110results about "Target-seeking control" patented technology

An estimated target position is generated based on agent data received from an agent sensor system of a reinforcement learning (RL) agent and teammate data received from a plurality of teammate RL agents. An information metric reward is generated based on a confidence level associated with the estimated target position. The confidence level is based on the estimated target position and historical estimated target positions. A distance metric reward is generated based on an agent position and the estimated target position. A combined reward is generated based on the information metric reward and the distance metric reward. A movement action is generated for the RL agent based on the agent position, the estimated target position, and the combined reward in accordance with a multi-agent reinforcement learning (MARL) algorithm.

A system for neutralizing target aerial vehicles comprises a projectile launching mechanism that launches a projectile that supports a counter-attack unmanned aerial vehicle (UAV) having an aerial vehicle countermeasure. The counter-attack UAV can be folded in the projectile, and operable to unfold when separated from the projectile. The system comprises an aerial vehicle detection system comprising a detection sensor that detects a target aerial vehicle. Upon detection, the projectile launching mechanisms launches the projectile, and the counter-attack UAV is thereafter separated from the projectile to operate in flight to neutralize the detected target aerial vehicle with the aerial vehicle countermeasure. The projectile launching mechanism can comprise a movable platform comprising a plurality of projectiles and counter-attack UAVs, and can comprise a detection sensor to detect target aerial vehicles.

Light emitting device positional tracking systems and methods are provided. In one example, a method includes receiving images captured of a target location comprising a plurality of light emitting devices, where each of the light emitting devices has an associated blinking pattern. The method may further include detecting the blinking pattern for each of the light emitting devices in the images. The method may further include determining a classification for each of the light emitting devices based on its detected blinking pattern. The method may further include aligning a mobile platform with the target location based on the classifications of the light emitting devices. Related devices and systems are also provided.

Method for defending an area from vehicular threats in the area's vicinity, comprising detection of threat scenarios including vehicular threats in the area's vicinity in real time or near-real time; and / or controlling multiple interceptors to intercept at least some of the vehicular threats as detected; and / or using a machine learning hardware processor, trained on training data which may pair scenario outcomes to given mission plans which operated on given threat scenarios, to generate at least one mission plan for the interceptors, and / or to feed said mission plans to the interceptor control processor, in real time.

The system comprises a plurality of sensor systems, a counter drone, and a processor. A sensor system of the plurality of sensor systems comprises one or more sensors that are connected to a network. The counter drone is connected to the network. The processor is configured to receive an indication of a potential target from the plurality of sensor systems; generate a fused data set for the potential target, determine whether the potential target comprises the threat drone based at least in part on the fused data set; and in response to determining that the potential target comprises the threat drone, provide counter drone instructions to the counter drone.

An aircraft includes at least one processor, and at least one memory including computer program code, where the at least one memory and the computer program code are configured, with the at least one processor, to cause the aircraft to at least: in response receiving a first input, control the aircraft to effect an autonomous flight using a first parameter and a second parameter, and during the autonomous flight, in response to receiving a second input, modify the first parameter to obtain a modified first parameter, and control the aircraft to continue the autonomous flight based on the modified first parameter and the second parameter. The first parameter and the second parameter are associated with an autonomous process of the aircraft to achieve a task of the autonomous flight. The second parameter is unchanged.

A closed, self-contained ballistic apogee detection module for use in a projectile, such as a rocket, mortar round, or artillery round, fuses data from multiple built-in sensors, such as an accelerometer, a magnetometer, and a gyroscope, and processes the data using a microprocessor through a custom quaternion extended Kalman filter to provide accurate state and orientation information about the projectile so as to accurately predict apogee. The module outputs a signal indicating apogee detection or prediction which they projectile uses to initiate fuze arming, targeting control, airbody transformation, maneuvering, flow effector deployment or activation, payload exposure or deployment, and / or other mission activity. Because the system and method of the invention does not rely on external environmental data to detect apogee, it need not use a pressure sensor and can be completely sealed in and closed without requiring access to air from outside the projectile for barometric readings.

