Unmanned ship water surface target detection and path planning method based on three-dimensional laser radar

Abstract

The invention discloses an unmanned ship water surface target detection and path planning method based on a three-dimensional laser radar. The unmanned ship water surface target detection and path planning method aims at sensing a water surface environment and carrying out autonomous navigation according to the environment information. The method comprises steps that firstly, a laser radar coordinate system is defined, then laser radar parameters are calibrated, angle and distance information under polar coordinates is converted into coordinates under a Cartesian coordinate system, and then in order to distinguish ground point clouds from water surface point clouds, ground segmentation is carried out, and the ground point clouds are filtered, so the calculated amount of a subsequent algorithm is reduced; then water surface obstacles scanned by the laser radar are clustered, and finally a water surface path is planned according to the obstacle information, so an unmanned ship avoids the obstacles on the water surface and plans a path so as to ensure that the unmanned ship can safely and accurately reach a specified target point.

Description

technical field [0001] The invention belongs to the technical field of target detection, and in particular relates to a target detection and path planning method. Background technique [0002] With the continuous improvement of computing, performance and sensing technology, autonomous driving technology has developed rapidly, and its application fields have expanded from land to air and water, and unmanned ships are typical unmanned equipment on the water. In order to realize the safe navigation of unmanned ships, surface path planning is required, and environmental perception is a prerequisite for path planning. [0003] Lidar is one of the most commonly used sensors in unmanned ships for surface environment perception. It is a system that uses laser light to detect geometric features such as position, shape, and velocity. It fires laser light at target objects and then receives signals reflected from those objects. By comparing the phase difference between the received s...

AI Technical Summary

Problems solved by technology

However, due to the sensor's sensing characteristics and environmental interference, the detection performance of 2D LiDAR degrades when the sensor reaches the blind spot at close range.

In addition, 2D LiDAR has a low sampling rate and low resolution, so the detection performance of 2D LiDAR will decrease when identifying high-speed ships or small objects protruding from the water surface

Images