-
公开(公告)号：US12125389B1
公开(公告)日：2024-10-22
申请号：US18514144
申请日：2023-11-20
CPC分类号： G08G3/02 , B63B43/18 , G05D1/0206
摘要： A propulsion control system for a marine vessel includes a propulsion system comprising at least one propulsion device configured to propel the marine vessel, a proximity sensor system configured to generate proximity measurements describing proximity of objects surrounding the marine vessel, and a control system. The control system is configured to receive the proximity measurements, generate a most important object (MIO) dataset based on the proximity measurements, wherein the MIO dataset defines a closest proximity measurement in each of a plurality of directions with respect to the marine vessel, calculate a velocity limit dataset based on the MIO dataset, wherein the velocity limit dataset defines a velocity limit in each of the plurality of directions, and control the propulsion system based on the velocity limit dataset.
-
公开(公告)号：US11990044B2
公开(公告)日：2024-05-21
申请号：US17292601
申请日：2020-09-30
发明人： Yong Ma , Yujiao Zhao , Yulong Wang
CPC分类号： G08G3/02 , G05D1/0088 , G05D1/0206 , G06N3/08
摘要： Disclosed is an intelligent collision avoidance method for a swarm of unmanned surface vehicles based on deep reinforcement learning; firstly, a theoretical framework of autonomous learning collision avoidance of a swarm of unmanned surface vehicles based on deep reinforcement learning is proposed, and the LSTM neural network memory ability is integrated to realize the continuity of collision avoidance actions; then, according to the USV environment in the framework, the characterization method is obtained, and the USV collision avoidance reward and punishment function is proposed to evaluate the collision avoidance effect; finally, an intelligent collision avoidance training system for a swarm of unmanned surface vehicles is formed. The simulation and verification of this disclosure show that the USV trained in this disclosure can navigate safely in the collision avoidance environment with a swarm of unmanned surface vehicles and realize intelligent collision avoidance.
-
公开(公告)号：US20240126262A1
公开(公告)日：2024-04-18
申请号：US17964917
申请日：2022-10-13
发明人： Yoshiyuki MISUMI
CPC分类号： G05D1/0208 , B63B49/00 , G01S17/89 , G06V20/05 , G06V20/13 , G06V20/17 , G06V20/56 , G08G3/02
摘要： A system for automatically determining a mooring direction or a berth approach direction of a boat. The system including a control unit including a processor. The control unit is configured to obtain image information, the image information including information of an other boat that is moored; identify a mooring direction of the other boat based on the image information; determine the mooring direction or the berth approach direction of the boat based on the mooring direction of the other boat, wherein the control unit determines an automatic mooring route of the boat based on the mooring direction or the berth approach direction of the boat, and the control unit outputs a control signal for controlling an automatic mooring of the boat.
-
4.发明公开公开(公告)号：US20240096221A1
公开(公告)日：2024-03-21
申请号：US18518694
申请日：2023-11-24
发明人： Kazuya NAKAGAWA , Daisuke FUJIOKA
IPC分类号： G08G3/02 , G01S13/937
CPC分类号： G08G3/02 , G01S13/937
摘要： A ship monitoring device includes processing circuitry that accepts a specification of a position in an image displayed on a display unit, acquires first ship data indicative of a position and a velocity of a first ship, acquires a plurality of second ship data indicative of positions and velocities of a plurality of second ships, calculates a collision risk area where a risk of the first ship colliding each of the second ships becomes more than a given value, based on the first ship data and the plurality of second ship data, and displays a plurality of ship objects indicative of the plurality of second ships, and the collision risk area disposed at corresponding positions in the image, and when a specification of the collision risk area is accepted, displays the ship object corresponding to the specified collision risk area so as to be discriminated from other ship objects.
-
公开(公告)号：US11928979B2
公开(公告)日：2024-03-12
申请号：US16976870
申请日：2019-03-04
发明人： Philippe Reinquin
CPC分类号： G08G9/02 , G08G3/02 , G08G5/0082 , G08G5/04
摘要： A device for avoiding a potential conflict detected in a predetermined trajectory prediction horizon between a first trajectory of a first ship or aircraft and a second trajectory of a second ship or aircraft is disclosed. Each trajectory includes a plurality of segments formed between multiple navigation points. The device includes a determination unit for determining at least one lateral peripheral envelope of the first trajectory, a division unit for dividing the lateral peripheral envelope into a plurality of juxtaposed sections arranged longitudinally the ones after the others and delimited by transition lines marking the change between sections, each transition line cutting, at a first point of intersection, a segment of the first trajectory and, at a second point of intersection, and an edge of the lateral peripheral envelope, a discretisation unit, and a computing unit.
