Roadside Perception Method, Device, Roadside Equipment and System Based on Deep Fusion

Abstract

The present application relates to a roadside sensing method, device, roadside device and system based on deep fusion. The method includes: acquiring sensing data collected based on roadside sensors and cloud data collected based on cloud devices; Data and cloud data are calculated to obtain roadside perception information; the roadside perception information includes a semi-static target object and a drivable area; the semi-static target object is static in the first time range, and is static in the second time range A dynamic object; the road-end perception information is sent to the vehicle end, so that the vehicle end deeply fuses the vehicle-end perception information with the road-side perception information to obtain fusion information, and drives the vehicle to run according to the fusion information. This application is based on the in-depth fusion of the original data collected by roadside sensors and cloud data, and the semi-static target objects and drivable areas are calculated and sent to the vehicle end, which enhances the vehicle's automatic driving decision-making and planning capabilities.

Description

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

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