An autonomous unmanned aerial vehicle (10) comprising an airframe body; at least one flight system mounted to the airframe body(12); an onboard flight controller (18) which is adapted to control the or each flight system; a memory storage unit having machine-readable flight control instructions which are implementable by the onboard flight controller; an onboard feedback system which is communicatively coupled with the or each flight system to provide real-time internal flight characteristic data to the onboard flight controller(18); and an external feedback system adapted to receive and provide to the onboard flight controller (18) real-time external flight characteristic data; wherein the onboard flight controller (18) is arranged to receive mission parameter data from an external source, determine a pre- take-off flight plan in accordance with the mission parameter data, and dynamically implement the machine-readable flight control instructions to adapt the pre-take-off flight plan to control the or each flight system based on the real-time internal flight characteristic data and real-time external flight characteristic data.

The present invention discloses a reentry tracking guidance method for an aircraft based on a reinforcement learning algorithm, which is used to solve the problems of high dependence on the system model, poor adaptability and guidance performance in the prior art. The implementation scheme is as follows: establishing the continuous optimal control problem of aircraft reentry in the semi-speed coordinate system; transforming the continuous optimal control problem of aircraft reentry into a sequential convex optimal control problem; transforming the sequential convex optimal control problem into a sequential second-order cone programming problem; solving the sequential second-order cone programming problem to obtain the optimal bank angle of the aircraft; sampling the optimal bank angle trajectory to obtain a reference trajectory training data set; constructing a neural network and a reward function; using the training data set to perform offline training on the neural network until the cumulative reward converges to the maximum value to obtain a guidance network; obtaining the reentry guidance command of the aircraft online through the guidance network and tracking the target altitude in real time. The present invention has strong adaptability and high guidance accuracy, and can be used for rocket recovery.

A system comprising an unmanned aerial vehicle (UAV) (100) configured to transition (520) from a terminal homing mode (510) to a target search mode (530), responsive to an uplink signal (451) and / or an autonomous determination of scene change.

This invention provides a method for UAV obstacle avoidance trajectory planning based on digital elevation maps, including digital elevation map conversion, initial trajectory loading, trajectory pre-planning, and trajectory re-planning. Using this invention, UAV obstacle avoidance trajectory planning can fully consider terrain variations during low-altitude flight missions to achieve ground-hugging flight. Simultaneously, this method first performs offline trajectory pre-planning and uploads the planned trajectory to the flight controller to provide flight guidance, effectively solving the problem of low real-time performance. When obstacles or threat areas appear on the pre-planned trajectory, the method provided by this invention can find the vertices of obstacles with complex shapes, handle obstacle overlap issues, and thus quickly plan a flight path.

The present application relates to a device, a system, a method and a recording medium. A device is provided, comprising: an acquisition unit, which acquires a camera image from a camera whose direction can be controlled; a display control unit, which displays the camera image on a display screen; a detection unit, which detects a subject being viewed by a user in the display screen; and a direction changing unit, which changes the direction of the camera so that the subject does not leave the camera's camera area.

There is provided a toy, including a ball chasing robot including: a controller configured to receive power from a battery a plurality of infrared sensors configured to detect infrared radiation emitted by a satellite object, the plurality of infrared sensors connected to the controller; a motor configured to drive a wheel arrangement, the wheel arrangement including at least two drive wheels, wherein: the controller is configured to control the motor and wheel arrangement to drive the ball chasing robot towards the infrared radiation emitted by the satellite object detected by the plurality of infrared sensors; wherein the ball chasing robot includes a plurality of settings, including: a play setting, wherein the controller is configured to control the motor, such that the ball chasing robot is driven towards the source of the infrared radiation emitted by the satellite object, and a sleep setting wherein the controller is configured to turn off the plurality of sensors, wherein the sleep setting is entered automatically after a period of inactivity; and / or: a hard floor setting, wherein the motor is configured to drive the wheel arrangement at a first power setting, and a carpet setting, wherein the motor is configured to drive the wheel arrangement at a second power setting.

The present invention discloses a charging base, a robot recharging system and a recharging method based on a magnetic sensor, comprising a base, the bottom of which is provided with a preset charging position and a tracking guide element for robot recharging docking, which restricts the recharging robot to move forward within the signal sensing range generated by the tracking guide element, so that the recharging direction of the robot is guided to approach the center line of the tracking guide element until the robot moves to the preset charging position; wherein the signal sensing range is the range of the signal generated by the tracking guide element; the bottom of the base is provided at the lower end of the base in contact with the ground. When the robot enters the range of the signal generated by the tracking guide element, a circuitous recharging path is planned based on the straight line where the tracking guide element is located, thereby improving the guiding efficiency of the charging base, and compared with the prior art, the structure of the charging base is simple, and the recharging guide signal generated at the bottom of the charging base is less subject to interference.

