Unmanned surface vehicle navigation obstacle detection method based on laser radar under complex sea condition

• Main Authors: WU YUANYUAN, DENG LIHUI, WANG LIANWEN, GUO TINGTING, FAN XIN, LIU SHUAI, YUAN RUBIN
• Format: Patent
• Language: Chinese; English
• Published: 07.03.2023
• Subjects: ANALOGOUS ARRANGEMENTS USING OTHER WAVES; CALCULATING; COMPUTING; COUNTING; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES; MEASURING; PHYSICS; RADIO DIRECTION-FINDING; RADIO NAVIGATION; TESTING

The invention relates to an unmanned surface vehicle navigation obstacle detection method based on a laser radar under a complex sea condition, and the method comprises the following steps: 1, carrying out the multi-cloud multi-frame fusion processing of point cloud data obtained by the laser radar, and constructing a foresight projection grid map of an unmanned surface vehicle; step 2, based on the foresight projection grid map of the unmanned surface vehicle constructed in the step 1, adopting a vertical attribute to improve a traditional RANSAC algorithm, and performing traversal optimization and improvement on data to realize efficient filtering of clutter interference point cloud data; and step 3, based on the unmanned surface vehicle navigation obstacle point cloud data information with few clutters obtained in the step 2, performing clustering processing on the point cloud data obtained by the laser radar by using an adaptive parameter improved DBSCAN algorithm to obtain the unmanned surface vehicle na