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 unmanned aerial vehicle (UAV) or drone executes a neural network to assist with detecting and responding to attacks. The neural network may monitor, in real time, the data stream from a plurality of onboard sensors during navigation and may communicate with a high-altitude pseudosatellite (HAPS) platform. For example, if the neural network detects a cyber-attack but determines that it does not interfere with external communications, it may shift navigation control of the drone to the HAPS.

Systems and methods of sensor data fusion including sensor data capture, curation, linking, fusion, inference, and validation. The systems and methods described herein reduce computational demand and processing time by curating data and calculating conditional entropy. The system is operable to fuse data from a plurality of sensor types. A computer processor optionally stores fused sensor data that the system validates above a mathematical threshold.

Systems and methods of sensor data fusion including sensor data capture, curation, linking, fusion, inference, and validation. The systems and methods described herein reduce computational demand and processing time by curating data and calculating conditional entropy. The system is operable to fuse data from a plurality of sensor types. A computer processor optionally stores fused sensor data that the system validates above a mathematical threshold.

A method for selecting an altitude changing phase route for an aircraft is presented. The method comprises receiving sequences of multivariate flight data from at least one prior flight, receiving a set of flight parameters for the aircraft including at least a total altitude change and a takeoff weight, and receiving a set of candidate altitude changing phase routes having candidate step profiles. For each candidate altitude changing phase route, a sequence of fuel burn quantities is predicted for the respective candidate step profile based on at least the sequences of multivariate flight data and the set of flight parameters. The fuel burn quantities are summed over the candidate altitude changing phase route to obtain an estimated fuel burn. A preferred candidate altitude changing phase route having a lowest estimated fuel burn is indicated.

A method for detecting anomalies in a swarm system comprises: collecting first movement data from multiple vehicles moving as a swarm in a first scenario; generating first training data based on positioning data and second training data based on multi-channel inertial sensor data from the first movement data; training a first learning model using the first training data and multiple second learning models using the second training data for each vehicle; receiving real-time second movement data from vehicles moving as a swarm in a second scenario; generating first input data based on positioning data from the second movement data; inputting the first input data into the first learning model to detect abnormal vehicles in real-time; generating second input data for abnormal vehicles based on inertial sensor data from the second movement data; and inputting the second input data into the corresponding second learning model to identify abnormal channels in the inertial measurement unit of abnormal vehicles.

A method and a system for rhythmic motion control of a robot based on a neural oscillator, including: acquiring a current state of the robot, and a phase and a frequency generated by the neural oscillator; and obtaining a control instruction according to the acquired current state, phase and frequency and a preset reinforcement learning network so as to control the robot. The preset reinforcement learning network includes an action space, a pattern formation network and the neural oscillator. A control structure designed by the present disclosure, which is composed of the neural oscillator and the pattern formation network, can ensure formation of an expected rhythmic motion behavior; and meanwhile, a designed action space for joint position increment can effectively accelerate the training process of rhythmic motion reinforcement learning, and solve a problem that design of the reward function is time-consuming and difficult in learning with existing model-free reinforcement learning.

A method for guiding an autonomous aircraft, the aircraft includes an automatic pilot, a plurality of sensors and an imaging unit, the aircraft being configured to fly over a geographic zone comprising overflight prohibited zones, the guidance method can advantageously comprise a phase of real flight of the autonomous aircraft by using a given guidance law, comprising the following steps: determining a current state of the autonomous aircraft; determining an optimum action to be executed by using a neural network receiving the current state; determining a plurality of control instructions compatible with the guidance law based on the optimum action to be executed; transmitting to the automatic pilot the plurality of control instructions, which provides a new state of the autonomous aircraft.

Provided is a model parameter learning method by which a model parameter of a learning model used in control of a moving body having movement constraints can be appropriately learned. In this model parameter learning method, a model prediction control algorithm reflecting movement constraints of a robot 1 is used to calculate a time series of learning speed commands such that the movement trajectory of the robot 1 tracks the time series of a movement trajectory of a first pedestrian 5; and a model parameter of a CNN model is learned by an error back propagation method, the CNN model using learning data including the learning speed commands time series as input and outputting a time series of speed commands for a first moving body.

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.