A vehicle to transport a first drone and a second drone includes a controller. The controller is configured to release the first drone from the vehicle with instructions for the first drone to move a package container to a package container reception point. The controller is configured to release the second drone from the vehicle. The second drone is configured to provide data to the first drone. The data is related to a route from the vehicle to the package container reception point.

The present invention discloses a spacecraft wreckage search and rescue identification and tracking method based on a neural network, comprising: determining the theoretical landing point of the spacecraft wreckage, planning a search area, and controlling an aircraft to move to the search area; controlling the aircraft to move in the direction of the actual landing point of the spacecraft wreckage and capturing images in real time during the movement; using a multi-scale image neural network model to perform real-time identification and detection on the acquired images to determine whether there is spacecraft wreckage in the image; if so, adjusting the direction of the aircraft in real time according to the position of the detection target in the image, and controlling the aircraft to move above the detection target; determining whether the confidence level of the current detection result is greater than a preset threshold, and if so, confirming whether the detection target is spacecraft wreckage; if not or the detection target is not spacecraft wreckage, leveling the aircraft's camera and continuing to control the aircraft's movement. The present invention can achieve rapid search for spacecraft wreckage, effectively narrow the search range, and improve search efficiency.

The neutralisation system (1) comprises a drone (2) configured to be able to fly close to a target and transmit at least position information concerning the position of the target, the neutralisation system (1) also comprising at least one missile (6) capable of being guided towards the target in order to neutralise it and at least one control station (8), the control station (8) comprising a receiving unit (9B) capable of receiving at least the position information transmitted by the drone (2) and a display unit (10A) capable of displaying this information to an operator, the missile (6) being configured to be able to be guided towards the target by means of the position information received by the control station (8).

Systems, methods, and devices are provided herein for effecting autonomous flight of one or more unmanned aerial vehicles (UAV), and modifying the autonomous flight. In some instances, the autonomous flight may be effected via a first user input. The autonomous flight may modified by a second user input while maintaining the autonomous flight. The first and second inputs may be input at different user interfaces. Various parameters of the UAV, including a flight path, may be modified while maintaining the autonomous flight such that user is assisted and maintains a degree of control of the UAV during the autonomous flight.

A system including an image capture module and a handheld module. The image capture module includes a body; an image sensor; and a mechanical stabilization system comprising a first gimbal, a second gimbal, and a third gimbal connected to the body and configured to control an orientation of the image sensor of the image capture module relative to the body. The handheld module defines a slot that is keyed to the body of the image capture module. The image capture module, when located within the handheld module, has a low profile so that the third gimbal is protected from damage by the handheld module.

An aircraft position control system that keeps an aircraft at target coordinates in an inertial space with respect to a target landing point that moves includes an acceleration correction processing unit that, based on acceleration of the aircraft and an attitude of the aircraft, outputs first attitude correction acceleration for correcting the acceleration of the aircraft, a complementary filter that, based on the first attitude correction acceleration and inertial velocity of the aircraft, outputs second attitude correction acceleration in which a drift component included in the first attitude correction acceleration is removed, and a smoothing processing unit that, based on the second attitude correction acceleration and relative coordinates between the aircraft and the target landing point, outputs smoothed relative coordinates obtained by smoothing the relative coordinates.

The present invention discloses an automatic working system and a control method thereof. The automatic working system includes a self-moving device, a charging station for the self-moving device to dock and charge, and a rechargeable active signal beacon. The self-moving device and the active signal beacon are respectively provided with adaptable docking charging structures. When the active signal beacon has a charging requirement, the self-moving device charges the active signal beacon via the charging structure. The automatic working system of the present invention can conveniently charge the active signal beacon by using a simple charging structure by setting an adaptable charging structure on the active signal beacon for the self-moving device, so that when the active signal beacon needs to be charged, the self-moving device can charge the active signal beacon.

Systems and methods for detection of potential obstructions in a specified space. In some embodiments, the system and / or method comprises a robotic vehicle having one or more sensors configured to collect point cloud data from locations at or near a target drop zone. At least one processor performs an object detection analysis using the point cloud data to determine if there is an object in the target drop zone. To determine if there is an object or obstruction at the target drop zone, a volume of interest that is about the size of a payload can be generated for the target drop zone. If point cloud data indicates an object within the VOI, an obstruction exists and the payload is held rather than dropped at the target drop location.

