The present disclosure provides a locomotion apparatus used in liquid. The moving apparatus includes a buoyancy cavity disposed in the locomotion apparatus, and is configured to accommodate gas or liquid; and a first regulation part disposed in the locomotion apparatus, and is configured to regulate a volume of the gas or the liquid in the buoyancy cavity; when the locomotion apparatus is switched from the sidewall of a swimming pool to the liquid surface, the volume of the gas or the liquid in the buoyancy cavity is regulated by the first regulation part to increase the buoyancy force applied to the locomotion apparatus.

The present disclosure provides a cleaning device, including: a cleaning device body; a filtering mechanism; a cleaning cavity disposed at a front portion of the cleaning device body and configured to accommodate at least one first cleaning part; a liquid inlet portion; a mode switching member configured to adjust a pose of the cleaning device, enabling the cleaning device to be switched between a first motion state and a third motion state, where when the cleaning device is in the first motion state, the liquid inlet portion is located under a water surface, and the cleaning device performs underwater cleaning, and when the cleaning device is in the third motion state, the liquid inlet portion is at least partially located above the water surface, and the cleaning device performs water surface cleaning; and a main water pump configured to generate a suction force.

Embodiments of the invention include systems and methods for range estimation in autonomous maritime vehicles through use of an image processing model. The model comprises a neural network that informs the vehicle as to the ranges of real-world objects based on a diversified set of synthetic and real-world training data. During training, the model estimates the ranges of objects and/or subcomponents extracted from the training data and compares the estimated ranges with the corresponding ground truths. The system then uses the results of the comparisons to update the weights and biases in the neural network and improve the accuracy and performance of the image processing model deployed to the vehicle.

A control system adapted for a boat having a first sensor including a GNSS receiver detecting a position of the boat, and a second sensor detecting the position of the boat is provided. The control system includes a control unit having a processor, configured to: switch a control mode of the control unit to an automatic docking mode; obtain roof information regarding whether a berth for mooring the boat includes a roof wherein when the control unit determines the berth for mooring the boat includes the roof, the control unit switches, at a predetermined timing, from the first sensor to the second sensor for determining the position of the boat.

A system, adapted for correcting an effect of an external disturbance on a boat. The system includes a control unit including a processor configured to function as: a disturbance obtaining unit, that obtains disturbance information of the boat, the disturbance information of the boat including at least one of a flow direction of the boat, a flow speed of the boat, or a rotation direction of the boat while a propulsion unit of the boat is stopped; a switching unit, that switches a control mode of the control unit to an automatic driving mode; a setting unit, that sets a steering route of the automatic driving mode, wherein, when the control mode is switched to the automatic driving mode, the control unit controls an automatic steering of the boat based on the disturbance information of the boat and the steering route of the automatic driving mode.

Approaches are disclosed for mapping surroundings of a marine vessel. These involve obtaining, at a first location, first distance data from distance sensors including a bow-mounted sensor arranged to monitor a first area involving surroundings adjacent to the bow and a first side of the marine vessel, and a stern-mounted sensor arranged to monitor a second area involving surroundings adjacent to the stern and a second side, opposite the first side, of the marine vessel. The approaches further includes generating a surroundings map comprising at least two unmapped areas indicating blind spots of at least partially incomplete surroundings representations; obtaining, at a second location, second distance data from the set of distance sensors; and causing updates to the unmapped areas based on the second distance data.

An automatic watercraft maneuvering system includes a propulsion device, a steering, a position sensor, a camera, and a controller configured or programmed to execute an automatic watercraft maneuvering control to control the propulsion device and the steering in order to perform automatic watercraft maneuvering from a departure location to a destination location. The automatic watercraft maneuvering control includes a camera watercraft maneuvering control and a position sensor watercraft maneuvering control. The controller is configured or programmed to, when a failure occurs in the position sensor in a predetermined area of water in which the automatic watercraft maneuvering is executable using the camera watercraft maneuvering control, cause the watercraft to head to a predetermined target position in the predetermined area of water in which the failure occurs during the camera watercraft maneuvering control.

An unmanned device for a marine environment comprises a location sensor configured to gather location data corresponding to the unmanned device; at least one propulsion system; a transmitter and memory including computer program code. The computer program code is configured to, when executed, cause the processor to cause the propulsion system to propel the unmanned device in a pattern along the body of water, cause the sonar transducer to emit the one or more sonar beams into the body of water, receive sonar return data corresponding to sonar returns, and generate a sonar image corresponding to the sonar return data. Further, the computer program code is configured to cause the processor to detect an object within the sonar image, assign a score to the object indicating the likelihood that the object is a desired object type, and send an alert to the remote electronics device upon assignment of the score.

Marine vessel control can include the application of surge force, sway force, and yaw moment. The present subject matter can include two aspects, including determination of forces and moments to achieve desired motion, and translation of such forces and moments into thrust and steering commands suitable for the available propulsion devices. Various operating modes can be employed to effectively control their motion. In each operating mode, feedback control can be used to determine one or more of a target surge force, sway force, or yaw moment, or combinations thereof. The feedback controller can include individual PID (or other) controllers corresponding to each degree of freedom, a state feedback controller, or other feedback control architectures. A current vessel state can be compared to the target vessel state to determine the error in position, heading, and speed. These errors can be transformed from the global coordinate system to the vessel coordinate system for determination of appropriate thrust and steering commands.

The present invention relates to an autonomous water vehicle for collecting and separating waste from aquatic environments, thereby enabling the efficient extraction of algae from water bodies. The autonomous water vehicle comprises a floating body, a driving unit, a conveyor unit, a scraping assembly, a first capturing unit, a second capturing unit, and a control unit. The autonomous water vehicle reduces operational costs while being adaptable for lakes, rivers, and small water bodies, making it ideal for environmental clean-up projects. The autonomous water vehicle is continuously monitored by a user, thereby improving efficiency and convenience. The autonomous water vehicle utilizes capturing units and GPS tracker for enabling precise navigation, real-time detection of floating waste, and obstacle avoidance. This integration ensures efficient route optimization for enhanced cleaning performance.