435 results about "Unmanned surface vehicle" patented technology

The invention discloses a lane changing trajectory planning method for an unmanned vehicle based on vehicle-to-vehicle cooperation. In consideration of the vehicle lane changing complexity in an unmanned driving environment and characteristics of frequent turning and lane changing in urban road sections, a vehicle-to-vehicle cooperation policy and a trajectory planning method during the lane changing process are provided. With a lane changing cooperation policy and a quintic polynomial trajectory planning method as a basis and with vehicle kinematics and comfort as control conditions, a main vehicle lane changing trajectory optimization model under different cooperation degrees of a rear vehicle in the target lane is built; and besides, in consideration of defects of traditional elliptic and circular vehicle simulation models, through analyzing a boundary relationship between a possible collision point and a vehicle contour, a collision avoidance boundary condition under a rectangular vehicle model is built, and the vehicle lane changing trajectory model is tested through a scene. Under the vehicle-to-vehicle cooperation condition, safe vehicle lane changing under the unmanned driving environment can be completed, and requirements of lane changing comfort and kinematics can be met.

A communications system and method utilizes an unmanned surface vehicle (USV) capable of collecting data about an environment in which the USV resides. At least one micro-aerial vehicle (MAV), equipped for unmanned flight after a launch thereof, is mounted on the USV. Each MAV has onboard radio frequency (RF) communications. Each MAV launched into the air transmits the data collected by the USV using the MAV's RF communications.

The invention relates to the field of unmanned aerial vehicles, and discloses a remote control method and equipment for the unmanned aerial vehicle and the unmanned aerial vehicle. According to the remote control method and equipment for the unmanned aerial vehicle and the unmanned aerial vehicle, operators just need to trigger a wireless remote control to send a first command, a second command and a third command so that the unmanned aerial vehicle can carry out point-surrounding flight monitoring around the physical coordinate of an interest point according to an adjusted flight speed and an adjusted point-surrounding flight radius, the second command is independently used for adjusting the surrounding radius, the third command is independently used for controlling the surrounding speed, and therefore the operating skill requirement for the operators is lowered, and the experience of the operators is improved.

The invention discloses a method in a boat control field and especially relates to the sliding mode-reverse step double loop trace tracking control method of an underactuated unmanned surface vehicle.The method comprises the following steps of firstly, establishing a three-degree-of-freedom motion mathematical model of the heading, the surging and the swaying of the unmanned surface vehicle; then, through an integrated pose sensor, measuring the current position information of the unmanned surface vehicle, combining the real-time position and the reference trace of the unmanned surface vehicle, calculating an error under a boat body coordinate system; and then, designing a kinematic loop trace tracking controller based on a backstepping method, and designing a dynamic loop trace trackingcontroller based on a sliding mode control algorithm. Through a sliding mode-reverse step double loop trace tracking controller, the trace tracking control of the unmanned surface vehicle Is realized,the unmanned surface vehicle can track a linear trace, and the stability and accuracy of unmanned surface vehicle navigation can be increased.

A seismic survey system records seismic signals during a marine seismic survey. The system includes first and second clusters, each including a set of autonomous underwater vehicles (AUVs); each cluster being associated with a corresponding first or second unmanned surface vehicle (USV); and a central control unit located on a floating platform and configured to control the first and second USVs. The first USV follows its own path and the first cluster follows the first USV independent of the second USV or the second cluster.

The present invention relates to a target tracking cooperative control system and method based on multiple unmanned surface vehicles. The system is formed by connecting a shore-based global location host and a single unmanned surface vehicle control system through a wireless communication module. The method comprises the operation steps of: 1) a formation generation process: employing an auction algorithm to find a multi-target distribution scheme of the multiple unmanned surface vehicles with the maximum income of an unmanned surface vehicle group; 2) motion of the unmanned surface vehicles to perform geometric path planning from any initial state to a target point; and 3) prediction of a target motion track through adoption of a prediction model based on a particle swarm to replace communication abnormal data and perform formation track tracking. The method reduces the calculation amount of the multiple auction processes, achieves the real-time demands of task distribution of the unmanned surface vehicles, employs the path planning method based on the geometric method and the track tracking method based on the neural network to meet the timeliness and the accuracy requirements ofsingle-vehicle track tracking control, employs the motion track predicted by employing the particle swarm optimization to perform compensation, improves the tracking capacity of the unmanned surfacevehicles in the limitation of the communication condition and allows the formation tracking to have high reliability and stability.

