Road end sensing method, device, road end equipment and system based on deep fusion

Abstract

The invention relates to a road end sensing method, device, road end equipment and system based on deep fusion. The method comprises the following steps: obtaining sensing data collected based on a road end sensor and cloud data collected based on cloud equipment; calculating according to the perception data and the cloud data to obtain road end perception information, wherein the road end sensinginformation comprises a semi-static target object and a drivable area, and the semi-static target object is an object which is static in a first time range and dynamic in a second time range; and sending the road end sensing information to a vehicle end, so that the vehicle end performs deep fusion on the vehicle end sensing information and the road end sensing information to obtain fusion information, and drives a vehicle to run according to the fusion information. According to the invention, deep fusion is carried out based on the original data collected by the road end sensor and the clouddata, the semi-static target object and the drivable area are obtained through calculation and issued to the vehicle end, and the automatic driving decision planning capability of the vehicle end isenhanced.

Description

technical field [0001] The present application relates to the technical field of intelligent transportation, in particular to a roadside perception method, device, roadside equipment and system based on deep fusion. Background technique [0002] The highly automatic driving system has been in practical use for more than ten years, and the related technologies have gradually matured and improved. They can be mainly divided into: 1) perception technology: including millimeter wave radar, camera perception, laser radar, ultrasonic radar, etc.; 2) fusion technology : Including dynamic target fusion, drivable area fusion and static target fusion; 3) Decision-making planning technology: including behavior decision-making, trajectory planning, horizontal and vertical control, vehicle dynamic model adaptation, etc. [0003] However, despite the further reduction in the cost of autonomous driving hardware in vehicles in the near future, autonomous driving still faces many challenges....

AI Technical Summary

Problems solved by technology

In fact, autonomous driving has very high requirements for perception performance, both in space and time domain. However, the current vehicle-road collaboration technology emphasizes the application of landing scenarios, and road-side perception devices often only have simple target-level fusion capabilities. , and only integrate moving or stationary targets (such as passing pedestrians, vehicles, street signs, parking booths, etc.), resulting in incomplete perception information obtained by the vehicle

Images