Method and system for evaluating environment modeling capabilities of autonomous vehicles

Abstract

Embodiments of the present invention provide a method and system for evaluating the environment modeling capability of an autonomous vehicle, belonging to the field of intelligent transportation. The method includes: constructing a polygonal capability graph for environment modeling capabilities, each vertex of which is configured to represent a level; obtaining entity attribute information of several entities associated with environment modeling in each level; combining entity attributes information to determine the importance of the corresponding entity to vehicle driving safety, and assign weights to each entity according to the importance; obtain the accuracy of each entity correctly detected by the on-board sensing system; combine the accuracy and weight to calculate the weight of each level a weighted total score; and displaying the weighted total score in a polygonal capability map to form an environment modeling capability map. The present invention can obtain the environmental modeling capability map of vehicles based on multiple levels, which is helpful for determining the environmental modeling scores of each level and comparing the environmental modeling capabilities with other versions of vehicles and competing vehicles.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a method and system for evaluating the environment modeling capability of an automatic driving vehicle. Background technique [0002] At present, the Autonomous Driving System (ADS) of autonomous vehicles can be divided into five parts: environmental perception, data fusion, decision-making system, control system, and execution system. Among them, environmental perception refers to extracting the current driving environment information of vehicles, pedestrians, roads, traffic signs and other vehicles through the in-vehicle sensing system, and transmitting the extracted information to other systems to realize automatic driving path planning and vehicle behavior control. [0003] Therefore, it can be seen that environmental perception is the information basis of ADS. The important requirement for autonomous driving safety at this stage is how to make the autonomous driving...

AI Technical Summary

Problems solved by technology

[0004] However, there is a lack of evaluation of the environmental modeling capabilities of autonomous vehicles in the prior art, so that the final environmental models do not meet the requirements of "accurate" and "stable", and even some environmental models can only perform a single analysis of the environment. The description of one or very few aspects is not enough to support vehicle driving planning

Images