The invention belongs to the field of the environment perception and autonomous obstacle avoidance of quadrotor unmanned aerial vehicles and relates to a depth Q learning-based UAV (unmanned aerial vehicle) environment perception and autonomous obstacle avoidance method. The invention aims to reduce resource loss and cost and satisfy the real-time performance, robustness and safety requirements ofthe autonomous obstacle avoidance of an unmanned aerial vehicle. According to the depth Q learning-based UAV (unmanned aerial vehicle) environment perception and autonomous obstacle avoidance methodprovided by the technical schemes of the invention, a radar is utilized to detect a path within a certain distance in front of an unmanned aerial vehicle, so that a distance between the radar and an obstacle and a distance between the radar and a target point are obtained and are adopted as the current states of the unmanned aerial vehicle; during a training process, a neural network is used to simulate a depth learning Q value corresponding to each state-action of the unmanned aerial vehicle; and when a training result gradually converges, a greedy algorithm is used to select an optimal action for the unmanned aerial vehicle under each specific state, and therefore, the autonomous obstacle avoidance of the unmanned aerial vehicle can be realized. The method of the invention is mainly applied to unmanned aerial vehicle environment perception and autonomous obstacle avoidance control conditions.

The present invention provides an accurate track tracking control method based on a finite time expansion state observer. The method comprises the following steps of: establishing a mathematical modeland a kinematic equation representing current unmanned ship motion features, designing a combined nonsingular rapid terminal sliding-mode control law according to the unmanned surface ship motion tracking errors and a nonsingular rapid terminal sliding-mode surface, designing a finite time expansion state observer according to the unmanned ship motion features, and designing an accurate track tracking control law according to the combined nonsingular rapid terminal sliding-mode control law and the finite time expansion state observer. Through design of the finite time expansion state observer, the lump interference comprising external interference and a complex nonlinear term can be observed by the finite time to a small enough range to avoid the limitation of the approximation observation. Through the designed combined nonsingular rapid terminal sliding-mode control law and the nonsingular rapid terminal sliding-mode unmanned ship track tracking controller, the accurate track tracking control method achieves the accurate track tracking control performance in a complex external interference.

The invention discloses a vision based steady object tracking control system for a rotor UAV (unmanned aerial vehicle). The system comprises an airborne part, wherein the airborne part comprises a flight control unit of the rotor UAV, an ultrasonic ranging module and a visual navigation module; the visual navigation module comprises an image processor, a camera module and a two-axis brushless pan-tilt unit which is fixed under the rotor UAV; the camera module and the ultrasonic ranging module are both fixed on the two-axis brushless pan-tilt unit, and a lens of the camera module and the ultrasonic ranging module are both parallel to the horizontal plane. The invention further discloses a vision based steady object tracking control method for the rotor UAV. The airborne visual navigation module is used for automatically detecting a target characteristic indication and solving the practical relative error distance between the rotor UAV and a target object, and the problem that the rotor UAV cannot steadily track a moving object under the condition that the target object is shielded is particularly solved.

The invention provides an under-actuated unmanned surface vehicle self-adaptive trajectory tracking control device and method. The device comprises a reference path generator, a state sensor, a differential converter, a parameter estimator, a virtual controller and a longitudinal thrust and bow steering torque controller. According to the unmanned surface vehicle actual position and course angle collected by the state sensor (2) and the reference position and reference course angle information generated by the reference path generator (1), the new state variable is obtained through the differential converter (5), the new state variable and the speed and angle speed information collected by a sensor (4) are transmitted to the parameter estimator (8) and the longitudinal thrust and bow steering torque controller (12), a control instruction is obtained through calculation to drive an execution mechanism, and the longitudinal thrust and bow steering torque of an unmanned surface vehicle are adjusted. According to the device and method, the unmanned surface vehicle can reach the specific position within specific time at specific speed. Due to the under-actuated unmanned surface vehicle, energy consumption and manufacturing cost of a system can be lowered, and the weight of the system is reduced.

