Automatic driving system and control method thereof

Abstract

The invention relates to an automatic driving system and a control method thereof. The automatic driving system comprises sensors, a vehicle-mounted calculation unit and a drive-by-wire execution mechanism; the vehicle-mounted calculation unit comprises a visual perception processor, a fusion decision unit and a safety control unit; the visual perception processor directly processes data acquiredby the sensors and reasonably distributes the data to the fusion decision unit and the safety control unit; the fusion decision unit makes a decision plan on the basis of vehicle body state data and drive-by-wire part data, and transmits decision plan information to the safety controller; and the safety controller sends a motion control instruction to the drive-by-wire execution mechanism according to the decision planning information. According to the automatic driving system and the control method thereof of the invention, the calculation processing tasks of the sensors with different data characteristics are ingeniously distributed to different component modules of the calculation platform. On the basis that the safety, redundancy and high efficiency of the system are guaranteed, the manufacturing cost of the automatic driving automobile is greatly reduced, and a direction is pointed out for the mass production of automatic driving vehicles.

Description

technical field

[0001] The invention relates to the field of automatic driving, in particular to an automatic driving system and a control method thereof. Background technique

[0002] At present, many autonomous driving car manufacturers do not have the ability to rationally optimize the fusion of different characteristic sensors. The types of on-board sensors used are not only complicated but also a large number of certain types of sensors. In order to ensure that the computing platform has matching efficient and powerful data computing and processing Performance, computing platforms often use expensive single-chip processors to be responsible for all data fusion decisions and motion control for autonomous vehicles, such as Huawei's MDC600 automatic driving system, Nvidia's Driver PX2 automatic driving system and Baidu's apollo automatic driving system . Therefore, from the perspective of system design, reducing the cost of autonomous vehicles on the basis of ensuring the...

Images