As the most indispensable sensor in autonomous driving, the camera can distinguish the size and distance of obstacles, recognize pedestrians, lane markings, traffic signs, etc., and analyze image information through algorithms to achieve numerous warning and recognition functions, such as pedestrian warning, lane keeping, traffic signal recognition, etc. According to the number of lenses, cameras can be divided into monocular, binocular, and multi lens cameras.
The main advantages of a camera are its high resolution and low cost. The human eye can quickly capture massive amounts of information, and the camera can also obtain rich information. However, like the human eye, it is also affected by the field of view and environment. A monocular camera can capture a maximum range of 50 °, with limited observation distance; The performance of the camera will rapidly decline at night and in adverse weather conditions such as rain and snow.
In March 2018, a autonomous vehicle of Uber collided with a woman crossing the road in Arizona and killed her. The main reason was that the light conditions were poor at night and the road section was in shadow, so the pedestrians were not accurately identified. Millimeter wave radar compensates for the shortcomings of cameras. Compared to human eyes, it is more like the ears of bats: bats almost do not rely on their eyes, but emit ultrasonic waves through their ears, distinguish objects based on their reflected echoes, avoid obstacles, and therefore are not affected by lighting conditions.
Similar to the principle of bat flight, millimeter wave radar uses an antenna to emit millimeter waves with wavelengths of 1-10mm and frequencies of 24-300GHz. By processing the target reflection signal, it obtains environmental information such as the relative distance and velocity between the car and other objects, and tracks and classifies the target based on the information. The electronic control unit combines the dynamic information of the car body to make decisions.
The advantage of millimeter wave radar lies in its strong anti-interference ability, with higher penetration ability for rainfall, dust, smoke and plasma than laser and infrared. However, it also has disadvantages such as large signal attenuation, susceptibility to obstruction by buildings, and short transmission distance.
Lidar works similarly to radar, but its biggest advantage is the ability to use Doppler imaging technology to create clear 3D images of targets.
By measuring the time difference and phase difference of the laser signal to determine the distance, and using the collected three-dimensional coordinates, reflectivity, and texture information of a large number of dense points on the surface of the target object, a three-dimensional model of the measured target and various related data such as lines, surfaces, and volumes can be quickly obtained to achieve environmental perception.
He Wenxi, Director of the Safety and Quality Engineering Department of Shanghai Xingxuan IoT Technology, a domestic LiDAR solution provider, told Travel News that LiDAR is an indispensable sensor for cars to achieve autonomous driving, especially for L4 level and above. Lidar has obvious advantages, such as high resolution, high accuracy, and strong anti-interference ability. The more laser radar lines there are, the higher the measurement accuracy and the higher the safety.