Barrier motion information generating method and device used for unmanned vehicle

Abstract

The embodiment of the invention discloses a barrier motion information generating method and device used for a unmanned vehicle. The method comprises the following steps of obtaining current frame barrier point cloud and reference frame barrier point cloud for representing a target barrier with motion information to be generated; calculating the first observed displacement of the target barrier under each first displacement observation quantity in M first displacement observation quantities; determining the motion information of the target barrier under each first displacement observation quantity in the M first displacement observation quantities; determining the observed motion information of the target barrier according to the determined M kinds of motion information and the historicalmotion information of the target barrier; and taking the motion information of the target barrier as a state variable, taking the observed motion information as the observation quantity, and using a preset filtering algorithm to generate the current motion information of the target barrier. In the invention, under the condition that barrier point cloud segmentation is not accurate, motion estimation is effectively performed on the barrier.

Description

technical field [0001] The present application relates to the technical field of unmanned vehicles, in particular to the technical field of obstacle motion estimation, and in particular, to a method and device for generating obstacle motion information for unmanned vehicles. Background technique [0002] Unmanned vehicles, also known as "mobile wheeled robots", are based on the information collected by various sensors (such as cameras and lidars) through comprehensive analysis and processing by the driving control equipment set on the vehicle to achieve Path planning and ride control. Most driverless vehicles are equipped with lidar to collect information from the outside world. In the process of path planning and driving control of the unmanned vehicle, obstacle detection can be performed on each frame of the laser point cloud collected by the lidar (ie, the laser point cloud collected by the lidar in each sampling period), and then , and then perform motion estimation on...

AI Technical Summary

Problems solved by technology

[0003] However, most of the existing methods for obstacle motion estimation adopt the definition of interest points on the obstacle point cloud (point cloud used to characterize obstacles), and perform motion estimation on obstacles according to the displacement of interest points, thus There is a problem of inaccurate motion estimation when the obstacle point cloud segmentation is inaccurate (eg, under-segmentation or over-segmentation)

Images