Why does lidar limit the development of autonomous driving?

In the past two years, the concept of autonomous driving has swept the automotive industry, and software technology has advanced by leaps and bounds. However, the rapid progress of the industry is encountering hardware bottlenecks - Lidar, one of the core hardware of the autonomous driving system, is slowing down the wheels of autonomous driving because of its high cost and limited capacity.

In the autonomous driving industry, despite the controversy, the mainstream still believes that laser radar is the most important component to achieve automatic vehicle driving. The device receives and processes the reflected laser signal by actively emitting a laser beam to draw a 3D image of the surrounding environment in the form of a "point cloud." Many self-driving test vehicles, including Google, Uber, and Toyota, rely heavily on laser radar to locate high-precision maps and distinguish pedestrians and other vehicles. The best performing Lidar is capable of centimeter accuracy over distances of over 100 meters.

Timg (4) copy

Point cloud data formed by lidar

Most companies that are aggressively commercializing super-automatic driving believe that laser radar is essential. (Except for the aggressive Tesla, they only use cameras and radars.) Because the radar's ability to detect details is not strong, the camera does not perform well under low light or strong light conditions. Tesla’s death last year was due to the fact that Autopilot could not distinguish between reflective trailers and bright skies, resulting in the Model S rear-end trailer. Ryan EusTIce, Toyota's vice president, said whether laser radar should be used in a more conservative and safer autopilot system is still "a problem."

However, the development of autonomous driving is very fast, and this emerging industry is facing a problem - the laser radar is dragging its legs. Lidar was previously a small share of the business, and the technology is not mature enough to make millions of cars standard.

If we look at the prototype car that is now self-driving, it's easy to spot the problem: the lidar is too cumbersome. Google, Uber, and Toyota's test heads are all bearing this huge, non-stop spinning thing.

In addition to the volume problem, lidar is expensive, with a single cost of thousands or even tens of thousands of dollars. Most test vehicles are equipped with multiple laser radars. Although the number of test vehicles on the road is not large, the satisfaction of the demand has become a problem. The InformaTIon reported last week that the capacity of the laser radar manufacturer has forced downstream companies to wait until the first half of the year to get the product.

These may partly explain Waymo’s lawsuit against Uber last month. Waymo said there is evidence that Anthony Levandowski, the company's former top engineer, stole Waymo's lidar design before resigning to create autopilot truck company Otto.

When I visited Otto last year, Otto co-founder Lior Ron told me that Otto's sensors were made by themselves because there were no products on the market that could meet the needs of 18-wheel trucks. Now, Waymo says that Otto's technology is actually developed by itself. Waymo's team has invested tens of millions of dollars in this technology, achieving a 90% reduction in laser radar costs while improving performance.

Timg (1) copy

Better laser radar is a core part of Waymo's automated driving commercialization program. The company has developed three different types of laser radars. Waymo also said that a series of important technologies including laser radar will be licensed to automakers in the future.

Waymo is not the only company that has spent huge sums of money to solve the lidar problem. Last year, Ford and Baidu jointly invested $150 million in Velodane, the leading manufacturer of laser radar. The latter is building a large plant in San Jose, Silicon Valley to expand capacity, and plans to start producing laser radars next year.

However, many in the autonomous driving industry believe that Lidar needs to be redesigned for practical use. Velodyne is currently working on solid-state laser radar, so that the laser radar can complete the coverage of the road without rotating it. (Translator's Note: Velodyne has not yet launched a full-scale solid-state laser radar, which is half the product closer to this form. Solid state laser radar PUCK). Lidars that work in solid form are much cheaper, smaller, and more rugged because they don't have mechanical parts that need to drive the radar to rotate.

Velodyne announced last year that their project has made a breakthrough, allowing the price of lidar to reach $50, but did not disclose when to mass-produce this solid-state lidar. Another startup, focusing on solid-state lidar, which received $90 million in financing last year, announced that it will begin production of solid-state lidar at its Massachusetts plant this year for $250, but its performance is unclear. . Auto parts suppliers Continental and Valeo are also developing similar technologies, but they say it will take two or three years to go public.

A number of automakers, including Ford and BMW, said they hope to get autonomous vehicles on the road in 2021. These laser radars under development will greatly affect the performance, cost, and appearance of future autonomous vehicles.

This article is compiled by wise things

2-Piece Fixing Ties with Fir Tree

2-Piece Fixing Ties With Fir Tree,Fir Tree Mount Cable Tie,Wire Ties With Loops,Push Mount Zip Tie

Wenzhou Langrun Electric Co.,Ltd , https://www.langrunele.com

Posted on