The invention relates to the technical field of unmanned surface vehicle path planning, in particular to an unmanned surface vehicle path planning method based on a neighborhood intelligent water drop algorithm. The method comprises the steps of 1, performing environment modeling on unmanned surface vehicle path planning; 2, performing off-line global path planning in an operation area grid matrix by utilizing the intelligent water drop (IWD) algorithm according to a known unmanned surface vehicle operation area static obstacle, an advancing goal and path evaluating function so as to obtain a global off-line optimum path. The problem that the method is stagnated and low in convergence rate caused by the fact that a basic IWD method is easily caught in local optical solution is improved, and an optical solution adjacency expansion mechanism and a global optimum stressing mechanism are introduced on the basis of the basic IWD method to obtain an NIWD method, so that prematurity caused by the fact that the method is caught in local optimum is avoided, and the optimizing convergence rate of the method is improved.

The invention relates to the technical field of aircrafts, and particularly provides an unmanned aerial vehicle multi-distance obstacle avoidance method and an obstacle avoidance system. According tothe invention, firstly, a flight path of the unmanned aerial vehicle is set. Secondly, the obstacle information on a plurality of distance levels in the flight space of the unmanned aerial vehicle isacquired. At the same time, the current flight state information of the unmanned aerial vehicle is acquired in real time. Thirdly, a flight obstacle avoidance plan is formulated according to the obstacle information and the current flight state information. Finally, the unmanned aerial vehicle performs the obstacle avoidance flight according to the flight obstacle avoidance plan. According to theinvention, a plurality of obstacle avoidance mechanisms are applied in parallel, wherein the predictive obstacle avoidance can be realized especially for large barriers such as buildings existing on flight paths, as well as moving barriers within the range of a moderate distance. The defects caused by purely relying on a short-distance obstacle avoidance mechanism are fully overcome.

The invention belongs to the field of unmanned ship global path planning and particularly relates to an unmanned ship global path multi-target planning method based on the improved ant colony algorithm. The method comprises steps of establishing a marine environment map model by utilizing a Maklink graph theory; improving a path heuristic information strategy to obtain a path average value; designing an ant pheromone volatilization adaptive adjustment strategy; designing a strategy combining local pheromone updating and global pheromone updating; improving the state transition probability of anext node searched by an ant colony through a heading angle deviation factor of an unmanned ship; and designing an evaluation function by integrating the requirements of the shortest global path length, the least optimization iteration times of the improved ant colony algorithm, the lowest path smoothing coefficient and the like. The method is advantaged in that multiple targets such as a globalpath distance of marine navigation of an unmanned surface vehicle, the iteration frequency of optimizing the global path by improving the ant colony algorithm and the smoothness coefficient of the planned global path are comprehensively considered, the optimal global path of marine navigation of the unmanned surface vehicle is finally planned, and the method has relatively high safety.

The invention discloses a novel general obstacle avoidance module for a UAV (unmanned aerial vehicle). The module consists of a range sensor, an inertial sensor, a single-chip microcomputer and a wireless communication module, wherein a connecting structure is as follows: the range sensor, the inertial sensor and the wireless communication module are connected with the single-chip microcomputer respectively; the single-chip microcomputer is also connected with a UAV flight control and a remote-control receiver respectively; the range sensor is used for detecting the distance between the UAV and an obstacle; the inertial sensor is used for compensating a distance error caused by inclination of the UAV during flight; the wireless communication module is responsible for transmission of the flight state of the UAV; the single-chip microcomputer is used for processing data. The module has the benefits that the module is simple in structure, stable, reliable, higher in universality and capable of effectively preventing the UAV from colliding with the obstacle and can be mounted on various UAVs through simple setting.

