The traditional A^(*)algorithm exhibits a low efficiency in the path planning of unmanned surface vehicles(USVs).In addition,the path planned presents numerous redundant inflection waypoints,and the security is low,wh...The traditional A^(*)algorithm exhibits a low efficiency in the path planning of unmanned surface vehicles(USVs).In addition,the path planned presents numerous redundant inflection waypoints,and the security is low,which is not conducive to the control of USV and also affects navigation safety.In this paper,these problems were addressed through the following improvements.First,the path search angle and security were comprehensively considered,and a security expansion strategy of nodes based on the 5×5 neighborhood was proposed.The A^(*)algorithm search neighborhood was expanded from 3×3 to 5×5,and safe nodes were screened out for extension via the node security expansion strategy.This algorithm can also optimize path search angles while improving path security.Second,the distance from the current node to the target node was introduced into the heuristic function.The efficiency of the A^(*)algorithm was improved,and the path was smoothed using the Floyd algorithm.For the dynamic adjustment of the weight to improve the efficiency of DWA,the distance from the USV to the target point was introduced into the evaluation function of the dynamic-window approach(DWA)algorithm.Finally,combined with the local target point selection strategy,the optimized DWA algorithm was performed for local path planning.The experimental results show the smooth and safe path planned by the fusion algorithm,which can successfully avoid dynamic obstacles and is effective and feasible in path planning for USVs.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Supported by the EDD of China(No.80912020104)the Science and Technology Commission of Shanghai Municipality(No.22ZR1427700 and No.23692106900).
文摘The traditional A^(*)algorithm exhibits a low efficiency in the path planning of unmanned surface vehicles(USVs).In addition,the path planned presents numerous redundant inflection waypoints,and the security is low,which is not conducive to the control of USV and also affects navigation safety.In this paper,these problems were addressed through the following improvements.First,the path search angle and security were comprehensively considered,and a security expansion strategy of nodes based on the 5×5 neighborhood was proposed.The A^(*)algorithm search neighborhood was expanded from 3×3 to 5×5,and safe nodes were screened out for extension via the node security expansion strategy.This algorithm can also optimize path search angles while improving path security.Second,the distance from the current node to the target node was introduced into the heuristic function.The efficiency of the A^(*)algorithm was improved,and the path was smoothed using the Floyd algorithm.For the dynamic adjustment of the weight to improve the efficiency of DWA,the distance from the USV to the target point was introduced into the evaluation function of the dynamic-window approach(DWA)algorithm.Finally,combined with the local target point selection strategy,the optimized DWA algorithm was performed for local path planning.The experimental results show the smooth and safe path planned by the fusion algorithm,which can successfully avoid dynamic obstacles and is effective and feasible in path planning for USVs.
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.