-
公开(公告)号：US11862025B2
公开(公告)日：2024-01-02
申请号：US17392349
申请日：2021-08-03
申请人： FUJITSU LIMITED
发明人： Isamu Watanabe
CPC分类号： G08G3/02 , B60G2800/242 , B60W30/08 , B63B49/00 , B63B79/40
摘要： A method for calculating a dangerous spot and time for a computer to execute a process includes, detecting, by at least two mobile bodies, an avoidance action, which is an action that indicates a possibility that each mobile body has avoided a collision with another mobile body, based on locus data of a plurality of mobile bodies that belongs to a predetermined area; calculating an evaluation value that indicates a possibility that an avoidance action by one of the two mobile bodies has occurred under an influence of an avoidance action by another one; and calculating, based on the evaluation value, a collision risk in an area where a plurality of mobile bodies is concentrated.
-
公开(公告)号：US11851147B2
公开(公告)日：2023-12-26
申请号：US17615111
申请日：2021-08-11
发明人： Yong Ma , Haiyang Jiang , Xinping Yan
CPC分类号： B63B79/40 , G05D1/0206 , G08G3/02
摘要： A spatio-temporal DP method based on ship trajectory characteristic point extraction, which belongs to the technical field of ship trajectory compression and includes: Step 1: performing clustering analysis on AIS raw data using a clustering algorithm to identify outliers in the AIS data and then eliminate noise points; Step 2: identifying and retaining the characteristic trajectory points of the ship course change, ship speed change, and the ship entering and exiting from a certain area and the like; Step 3: compressing the AIS data by taking the start and end points of the ship trajectory and the characteristic trajectory points retained in step 2 as the initial points, and considering the spatio-temporal characteristics of the AIS data at the same time. The compressed ship can effectively compress redundant AIS data. The compressed ship trajectory has very little difference from the original trajectory, can retain the information of points of the ship motion state change and the points of the ship entering and exiting from the boundary of an area at the same time, has a large reuse value space, and is used for laving the foundation of data processing for ship historical data analysis and ship behavior recognition.
-
公开(公告)号：US11776250B2
公开(公告)日：2023-10-03
申请号：US17976296
申请日：2022-10-28
申请人： Seadronix Corp.
发明人： Byeol Teo Park , Han Keun Kim , Dong Hoon Kim
IPC分类号： G06V20/00 , G08G3/02 , G06T7/50 , G06T7/70 , G06N3/08 , B63B79/15 , G06F18/21 , G06F18/2431 , G06T7/11
CPC分类号： G06V20/00 , B63B79/15 , G06F18/21 , G06F18/2431 , G06N3/08 , G06T7/50 , G06T7/70 , G08G3/02 , G06T7/11 , G06T2207/20081 , G06T2207/20084 , G06T2207/30252
摘要： A method for situation awareness is provided. The method comprises: preparing a neural network trained by a learning set, wherein the learning set includes a plurality of maritime images and maritime information including object type information which includes a first type index for a vessel, a second type index for a water surface and a third type index for a ground surface, and distance level information which includes a first level index indicating that a distance is undefined, a second level index indicating a first distance range and a third level index indicating a second distance range greater than the first distance range; obtaining a target maritime image generated from a camera; and determining a distance of a target vessel based on the distance level index of the maritime information being outputted from the neural network which receives the target maritime image and having the first type index.
-
公开(公告)号：US11691703B2
公开(公告)日：2023-07-04
申请号：US17059852
申请日：2018-06-01
申请人： WÄRTSILÄ VOYAGE GMBH
CPC分类号： B63B79/40 , G05D1/0206 , G08G3/02 , B63B2213/02
摘要： Apparatus and computer-implemented method for autonomous marine vessel docking, the method including determining a transit control mode associated with route plan data defining transit operation between ports; determining an autonomous docking control mode associated with harbor track data including a set of waypoint properties and defining approach zone information and track segments joined at waypoints. Method further includes determining vessel location, speed and heading; comparing the vessel location, speed and heading to the approach zone information and changing from the transit control mode to the autonomous docking control mode in response to: the vessel location included by the location area information; the vessel speed being lower than the maximum vessel speed for entering the approach zone; and the vessel heading matching criteria defined by the maximum heading deviation for entering the approach zone.
-
公开(公告)号：US20230124356A1
公开(公告)日：2023-04-20
申请号：US18069986
申请日：2022-12-21
发明人： Yong MA , Jing WANG , Huaxiong BI , Xinping YAN , Yuanzhou ZHENG
摘要： An optimized coverage-path planning method for a single unmanned surface mapping vessel (USMV), includes: initializing GT values of all grids as ue, pre-configuring each grid assigned value BVa0, inputting coordinates, continuing to update a pre-configured map; importing a static map according to the grids; inputting coordinates and continuing to update the pre-configured map according to the static map; outputting, by a USMV, position information ω and obstacle information η thereof according to the pre-configured map, and starting to update the map; outputting a grid status list GT_list according to the updated map, and receiving, by a BL0-level map, input map information and USMV information, starting path planning, and outputting a target point tp to the USMV; if the solution is trapped in a local optimum at the BL0 level, updating each map level in ascending order, and searching the corresponding level for the tp.
-
-
-
-
-
-
-
-
-
搜索结果
286 条记录 (耗时 0.023 秒)