The invention discloses a preset performance control method for an uncertain under-actuated unmanned surface vehicle (USV) system. The preset performance control method specifically comprises the steps of establishing a USV dynamic model, including kinematics and dynamics models; processing tracking error constraints by proposing a preset performance control method; processing a virtual controllerby applying the dynamic surface control technology; learning the uncertain dynamics of the system online by using the neural network technology; and designing a tracking controller that meets the requirements by applying the Lyapunov stability theory. The preset performance control method of the invention can avoid the singular problem of controller design and can satisfy the pre-specified tracking error transient and steady state performance. The uncertain dynamics of the system are learned online by applying the adaptive neural network control technology and the controller is designed to complete the trajectory tracking control objective and the practicality of the control method is improved.

The invention provides a control method of accurate landing of an unmanned aerial vehicle. The control method is used for controlling the unmanned aerial vehicle to reach a present landing point. The control method is characterized by comprising the following steps that 1 a sound source is placed at the landing point, regular-tetrahedron-shaped microphone arrays are placed on the unmanned aerial vehicle and a signal amplification circuit and a filtering circuit are arranged at the signal output end of each microphone; 2 GPS navigation is used for controlling the unmanned aerial vehicle to reach the range which is ten meters away from the landing point; 3 a processor on the unmanned aerial vehicle is used for calculating delay generated when sound source signals reach the second microphone, the third microphone, the fourth microphone and the first microphone; 4 the yaw angle and the pitch angle of the unmanned aerial vehicle are calculated through the processor according to the spatial geometric relationship of the sound source and the microphone arrays and delay values; 5 the unmanned aerial vehicle is navigated to the position over the landing point according to the yaw angle and the pitch angle; 6 an air pressure height sensor is used for enabling the unmanned aerial vehicle to be landed at the landing point accurately.

The invention provides a clustering control system and method for unmanned aerial vehicles. The method comprises the steps that all the unmanned aerial vehicles are subjected to task planning, task planning content is sent to a main unit and sub units, position and speed information of the main unit is sent to other sub units when the main unit executes tasks during flight, and correspondingly thesub units fly along with the main unit according to task planning. Compared with the prior art, the clustering control system and method have the advantages that an operator can control multiple unmanned aerial vehicles at the same moment, and the tasks such as formation performance, large-range search or surveying and mapping which cannot be achieved by a single unmanned aerial vehicle can be completed.

The invention discloses a UAV (unmanned aerial vehicle) landing method and system. The method comprises steps as follows: the flight height of a UAV is acquired; a template image corresponding to the flight height is acquired according to the flight height of the UAV; a scene picture is shot by a camera device of the UAV, and the shot picture is acquired; the shot picture is matched with the template image corresponding to the flight height, and the position where the UAV deviates from the target landing site is obtained; the UAV is controlled to fly to the target landing site on the basis of the position where the UAV deviates from the target landing site and controlled to land at the target landing site. By means of the UAV landing method and system, the UAV accurately lands without GPS positioning or position estimation.

The invention belongs to the field of image identification, and particularly relates to a classification and identification method for a foggy water surface image and a clear water surface image. The method comprises the steps of acquiring water surface images to be identified; establishing a water surface image database; extracting features of the water surface images; training and learning classification and identification features of the fog of the water surface images; and identifying the foggy water surface image to be identified and the clear water surface image to be identified. The method can greatly improve the intelligence of a visual system of a water surface aircraft. The features can be extracted simply, few features for identification are available, and the identification rate is high; and being used for earlier stage processing of the visual system of water surface ship or an unmanned surface vehicle, the method can adaptively judge water surface weather environment, and can effectively improve the performances of post-defogging, and target detection, tracking and identification.

