An automated evaluation method for drivability of intelligent vehicles based on fusion of multi-source on-board sensor information

Abstract

The present invention provides an intelligent vehicle drivability automatic evaluation method that integrates multi-source on-board sensor information. The real vehicle signal necessary for drivability evaluation is obtained synchronously through the intelligent vehicle test platform; the real vehicle signal is processed by using the time-frequency analysis method and the abnormal point elimination method. , and then complete the information fusion on the target layer and the data layer to obtain the data set; analyze the data set combined with the characteristics of driving conditions, and intercept the specific working conditions through the sliding window method; use the principal component analysis method to find the main influencing factors of the driving performance of intelligent vehicles, extract Intelligent vehicles characterize the quantitative characteristics of drivability and establish a training set database; combine the Delphi method and subjective evaluation engineer knowledge base to construct subjective and objective correlation analysis and drivability automatic evaluation standard evaluation system; use machine learning C4.5 algorithm to realize intelligent Analysis of vehicle subjective and objective correlations and automated evaluation of drivability. The invention can provide evaluation basis for the feasibility of decision planning algorithm and tracking control algorithm of intelligent vehicles.

Description

An automated evaluation of intelligent vehicle drivability based on multi-source vehicle sensor information method technical field The invention belongs to the technical field of intelligent vehicle performance evaluation and analysis, and in particular relates to a fusion multi-source vehicle-mounted sensor Automatic evaluation method of intelligent vehicle drivability based on device information. Background technique [0002] The intelligent vehicle integrates environmental perception, decision-making and planning, and trajectory tracking modules, through radar, camera and planning control. The control algorithm is used to simulate the driving behavior of the driver to ensure the safety, economy and comfort of the vehicle-road-human system. Focus and hotspots of development in the field of vehicles and robots. When evaluating decision planning algorithms and tracking control algorithms, only safety and economy as the goal, without considering the vehicle's executi...

AI Technical Summary

Problems solved by technology

The current patents and research on drivability evaluation focus on subjective evaluation and traditional vehicles, but the subjective evaluation of drivability is costly, has a large environmental impact, is difficult to repeat, and is difficult to provide for the optimization of intelligent vehicle trajectory planning and tracking control algorithms. objective reference value

Images