A system includes a data communication module, a position sensor, and a controller. The position sensor is operable to detect a position of a watercraft. The controller is configured or programmed to send at least one of functional information, trouble information, or operational information to an external computer through a data communication module. In the functional information, an automatic control function of a marine propulsion device and the position of the watercraft when the automatic control function is used are associated with each other. In the trouble information, a trouble in the marine propulsion device and the position of the watercraft when the trouble occurred are associated with each other. In the operational information, an operational pattern performed by a user for the marine propulsion device and the position of the watercraft when the operational pattern is performed are associated with each other.

Provided is an autonomous ship navigation apparatus including an acquisition unit configured to acquire a surrounding environment image, marine information, and navigation information, a map generation unit configured to generate a grid map by displaying topography, a host ship, and an obstacle corresponding to the marine information and the navigation information in the surrounding environment image, and a sailing method determination unit configured to determine a sailing method of a ship through deep reinforcement learning based on the grid map, the marine information, and the navigation information.

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.

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.

The present disclosure discloses a wingless hydraulic extrusion spiral rotation and forward movement type intelligent unmanned underwater vehicle, including a cabin body and a control module. The cabin body includes a power reaction cabin and a power fuel storage cabin, a power reaction cabin water supply device is fixedly arranged on the cabin body. The power reaction cabin and the power fuel storage cabin are separated by a partition plate. Power fuel in the power fuel storage cabin may enter the power reaction cabin. A tail part of the power reaction cabin is provided with a jet forward propeller. The control module is fixed on the cabin body. At least two jet rotation propellers are arranged on the cabin body. The jet rotation propeller includes a main propelling pipe, an auxiliary propelling pipe, and a jet magnification ring. The jet magnification ring includes an outer ring and an inner ring.

The present disclosure discloses a wingless hydraulic extrusion spiral rotation and forward movement type intelligent unmanned underwater vehicle, including a cabin body and a control module. The cabin body includes a power reaction cabin and a power fuel storage cabin, a power reaction cabin water supply device is fixedly arranged on the cabin body. The power reaction cabin and the power fuel storage cabin are separated by a partition plate. Power fuel in the power fuel storage cabin may enter the power reaction cabin. A tail part of the power reaction cabin is provided with a jet forward propeller. The control module is fixed on the cabin body. At least two jet rotation propellers are arranged on the cabin body. The jet rotation propeller includes a main propelling pipe, an auxiliary propelling pipe, and a jet magnification ring. The jet magnification ring includes an outer ring and an inner ring.

Upon determining a mobile object is approaching an ice layer above a body of water, a thermal image of the ice layer is obtained. The thermal image and ambient temperature data are input to a neural network that outputs a plurality of regions of the ice layer and respective estimated thicknesses for the regions. A classification for each region is determined based on its estimated thickness and the mobile object. The classification is one of preferred or nonpreferred. The classifications for the regions are output.

Upon determining a mobile object is approaching an ice layer above a body of water, a thermal image of the ice layer is obtained. The thermal image and ambient temperature data are input to a neural network that outputs a plurality of regions of the ice layer and respective estimated thicknesses for the regions. A classification for each region is determined based on its estimated thickness and the mobile object. The classification is one of preferred or nonpreferred. The classifications for the regions are output.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for estimating wave properties of a body of water. A computer-implemented system obtains measurement data for a duration of time from an inertial measurement unit (IMU) onboard an underwater device, generates model input data based on at least the measurement data obtained at the plurality of time points, and processes the model input data to generate model output data indicating one or more wave properties using a machine-learning model. The system further determines, based on at least the one or more wave properties, whether the device is safe to be deployed.

Systems and methods for conveniently providing anchoring assistance onboard a watercraft are provided herein. An example system includes a display and a processor in communication with a marine system. The processor is configured to receive marine data from the marine system and/or one or more user inputs and cause the display to show one or more anchoring locations with visual indications of the anchorage quality index based on at least the marine data and/or user inputs. The one or more anchoring locations may be shown as a heat map overlaid on a map. The system may use real-time marine data, environmental data, weather data, tide data, etc. to dynamically adjust the anchoring locations and anchorage quality index. The system may enable convenient and helpful suggestions and notifications to the user when anchoring a watercraft. Some examples provide automatic deployment of an anchoring system and monitoring of a current anchoring.