Systems and methods for mitigating cable twists for underwater cleaners are provided. Cable twist mitigation logic is stored in a memory associated with a pool or spa cleaner, and controls operation of the cleaner to mitigate cable twists. A sequence of cleaner orientations is retrieved from memory and compare to one or more pre-defined sequences known to contribute to cable twist. If the sequence of cleaner orientations matches the one or more pre-defined sequences, a twist angle accumulator is incremented by a pre-defined twist angle corresponding to the one or more pre-defined sequences. The system determines whether the cleaner is turning on a surface of a pool or spa, and if so, controls turning of the cleaner using an accumulated angle stored in the twist angle accumulator to mitigate cable twists. A user-definable bias value could also be applied by the system to further mitigate cable twists.

The present invention discloses an intention-driven reinforcement learning-based path planning method, including the following steps: 1: acquiring, by a data collector, a state of a monitoring network; 2: selecting a steering angle of the data collector according to positions of surrounding obstacles, sensor nodes, and the data collector; 3: selecting a speed of the data collector, a target node, and a next target node as an action of the data collector according to an greedy policy; 4: determining, by the data collector, the next time slot according to the selected steering angle and speed; 5: obtaining rewards and penalties according to intentions of the data collector and the sensor nodes, and updating a Q value; 6: repeating step 1 to step 5 until a termination state or a convergence condition is satisfied; and 7: selecting, by the data collector, an action in each time slot having the maximum Q value as a planning result, and generating an optimal path. The method provided in the present invention can complete the data collection path planning with a higher probability of success and performance closer to the intention.

An automatic berthing system and method for a vessel are provided. The automatic berthing system comprises a controller, controlling the vessel; an input part, receiving an input to perform the automatic berthing mode; at least one peripheral sensor, detecting position information and speed information of another vessel other than the vessel to determine whether a wake caused by the another vessel has influence on the vessel. The controller performs an automatic berthing control when the input to perform the automatic berthing mode is received until the vessel reaches a berthing position, and the controller stops the automatic berthing control when the another vessel is located within a predetermined distance from the vessel based on the position information.

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.

The present disclosure relates to the technical field of decision-making of unmanned surface vehicles, and provides a brain-like memory-based environment perception and decision-making method and system for an unmanned surface vehicle. The method includes: obtaining an image of an environment in front of an unmanned surface vehicle; and inputting the image of the environment into an environment perception and decision-making model of the unmanned surface vehicle, and outputting an action instruction, where the environment perception and decision-making model of the unmanned surface vehicle includes an image feature extractor, a Bidirectional Encoder Representations from Transformers (BERT) model, a fully connected layer, a short-term scene memory module, and a long-term memory module that are connected in turn; the BERT model extracts an image feature representation containing a text feature from an image feature. The present disclosure improves accuracy of decision-making of an action.

A device for relaying an engine control message includes at least one memory and at least one processor, wherein the processor determines whether a navigation mode of a ship is a manual navigation mode or an autonomous navigation mode based on a signal received from an autonomous navigation processing device, outputs a first message to an internal communication network in response to the navigation mode of the ship being the manual navigation mode, generates a second message by converting the first message stored in the at least one memory, and then outputs the second message to the internal communication network in response to the navigation mode of the ship being the autonomous navigation mode.

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.

An optimized coverage-path planning method for a single unmanned surface mapping vessel (USMV) is implemented with a system including a computer processor executing a computer program loaded in a storage device and implanting the method. The method includes rasterizing and initializing an environmental map, and an unmanned vessel outputting position data and obstacle data according to the environmental map so that path planning is started to provide a target point to the unmanned vessel. In case of tripping in a local optimum at a current-level map for the target point, the map level is updated in an ascending order until the highest level, in order to identify a map level in which the target point is found.

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.