Method and device for evaluating intelligent level of automatic driving system under different network connection degrees

Abstract

The invention discloses a method for evaluating the intelligent level of an automatic driving system under different network connection degrees. The method comprises the following steps: S1, selectingevaluation indexes of the intelligent level of the automatic driving system; s2, obtaining a quantitative evaluation basis of the intelligent level of the automatic driving system according to the numerical difference between the actual action quantity and the theoretical minimum action quantity in the test traffic process; s3, determining the change range of the quantitative evaluation basis, dividing at least two evaluation intervals for evaluating the intelligent level of the tested automatic driving system, wherein each evaluation interval corresponds to one intelligent level; s4, acquiring multiple groups of quantitative evaluation basis data of the tested automatic driving system under different network connection degrees; and S5, performing statistical analysis on the quantitativeevaluation basis data, and evaluating the intelligent level of the tested automatic driving system according to each statistical analysis result. According to the invention, the intelligent level of the automatic driving system under different network connection degrees can be evaluated stereoscopically and truly.

Description

technical field [0001] The invention relates to the technical field of evaluation of intelligent networked vehicles and automatic driving vehicles, in particular to a method and device for evaluating the intelligence level of automatic driving systems with different degrees of network connection. Background technique [0002] Intelligence and networking are the inevitable trends in the development of autonomous vehicles. In the long-term development of networking, there will be both networked vehicles and non-networked vehicles in traffic. Different degrees of network connection in mixed traffic are an important factor affecting the intelligence level of autonomous driving vehicles. The evaluation of the intelligence level of autonomous driving systems under different degrees of network connection can reveal the underlying law of influence. In recent years, the technology of intelligent test field for autonomous driving has been continuously developed. Compared with traditio...

AI Technical Summary

Problems solved by technology

[0004] 1. The selection of evaluation indicators for the intelligence level of the automatic driving system in the existing technology is not reasonable enough

The three unmanned driving challenges organized by the U.S. DARPA (Defense Advanced Research Projects Agency) all use the time-consuming time to complete all specified projects as the evaluation index, but a single index is difficult to reflect the intelligence level of the automatic driving system

The level of intelligence is stratified and indicators are selected according to the classification of tasks at each level for comprehensive evaluation, but such comprehensive indicators do not directly reflect the level of intelligence (such as safety, efficiency)

[0005] 2. The existing technology is mixed with subjective factors in the evaluation, which is not objective enough

However, the selected reference trajectory is not suitable for dynamic traffic environment, nor can it reflect the objective safety and efficiency.

[0007] 4. The comprehensive evaluation indicators and methods obtained by the existing technology are not enough to deal with the randomness of the degree of network connection in the test

Images