In order to solve the technical problems of autonomous berthing of the Unmanned Surface Vehicle(USV),this research has met the requirements of maneuverability berthing under different conditions by effectively using t...In order to solve the technical problems of autonomous berthing of the Unmanned Surface Vehicle(USV),this research has met the requirements of maneuverability berthing under different conditions by effectively using the bow and stern thrusters,which is a technological breakthrough in actual production and life.Based on the MMG model,the maneuverability mathematical model of the USV with bow and stern thruster was established.And the motion simulation of USV maneuvering was carried out through the numerical simulation calculation.Then the berthing plan was designed based on the maneuverability analysis of the USV low-speed motion,and the simulation of automatic berthing for USV was carried out.The research results of this paper can be of certain practical significance for the USV based on the support of the bow and stern thruster in the berthing.At the same time,it also provides a certain theoretical reference for the handling of the USV automatic berthing.展开更多
Automatic berthing guidance is an important aspect of automated ship technology to obtain the ship-shore position relationship.The current mainstream measurement methods for ship-shore position relationships are based...Automatic berthing guidance is an important aspect of automated ship technology to obtain the ship-shore position relationship.The current mainstream measurement methods for ship-shore position relationships are based on radar,multisensor fusion,and visual detection technologies.This paper proposes an automated ship berthing guidance method based on three-dimensional(3D)target measurement and compares it with a single-target recognition method using a binocular camera.An improved deep object pose estimation(DOPE)network is used in this method to predict the pixel coordinates of the two-dimensional(2D)keypoints of the shore target in the image.The pixel coordinates are then converted into 3D coordinates through the camera imaging principle,and an algorithm for calculating the relationship between the ship and the shore is proposed.Experiments were conducted on the improved DOPE network and the actual ship guidance performance to verify the effectiveness of the method.Results show that the proposed method with a monocular camera has high stability and accuracy and can meet the requirements of automatic berthing.展开更多
基金This research was funded by National Natural Science Foundation of China(No.51309148).
文摘In order to solve the technical problems of autonomous berthing of the Unmanned Surface Vehicle(USV),this research has met the requirements of maneuverability berthing under different conditions by effectively using the bow and stern thrusters,which is a technological breakthrough in actual production and life.Based on the MMG model,the maneuverability mathematical model of the USV with bow and stern thruster was established.And the motion simulation of USV maneuvering was carried out through the numerical simulation calculation.Then the berthing plan was designed based on the maneuverability analysis of the USV low-speed motion,and the simulation of automatic berthing for USV was carried out.The research results of this paper can be of certain practical significance for the USV based on the support of the bow and stern thruster in the berthing.At the same time,it also provides a certain theoretical reference for the handling of the USV automatic berthing.
基金The EDD of China(No.80912020104)the Science and Technology Commission of Shanghai Municipality(Grant No.22ZR1427700 and No.23692106900)。
文摘Automatic berthing guidance is an important aspect of automated ship technology to obtain the ship-shore position relationship.The current mainstream measurement methods for ship-shore position relationships are based on radar,multisensor fusion,and visual detection technologies.This paper proposes an automated ship berthing guidance method based on three-dimensional(3D)target measurement and compares it with a single-target recognition method using a binocular camera.An improved deep object pose estimation(DOPE)network is used in this method to predict the pixel coordinates of the two-dimensional(2D)keypoints of the shore target in the image.The pixel coordinates are then converted into 3D coordinates through the camera imaging principle,and an algorithm for calculating the relationship between the ship and the shore is proposed.Experiments were conducted on the improved DOPE network and the actual ship guidance performance to verify the effectiveness of the method.Results show that the proposed method with a monocular camera has high stability and accuracy and can meet the requirements of automatic berthing.