The application discloses a differential AGV path following method and system based on improved pure tracking control, and the method comprises the following steps: obtaining a path trajectory by using cubic B-spline curve fitting; taking the midpoint of an axle as an AGV reference point; selecting a current trajectory reference point according to the AGV reference point; calculating a turning radius and planning a set speed according to the trajectory reference point; calculating a preview mark length according to the current speed difference between the left and right wheels of the differential AGV; calculating the coordinates of a preview point according to the path length from the starting point of the current path segment to the trajectory reference point, the current path segment length, the relationship between the current path segment and the path trajectory and the preview mark length; calculating the preview distance and the included angle between the AGV reference point and the trajectory reference point according to the coordinates of the preview point and the AGV reference point; and calculating the speeds of the left and right wheels of the differential AGV by using a kinematic model of the differential AGV. The method solves the problems that pure tracking control causes oscillation due to too short preview distance during straight-line driving and poor following due to too long preview distance during curve driving.

Systems and methods for modifying autonomous flight of one or more unmanned aerial vehicles (UAVs) are provided herein. In some instances, autonomous flight of a UAV can be implemented by first user input received at a first user interface. While autonomous flight is maintained, second user input received at a second user interface can modify autonomous flight of the UAV. Wherein the second user input modifies autonomous flight of the UAV during a duration of the second user input to assist a user and modify autonomous flight of the UAV during autonomous flight.

Guidance systems and methods for a material handling vehicle are provided. A guidance system can include a sensor and a processor unit. The sensor can be configured to measure a distance to an external object within a field of view of the sensor and output distance information corresponding to the measured distance. The processor can be configured to receive the distance information from the sensor, transform the distance information from a sensor coordinate system to a material handling vehicle coordinate system, perform pattern recognition on the transformed distance information to identify an aisle feature, create an aisle model based on the identified aisle feature, and determine a guidance instruction for the material handling vehicle based on the aisle model. The aisle model can include information corresponding to the aisle feature. The guidance instruction may be configured to align the material handling vehicle within an aisle.

A system for aerial neutralization of a detected target aerial vehicle comprises a plurality of counter-attack unmanned aerial vehicles (UAVs), and an aerial vehicle capture countermeasure coupling together the plurality of counter-attack UAVs, to intercept and capture a detected target aerial vehicle in a coordinated manner. The system comprises an aerial vehicle detection system comprising at least one detection sensor operable to detect the target aerial vehicle, and operable to provide command data to at least one counter-attack UAV for tracking and neutralizing the target aerial vehicle. The counter-attack UAVs and a net can be deployed from a movable base station, and the net can be carried in a low-drag configuration until the counter-attack UAVs operate to deploy or open the net. The counter-attack UAVs and systems may be autonomously operated. Associated systems and methods are provided.

A server node and method therein for assisting a first wireless communication device and a second wireless communication device to seek each other in a wireless communication network are disclosed. The server node inquires positioning and movement information of the first and second devices and obtains information on a relative position between the first and the second devices. The server node then sends instructions to at least one of the first and second devices based on the information on the relative position.

This application discloses a method, apparatus, device, and storage medium for locating a mobile robot charging station. The method includes: when a mobile robot in a recharging state receives an infrared recharging signal, controlling the mobile robot to move to a preset distance from the charging station; controlling the mobile robot to move in a preset direction and storing all frames of radar data collected during the movement; obtaining radar signature data of the charging station based on the stored radar data; and obtaining the location information of the charging station based on the radar signature data. This method solves the technical problems of existing charging station positioning methods, such as high cost, limited applicability, and poor positioning accuracy.

Disclosed is a process for collaborating between a fixed camera and an unmanned mobile device to enhance identification of an object of interest. A first point of view (POV) of a detected object is obtained, and it is determined, with a first level of confidence, that the detected first POV of the object matches a stored object of interest. Then, one or more camera-equipped unmanned mobile vehicles are identified in a particular direction of travel of the first detected object, and dispatch instructions and intercept information are then transmitted to the one or more camera-equipped unmanned mobile vehicles. Subsequently, a detected second POV of the first detected object is received via the one or more camera-equipped unmanned mobile vehicles.The captured second POV of the detected object is used to determine with a second level of confidence that the detected object matches the stored object of interest.