What do sensors mean to autonomous driving?

2020-11-17

The invention of the automobile has brought convenience to people's lives. In recent years, with the continuous expansion and deepening of the application fields of artificial intelligence technology, autonomous driving has gradually entered the public's field of vision. In the eyes of consumers, driving has become an easy task. In the research and development of autonomous driving technology, choosing whether to use lidar or cameras as the main sensor is the primary problem to be solved. They represent two completely different systems—laser SLAM and visual SLAM.

In-vehicle cameras are the basis for realizing numerous warning and identification ADAS (Advanced Driver-Assistance Systems) functions. Among numerous ADAS functions, the visual imaging system is relatively basic and more intuitive for drivers, and the camera is the basis of the visual imaging processing system.

Many functions such as lane departure warning, forward collision warning, traffic sign recognition, pedestrian collision warning, and driver fatigue warning can be realized with the help of cameras; some functions can only be realized through cameras. In addition, cameras can not only capture images in high resolution but also better classify objects. So what are their shortcomings? "The data depth of the camera is not as good as that of lidar." Magney said.

With the popularity of autonomous driving, lidar has received unprecedented attention. Lidar (Light Detection And Ranging) combines laser, GPS (Global Positioning System), and inertial measurement units. It can distinguish between real moving pedestrians and posters of people, model in three-dimensional space, detect static objects, and accurately measure distances. Its working principle is also easy to understand. It is a radar system that uses laser beams to detect the position, speed, and other characteristic quantities of the target, with advantages such as high measurement accuracy and precise direction.

In the ADAS system, lidar obtains the position and movement speed of the target object through lenses, laser emission and receiving devices, based on the TOF (Time of Flight) principle, and transmits it to the data processor; at the same time, the speed, acceleration, and direction of the vehicle will also be transmitted to the data processor through the CAN bus.

Then, the data processor comprehensively processes the information data of the target object and the vehicle itself and issues corresponding passive warning instructions or active control instructions according to the processing results to realize the auxiliary driving function. Currently, mainstream lidar in the market or autonomous driving projects accounts for about 90% of the applications in autonomous driving projects. Autonomous vehicles developed by companies such as Google, Audi, Ford, and Baidu basically use lidar. In addition, according to the number of wire harnesses, lidar can be divided into single-beam lidar and multi-beam lidar. Single-beam lidar is mainly used to avoid obstacles, and it is very accurate in testing the distance and accuracy of surrounding obstacles, but single-beam lidar can only perform planar scanning and cannot measure the height of objects; multi-beam lidar makes up for the shortcomings of single-beam lidar, bringing qualitative changes in dimension enhancement and scene restoration, and can identify the height information of objects.

It is understood that the main ones currently launched internationally are 4-line, 8-line, 16-line, 32-line, and 64-line. Multi-line lidar is mainly used for automotive radar imaging.

The consensus in the industry is that the sensors used for autonomous driving control are either cameras or lidar, but the question of which one to use is still under debate. Some believe that the two are not so opposed; each technology has its own advantages and disadvantages, and complementing each other is a relatively achievable route at this stage. From a deeper perspective, the choice of sensor is actually a question of the choice of autonomous driving route. If autonomous driving is personified, then lidar is basically unnecessary. The vehicle can complete the dynamic judgment of the surrounding environment and vehicle control based on its own knowledge base and rule base.

Some believe that the issue between the two is which one is more emphasized in the actual industry development. Taking Tesla as an example, it focuses on cameras and millimeter-wave sensors. However, due to the frequent accidents of Tesla, more and more companies have begun to question this relatively low-cost and easy-to-promote method. In addition, the media reported that Tesla has started testing Model series equipped with lidar in North America. Autonomous driving is a systematic project, and sensors are indispensable and cannot work independently. Only based on realistic perfect cooperation can autonomous driving go faster and farther.

The effect of surface treatment of foil materials on the peel strength of different adhesives

Development trends of the nine-axis sensor market: multi-axis sensors

More news

喜迎国庆 · 盛世华诞｜楠华科技2026国庆节放假通知

秋分丨风吹一片叶万物已惊秋