some of our questions about the company's latest LiDAR for self-driving cars.

How LiDAR Works

LiDAR, an acronym for Light Detection And Ranging, is a surveying method that measures the distance of an object by using a pulsed laser beams. LiDAR bounces a laser off an object at an extremely high rate millions of laser pulses every second—and measures how long the laser takes to reflect off that surface. This generates a precise, three-dimensional image of the object, whether it's a vehicle, tree, pedestrian, or the road ahead.

Combined with machine learning and AI, LiDAR can help a self-driving car navigate. LiDAR is accurate enough to see which way pedestrians are facing at an intersection. From there, Machine learning algorithms can be used to predict which direction a pedestrian is likely to walk, to plan a safe path for the vehicle.

Support for Level 4 and 5 Autonomy

Gopalan explained that the Velodyne VLS-128 was built specifically for level 4 and 5 autonomous driving. The VLS-128 was also designed with direct input from automakers. "The VLS-128 was developed using the feedback from customers who are using our LiDAR in the field." Gopalan said. A Level 4 and 5 autonomy designation mean that an autonomous vehicle needs minimal or no human intervention.

Level 4 vehicles are designed to perform all safety-critical driving functions and monitor roadway conditions for an entire trip. Although  it's important to note that this is limited to the "operational design domain (ODD)" of the vehicle, which means it does not cover every driving scenario. An example is if the car was traveling off road in an unmapped region.

Level 5 autonomy refers to a fully-autonomous system that expects the vehicle's performance to equal that of a human driver, in every driving scenario, including extreme environments like dirt roads that are unlikely to be navigated by driverless vehicles in the near future.

Velodyne Supplied LiDAR for Google's Self-Driving Car Project

Velodyne was an early supplier of LiDAR to Google —now called Waymo— for its self-driving car project when it started back in 2009. Since then, the company has grown to supply Ford, Mercedes Benz, Volvo,Uber and others with LiDAR for their autonomous driving development projects. Gopalan declined to name any specific automotive partners for the VLS-128, however he did say that Velodyne is currently sending engineering samples to key automotive customers.

We asked Velodyne what are some of the advantages and advances in resolution between the company's 64 and 128 LiDARS. Gopalan said that the VLS-128 offers three times the resolution of the HDL-64, with more than doubles the range. This extra resolution is made possible by doubling the amount of individual lasers which are used to create a detailed map of the self-driving vehicles surroundings.

VLS-128 to HDL-64 comparison.jpg

Improved resolution of the VLS 128 (top) versus the HLD-64 (bottom)

We asked Gopalan what are some advantages of the VLS-128 versus a solid-state LiDAR. "The VLS-128 is able to deliver 2.1M data points in single return mode and 8.4M in quad return mode." he said. Additionally, the VLS-128 has a 300 meter range, and a vertical field of view of 40 degrees.

Gopalan said that the VLS-128 provides a 360 degree view combined with higher resolution. Solid-state LiDAR (SSL) has no moving parts, however these smaller units produce a lower resolution, and do not yet offer complete 360 degree coverage around a vehicle. However, using multiple SSL's, each of the 120 degree field of view can be stitched together for complete coverage around a vehicle. These smaller LiDAR units are currently used to supplement a higher resolution, roof-mounted LiDAR.

"The VLS-128 gives you a full 360 degree field of view and ultra-high resolution all at once, so it's meant to solve for all possible use cases in autonomous driving. It should be augmented with narrow field of view sensors such as Velarray for supplemental functionality." Gopalan said.

The Velarray is one of Velodyne's smaller, less expensive LiDAR units, designed to be embedded into a car's from or rear bumper. Data from the Velarray can be combined with that of a roof-mounted VLS-128. This setup provides a 360 degree view around the vehicle that supports higher levels of autonomous driving.

Velodyne LiDAR, Inc. Founder and CEO David Hall invented the 360-degree solid-state hybrid LiDAR ten years ago to use and sell in the Darpa Grand Challenge. He designed and sold the HDL-64 LiDAR, which since then became the standard LiDAR for the autonomous car industry.

The HDL-64 can be spotted on top of most autonomous cars driving on the roads, especially in Silicon Valley. The first autonomous cars were equipped with the company's HDL-64.

The VLS-128, with its higher resolution, is expected to be become an essential LiDAR for automakers and autonomous driving development.

Velodyne has not disclosed the price of the new LiDAR.

Prev                  Next
Writer's other posts
Comments:
    Related Content