A computer-implemented method for generating control parameters for auto-docking of a marine vessel, and to a control unit for executing the method, to a marine vessel including the control unit, and to a corresponding computer program product.

Provided herein are system, apparatus, article of manufacture, method and/or computer program product aspects, and/or combinations and sub-combinations thereof, for artificial intelligence in mobile autonomous robotics and autonomous mobile platforms. An example aspect operates by a method of using a general-purpose robotics operating system (GPROS) with generative pre-trained transformers (GPT) (GPROS-GPT) model. The method includes training the GPROS-GPT model and querying the GPROS-GPT model to generate GPROS configuration data and service extension files. The method further includes loading the configuration data and the service extension files into a GPROS-based application and using the GPROS-based application to operate a GPROS-based robot or a GPROS-based autonomous vehicle.

A camera-based and direct observation based relative position determination method for multiple unmanned aerial, naval and ground vehicles is provided. The method calculates the relative position between the relevant vehicles in multiple UAV, UNV and UGV systems.

A wind condition learning device according to the present disclosed technique includes: an input terminal to which a learning data set is input; and a calculator including AI to perform learning on the basis of the learning data set, in which one piece of the learning data set is a wind condition altitude distribution model value following a power law on an inflow side, and the other piece of the learning data set includes a wind speed average value, a wind speed maximum value, turbulence energy, or turbulence intensity in a wind condition distribution of an environmental space obtained by simulation.

The present application provides an unmanned aerial vehicle (UAV)-assisted federated learning resource allocation method for an UAV-assisted federated learning wireless network scenario, which takes into account the effect of altitude of the UAV on the coverage range in order to achieve an equilibrium between the total energy consumption of the user and federated learning performance. The method simultaneously considers the total energy consumption of the user and the federated learning performance, defines the total cost function of the system. The total cost function consists of weighting of the total energy consumption of the user and the inverse of the number of users participating in federated learning, and forms the optimization problem with a minimization of the total cost function.

A control system includes one or more processors configured to perform system control for controlling a system including a mobile robot configured to move autonomously and to be operated by a user based on a feature of a mobile body present around an operation interface configured to operate the mobile robot. The system control includes change control for changing operation limitation on the operation interface when the feature satisfies a predetermined condition.

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.

Methods and Internet of Things (IOT) systems for smart gas pipeline maintenance based on human-machine linkage are provided. The IoT system includes a smart gas user platform, a smart gas service platform, a smart gas pipeline network safety management platform, a smart gas pipeline network sensor network platform, and a smart gas pipeline network object platform. The method includes determining a first cycle based on data of a pipeline to be maintained, a feature of a maintainer, and/or a feature of a maintenance robot, obtaining, through a maintainer terminal and/or the maintenance robot, first feedback data based on the first cycle, determining, based on the first feedback data and the data of the pipeline to be maintained, a maintenance parameter and sending the maintenance parameter to the maintainer terminal, and generating, based on the maintenance parameter, a control instruction and sending the control instruction to the maintenance robot.

Disclosed herein is a method of detecting stalled state of a dynamic pool equipment unit, comprising receiving a plurality of movement features relating to a dynamic pool equipment unit deployed in a water pool which are captured during a predefined sampling window and comprise (1) motion features of the pool equipment unit, and (2) operational features of electric motor(s) of the pool equipment unit, determining a movement pattern of the pool equipment unit using one or more statistical models applied to the plurality of movement features which are trained to estimate a stalled state of the pool equipment unit in which the pool equipment unit is pitched up and unable to advance on a slopped obstacle in the water pool, and causing the pool equipment unit to stop attempted advance in a current direction responsive to determining that the pool equipment unit is in the stalled state.

Apparatuses for operating a remotely operated vehicle (ROV) over a communications network that includes at least one sparse datalink that hampers remotely controlling the ROV in real time or near real time. In some embodiments, remote operation of the ROV is enabled by locating a local awareness/autonomy edge-processing node on the ROV side of the sparse datalink(s) and configuring the local awareness/autonomy edge-processing node to provide the ROV with local control based on remote supervisory commands received over the sparse datalink(s). In some embodiments, the local awareness/autonomy edge-processing node maintains situational awareness information regarding the environment local to the ROV that autonomy algorithms on the local awareness/autonomy edge-processing node use in controlling the ROV to perform one or more tasks within the need for real time or near real time remote control. Related methods, software, and systems are also disclosed.