Vehicle environment information perception method, device, electronic equipment and storage medium

Abstract

The present application provides a method for sensing vehicle environment information, a vehicle state sensing device, electronic equipment, and a computer-readable storage medium. The method for sensing vehicle environment information includes: obtaining a tensor of a current probability heat map; obtaining a tensor of a predicted probability heat map; Merge the tensor of the current probability heat map with the tensor of the predicted probability heat map to obtain a dense tensor; obtain the center point position and direction of the car head and the center point position and direction of the car suspension from the dense tensor; use the center point position of the car head Stretch along the direction of the front of the vehicle, and extend along the direction of the vehicle suspension from the center point of the vehicle suspension, and determine the intersection point after the extension along the direction as the key point position of the connection between the vehicle front and the vehicle suspension; based on the connection key point of the vehicle front and vehicle suspension The position determines the current status of the semi-trailer. It can improve the accuracy of environmental information perception and improve the real-time performance of environmental information perception, and can run quickly and stably on embedded devices, achieving a lightweight effect.

Description

technical field [0001] The present application relates to the technical field of unmanned driving, and in particular to a vehicle environment information sensing method, a vehicle state sensing device, electronic equipment, and a computer-readable storage medium. Background technique [0002] With the continuous development of automation technology, unmanned driving has gradually become a trend. Especially for some closed and semi-closed engineering operation scenarios, such as: port docks, etc., the use of unmanned vehicles for automated operations can greatly improve operational efficiency. During the automatic operation of unmanned vehicles, the environmental perception system in the vehicle needs to obtain external information through sensors, convert the external information into environmental perception results, and then input the environmental perception results into the vehicle's decision-making system. The decision-making system is based on the environment The perc...

AI Technical Summary

Problems solved by technology

And after the detection of the front and the trailer respectively, it is necessary to use other algorithms to match and track the front and the trailer, which reduces the real-time output of the environmental perception results

Images