An environmental modeling capability assessment method and system for an autonomous vehicle

Abstract

The embodiment of the invention provides an environmental modeling capability assessment method and system for an autonomous vehicle, and belongs to the field of intelligent transportation. The methodcomprises the following steps: obtaining environment information of a plurality of continuous frames of a vehicle environment detected by a vehicle-mounted sensing system of the automatic driving vehicle; comparing and analyzing the environment information of a plurality of consecutive frames with corresponding real environment information, judging whether one or more of information delay, information missing report and signal false report exist or not, and if yes, counting the time of the information delay and the occurrence frequency of the information missing report and the signal false report; And evaluating the environment modeling capability of the autonomous vehicle according to the information delay time, the occurrence frequency of the information missing report and/or the occurrence frequency of the signal false report. According to the method, the labeling frequency and labeling quantity of information delay, information missing reporting, information false reporting and the like are improved, and more powerful data support is provided for evaluating the environment modeling capability of the autonomous vehicle.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

The technology presented in this patented method helps researchers better identify road conditions around cars or other objects on roads during automated driving simulations (ADV). By continuously analyzing an ADV frame over time, they are able to provide stronger data supports than previous methods like manually annotate them. This results in improved assessment efficiency and consistently high quality environmental descriptions. Overall, these improvements help drivers reduce their impact upon surrounding environments while making informed decisions about how best to navigate through complex scenarios such as urban areas.

Problems solved by technology

This patented technical problem addressed in this patents relating to autonomously driven cars is related to improving their ability to detect obstacles while navigating safely within its own surroundings due to poor environmental models caused by limited sensor technology used during navigation.

Images