An underwater robot and a control method therefor. The underwater robot includes a robot main body, wherein a dirt suction port is provided at bottom of the robot main body, a first water outlet is provided on top of the robot main body in communication with the dirt suction port, a second water outlet is further provided at bottom of the robot main body in communication with the first water outlet, and the second water outlet is located on a side of the dirt suction port close to a front end; and a water-pumping mechanism and an escape mechanism provided in the robot main body. By means of the underwater robot and the control method therefor, the obstacle crossing capability of the underwater robot is improved.

This disclosure describes monitoring and operating subsea well systems, such as to perform operations in the construction and control of targets in a subsea environment. A submerisble ROV that performs operations in the construction and control of targets (e.g., well completion components) in a subsea environment, the ROV has one or more imaging devices that capture data that is processed to provide information that assists in the control and operations of the ROV and/or well completion system while the ROV is subsea.

The present disclosure provides a cleaning device, including a cleaning device body, a liquid inlet portion, a liquid outlet portion, a filtering mechanism, and a mode switching member. The filtering mechanism includes at least a filtering box. The filtering box includes at least a filtering box opening for water surface cleaning, a filtering box roller brush assembly, and a drive gear. The filtering box roller brush assembly is disposed at the filtering box opening for water surface cleaning. The drive gear is configured to drive the filtering box roller brush assembly to rotate. The mode switching member is configured for the cleaning device to be switched from a first motion state to a third motion state via a second motion state. A posture of the cleaning device in the first motion state is substantially identical to a posture of the cleaning device in the third motion state.

A method of training a machine learning, ML, algorithm to control a watercraft is described. The watercraft is a submarine or a submersible submerged in water. The method is implemented, at least in part, by a computer, comprising a processor and a memory, aboard the watercraft. The method comprises: obtaining training data including respective sets of environmental parameters and corresponding actions of a set of communicatively isolated watercraft, including a first watercraft; and training the ML algorithm comprising determining relationships between the respective sets of environmental parameters and the corresponding actions of the watercraft of the set thereof. A method of controlling a watercraft by a trained ML algorithm is also described.

A system for navigating a dynamic pool equipment unit is disclosed. The system comprises a wireless unit physically connected to the dynamic pool equipment unit deployed in a water pool, allowing the wireless unit to move with the equipment while partially out of the water. The wireless unit includes a first interface for communicating with the equipment unit via a first communication channel, and a second interface for intercepting wireless signals from external stations via a wireless communication channel. A controller navigates the equipment unit towards the external station(s) by measuring the received signal strength indicator (RSSI) of intercepted wireless signals, estimating the direction of the external station(s) based on RSSI analysis, and transmitting movement instructions to the equipment unit to advance in the estimated direction.

A path planning method for a pool cleaning robot is provided. The method includes: controlling a pool cleaning robot to move to a first position on a pool wall of a pool, the first position being a position corresponding to a waterline of the pool; controlling the pool cleaning robot to turn a first angle, so as to adjust a moving direction of the pool cleaning robot to be a first direction; controlling the pool cleaning robot to move in the first direction on the pool wall; when the pool cleaning robot has moved a first distance in the first direction, controlling the pool cleaning robot to turn a second angle, so as to adjust the moving direction of the pool cleaning robot to be downward along the pool wall; and controlling the pool cleaning robot to move downwards along the pool wall.

Intelligent algorithms and systems (vehicles and/or mechanisms) locate and extract economic sound concentrations of e.g. any combinations of nodules, manganese crusts and/or sulphide deposit, and separate uneconomic matter from valuable minerals by applying differences in electric and/or acoustic properties to differentiate economically valuable minerals from cost bearing unprofitable other matters (e.g. mud, gravel, rocks, organic matter), thus providing added profitability compared to existing mining machines. Complex and multiple sophisticated technological fields, including, but not limited to Geophysics, Advanced sensor technology (acoustic and electric parameter detection), Signal processing (feature extraction and pattern recognition), Machine learning/AI (classification algorithms and adaptive systems), Mechanical engineering (precision collection mechanisms), Real-time control systems (feedback-based operation), Economic modeling (dynamic threshold determination) are combined. Both independent systems and add-on vehicles to existing mining machines have been developed. Environmental impacts are minimized by the nature of the invented technical solutions. MS and/or AI methods and algorithms can be incorporated.

The present disclosure provides a cleaning device, including a cleaning device body, a liquid inlet portion, a liquid outlet portion, a filtering mechanism, and a mode switching member. The filtering mechanism includes at least a filtering box. The filtering box includes at least a filtering box opening for water surface cleaning, a filtering box roller brush assembly, and a drive gear. The filtering box roller brush assembly is disposed at the filtering box opening for water surface cleaning. The drive gear is configured to drive the filtering box roller brush assembly to rotate. The mode switching member is configured for the cleaning device to be switched from a first motion state to a third motion state via a second motion state. A posture of the cleaning device in the first motion state is substantially identical to a posture of the cleaning device in the third motion state.

A self-propelled pool cleaner may be operable in a swimming pool or spa. The self-propelled pool cleaner may identify a removal area in the swimming pool or spa and stop at the removal area. In certain circumstances, the removal area identified by the self-propelled pool cleaner may be in proximity to a waterline of the swimming pool or spa. Optionally, the removal area may be a generally horizontal surface.

The present application discloses a sweeping method of a swimming pool cleaning robot and a cleaning robot, the method including: acquiring map information about an area to be cleaned; planning a first sweeping path based on the map information, the first sweeping path meeting pre-set cleaning parameter requirements; controlling the cleaning robot to travel and perform a cleaning operation based on the first sweeping path; determining whether the cleaning operation is ended, and if so, controlling the cleaning robot to travel to a missed area so as to perform supplementary sweeping. This application can improve sweeping coverage rate and sweeping efficiency.