Automatic driving safety assessment method, device and system

Abstract

The invention provides an automatic driving safety assessment method. The method includes the following steps: obtaining rb and rc, wherein the rb is a risk value of a shadow driving mode of a vehicle in a first unit of measurement, the rc is a risk value of an automatic driving mode of the vehicle based on a preset route in the first unit of measurement, the shadow driving mode is an automatic driving mode based on a real-time route of the vehicle, the real-time route is a route that is predicted according to a position and motion parameters of the vehicle in a manual driving mode and the first unit of measurement is a time period or distance; determining RB according to the rb, wherein the RB is a risk value of the shadow driving mode of the vehicle in multiple units of measurement and the multiple units of measurement include the first unit of measurement; and determining RC according to the rc, wherein the RCA is a risk value of the automatic driving mode of the vehicle based on the preset route in multiple units of measurement, and the RB and the RC are used for determining whether the safety of the automatic driving mode of the vehicle meets requirements. The method can more realistically assess the safety of the automatic driving.

Description

technical field [0001] The present application relates to the field of automatic driving, and in particular to an automatic driving safety assessment method, device and system. Background technique [0002] Self-driving cars, also known as unmanned cars, can obtain environmental information through sensors such as radar, and control the driving of the vehicle according to the environmental information, reducing the time for the driver to control the car. Self-driving cars have the advantages of reducing traffic violations. However, since the driver spends less time controlling the car in the automatic driving mode than the driver in the traditional manual driving mode, there are still many uncertainties in the self-driving car. In order to reduce the The risk to passengers of self-driving cars requires a rigorous assessment of their safety before they can be sold. [0003] In order to evaluate the safety of self-driving cars, it is necessary to collect a large amount of dri...

AI Technical Summary

Problems solved by technology

The above method can use the data in the manual driving mode to evaluate the safety of the automatic driving mode, which reduces the cost cycle of the mass production of automatic driving vehicles. However, the safety assessment based on the simulated automatic driving system cannot restore the real driver control scene. As a result, there is a large deviation between the safety assessment results based on the simulated automatic driving system and the real automatic driving safety.

Images