At present, the environment awareness technology of self-driving cars is mentioned. Many people think of laser pointer radar first. indeed. Compared with vehicle sensors such as cameras and millimeter wave radars. Lidar has the advantages of high precision and high resolution, and has been widely carried on many autonomous driving test vehicles. But this technology also has its shortcomings that cannot be ignored-high cost, such as Ibeo's LUX 4-line lidar, the price is as high as 15,000 dollars. Although Google announced at the beginning of the year that its self-developed lidar can reduce costs by 90%. Each set still costs $ 7,500. Such a high price is obviously unrealistic for self-driving cars that will eventually be commercialized.
Therefore, in addition to the existing green laser pointer radar solution. How to find a lower-cost environment-aware solution has become a concern for many companies. In response to this problem, in the fourth APEC car networking seminar held recently, Academician Gao Wen from the Chinese Academy of Engineering gave his answer-visual navigation. In his view, no matter how enterprises optimize the cost of lidar. If you want to reduce its price to, for example, $ 1,000 or even lower-after all, this price is reasonable for mass-produced cars, and they all face greater challenges. In comparison, the "camera + software" visual navigation technology is easier to achieve.