A method for controlling a motion of a multi-jointed bionic dolphin relates to a technical field of damage detection using a bionic robot. The method comprises: constructing a three-dimensional model and a three-dimensional model in computational domain of the multi-jointed bionic dolphin, and performing pre-processing; importing the model file after the pre-processing into analysis software for computational fluid dynamics for the hydrodynamic simulation to obtain a thrust-time curve and a hydrodynamic curve under a specified underwater working condition, then finding a difference, and fitting to obtain velocity-resistance fitting curves; performing a kinetic analysis, and deducing a kinetic model; completing kinetic coupling to obtain kinetic parameters according to the kinetic model, the thrust-time curve, and the velocity-resistance fitting curves; and controlling output torques by a pulse width modulation (PWM) technique.

In some embodiments, provided is a robot for water tunnel inspection, comprising: (a) a shell, comprising an upper shell and a lower shell; wherein the upper shell and the lower shell are sized and shaped to match each other, together defining a closed cavity therewithin; (b) a camera system, configured to capture an image or video of a field of view of surrounding; (c) a lighting system, configured to provide illumination at least partially for the field of view; (d) a propulsion system, configured to provide propulsion force to the robot in water; and (e) a controlling system, configured to provide power and control operation of the robot, wherein the robot is configured to float on water and to have a center of gravity positioned lower than geometric center. Other example embodiments are described herein. In certain embodiments, the robots provide safe and efficient tunnel inspections without human operation.

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 station keeping waterfowl system includes at least one self propelled station keeping waterfowl decoy and a homing buoy each having water resistant housings, with at least a portion of the decoy housing having a form of a waterfowl. The decoy and buoy each include batteries, microprocessors, and power switches. The decoy includes a motor driven propeller, a motor driven rudder, and a receiving array of antennae for radio direction finding and radio ranging to the buoy. The receiving array is a T-array of antennae comprising a first transverse linear array and a second longitudinal linear array. The homing buoy emits a homing signal and the one or more waterfowl decoys autonomously navigate to remain within a predetermined radius around the buoy. The system includes a simple handheld controller which preferably comprises no more than two switches or buttons.

A reservoir area water bloom rapid monitoring method and a device based on unmanned aerial vehicle swarm coordination are provided. Through the local updating quantification technology, the communication volume between UAV and central server is compressed and the communication efficiency of federated learning is optimized on the premise of ensuring the accuracy of the reservoir area water bloom monitoring model. The local update quantification defines the loss function queue for UAV, and uses the ratio of historical and current loss functions to reasonably quantify the upstream model update. According to the disclosure, the problems that pictures collected by unmanned aerial vehicle swarm are difficult to upload in large quantities, the communication volume required for reservoir area water bloom monitoring is too large, and the reservoir area water bloom monitoring model converges slowly due to frequent communication are solved.

The navigation support device includes processing circuitry. The processing circuitry generates a set of candidate values for a plurality of parameters associated with an automatic berthing control of a ship, performs simulations of a berthing behavior of the ship based on each set of candidate values for the plurality of parameters, performs evaluations of the berthing behavior for each set of candidate values for the plurality of parameters based on results of the simulations, and determines a control parameter associated with the automatic berthing control from the set of candidate values for the plurality of parameters, based on the results of the evaluation of the berthing behavior.

The present disclosure discloses a method for target assignment and route planning for multi-agent unmanned surface vehicles (USVs). Task information is transmitted to a task allocator, which identifies unassigned targets and available USVs. Based on a comprehensive cost function considering navigation distance and turning penalties between targets and USVs, a target is assigned to each USV A path planner then generates a smooth waypoint sequence for each assigned USV and target pair, serving as the navigation path. During navigation, a navigation controller constructs a velocity optimization model according to cooperative collision avoidance and maritime boundary constraints, and controls the USVs in real-time to navigate along the waypoint sequences. The present disclosure achieves efficient matching of multiple targets and multi-agent USVs, generates smooth navigation paths satisfying constraints, and enables intelligent navigation control while meeting cooperative collision avoidance requirements and maritime boundary constraints.

The present disclosure provides an information interaction method, system, and apparatus, a storage medium, and an electronic device. The method includes: obtaining a type of a target environment in which a target robot currently operates, where the type of the target environment includes an underwater environment and a non-underwater environment; determining a target communication mode based on the type of the target environment, where the target communication mode is used to indicate a communication mode between the target robot and a charging station; and controlling the target robot to establish a communication connection with the charging station in the target communication mode and controlling the target robot to perform information interaction with a target terminal via the charging station.

A hybrid, redundant, fail-safe architecture provides a unified fail-operational framework for autonomous agents operating across physical and virtual domains. The system employs a multi-modal data source suite, an adaptive hybrid data fusion module, and an intelligent decision-making module. A novel closed-loop interaction enables a health monitoring module that detects an incipient fault in a data source by monitoring ancillary performance metrics. Upon detection, the module generates a fault signature, including a quantitative prognostic estimate of a future failure time, and transmits it to an adaptive data fusion module. The fusion module proactively reconfigures its state estimation algorithm by decreasing reliance on the degrading data source in proportion to the prognostic estimate. This preemptive compensation ensures the system maintains a high-integrity environmental model and achieves true fail-operational continuity. The architecture is applicable to numerous embodiments providing a universal solution for proactive fault management and system resilience.

A method for steering an Autonomous Underwater Vehicle along an object buried below a seabed: the AUV being equipped with at least one acoustic transmitter for generating acoustic signal towards the buried object and the seabed; arranging a first sensor assembly flush with the AUV hull of the starboard side of the AUV for recording reflected acoustic signal from the buried object and the seabed, arranging a second sensor assembly flush with the AUV hull of the port side of the AUV for recording reflected acoustic signal from the buried object and the seabed.