Calibration method and arrangement structure of automatic driving environment perception sensor and vehicle

Abstract

The invention relates to the field of automatic driving sensors, in particular to a calibration method and arrangement structure of an automatic driving environment perception sensor and a vehicle. According to the calibration method, different calibration methods are adopted for different sensors, based on utilization and processing of data such as laser point clouds, pose transformation of coordinate systems of different sensors relative to a vehicle coordinate system is carried out through different methods, the automation degree of automatic driving environment perception sensor calibration is improved, the accuracy is high, the requirement of multi-sensor fusion is met; 360-degree uniform coverage of a vehicle body is met, meanwhile, sensor redundancy of a certain degree is achieved,under the condition that an individual sensor breaks down, the surrounding environment can be normally monitored, the automatic driving safety is improved, and through the arrangement method of the embodiment, on the premise that the perception performance is guaranteed, mutual cooperation is achieved to the maximum extent, the using number of sensors is reduced as much as possible, and cost is effectively reduced.

Description

technical field [0001] The invention relates to the field of automatic driving sensors, in particular to a calibration method, layout structure and vehicle of an automatic driving environment perception sensor. Background technique [0002] Autonomous driving requires sensors to detect the environment. Currently, several types of sensors such as laser radar, camera, millimeter-wave radar, and ultrasonic radar have their own advantages and disadvantages, and their characteristics are different. Multi-sensor information fusion is required to complement each other and make full use of it. The advantages of each sensor can achieve accurate perception, thereby ensuring the safe driving of autonomous vehicles. [0003] Based on technical and cost considerations, current self-driving cars are mainly used in specific scenarios. In the prior art, self-driving vehicles have different perception ranges and detection requirements for the front, side front, side, side rear and rear, and...

AI Technical Summary

Problems solved by technology

In the prior art, self-driving vehicles have different perception ranges and detection requirements for the front, side front, side, side rear and rear, and different scenarios need to implement different functions. The layout requirements of sensors are also different; in addition, for the calibration of sensing sensors, in the prior art, the calibration method of sensors is usually that each sensor establishes its own independent coordinate system, or different sensors are calibrated according to the same method; the calibration method is implemented Complex, cumbersome process, requiring a lot of manual operations, affecting calibration efficiency and calibration accuracy

[0004] To sum up, in the current field of autonomous driving, the layout and calibration of environmental perception sensors have shortcomings such as low accuracy and poor safety performance. Therefore, a sensor calibration and layout structure that can achieve high accuracy and automation is designed. very necessary

Images