The invention provides an unmanned surface ship optimal trajectory tracking control method based on a reinforced learning method. The unmanned surface ship optimal trajectory tracking control method based on the reinforced learning method comprises the following steps: S1, establishing an unmanned surface ship system mathematical model and a desired trajectory system mathematical model without considering a disturbance condition; S2, establishing a dead zone mathematical model, so as to obtain an unmanned surface ship system mathematical model introducing the dead zone; and further obtaining an tracking error system; S3, establishing an identifier system; and S4, evaluating whether the control strategy meets the requirements or not through an optimal cost function; if the control strategymeets the requirements, outputting the control strategy to the unmanned surface ship system as an optimal control strategy; and if the control strategy does not meet the requirements, evaluating whether the regenerated control strategy meets the requirements or not through the optimal cost function, and repeating the above process until the optimal control strategy is obtained and output to the unmanned surface ship system. The invention solves the technical problem that the unmanned ship optimal control method in the prior art does not consider the dead zone or completely unknown system dynamics, and the accuracy and robustness of the control system are reduced.

The invention relates to a vehicle laying and retrieving method, in particular to an unmanned surface vehicle laying and retrieving method.According to the unmanned surface vehicle laying and retrieving method, the traditional mode that when an unmanned surface vehicle is laid and retracted, manual operation on the unmanned surface vehicle is needed is changed, and meanwhile damage brought by cage-type retrieving to the unmanned surface vehicle is avoided.The laying and retrieving method is easy to operate, short in laying and retrieving time and high in success rate.

The invention discloses a quantum ant colony algorithm-based unmanned surface vehicle navigation path planning method and belongs to the unmanned surface vehicle and navigation path planning technicalfield. According to the method of the invention, a quantum ant colony algorithm is adopted to solve the navigation path planning problem of an unmanned surface vehicle. The method includes the following steps that: the static environment model of a navigation area is established according to an obstacle distribution condition in a geographic information database; the navigation path planning comprehensive evaluation function of the unmanned surface vehicle is established according to the objective function and constraints of the navigation path planning of the unmanned surface vehicle; and the quantum ant colony algorithm is adopted to perform global static navigation path planning on the unmanned surface vehicle. The algorithm provided by the invention not only can reflect the high efficiency of quantum computing, but also maintain the good searching capacity and strong robustness of the ant colony algorithm, and therefore, the calculation speed of the algorithm can be can improved.With the method adopted, the optimal navigation path of the unmanned surface vehicle under a complex sea condition can be obtained effectively and quickly, and therefore, the optimal navigation path can be obtained under a premise that the unmanned surface vehicle satisfies the constraints, and thus, mission requirements can be satisfied.

Systems and methods for controlling an unmanned aerial vehicle (102,152,900,1000) within an environment (100,150) are provided. In one aspect, a system comprises one or more sensors (1008) carried on the unmanned aerial vehicle (102,152,900,1000) and configured to receive sensor data of the environment (100,150) and one or more processors (1100). The one or more processors (1100) may be individually or collectively configured to: determine, based on the sensor data, an environmental complexity factor representative of an obstacle density for the environment (100,150); determine, based on the environmental complexity factor, one or more operating rules (602a-f) for the unmanned aerial vehicle (102,152,900,1000); receive a signal indicating a desired movement of the unmanned aerial vehicle (102,152,900,1000); and cause the unmanned aerial vehicle (102,152,900,1000) to move in accordance with the signal while complying with the one or more operating rules (602a-f).

The embodiment of the invention provides an unmanned aerial vehicle and a method and device for controlling the operation of the unmanned aerial vehicle. The method includes the following steps that operation flight-path information is obtained, wherein the operation flight-path information includes the geographic location information and operation sequence of a plurality of measuring points; theunmanned aerial vehicle is controlled to operate according to the operation sequence, and in the operation process, the variation trend between the current measuring point and the next measuring pointis determined; if the variation trend accords with the preset condition, the unmanned aerial vehicle is controlled to fly from the current measuring point to the next measuring point at a constant speed according to the set speed to operate; if the variation trend is not consistent with the preset condition, the unmanned aerial vehicle is controlled to fly the current measuring point to the nextmeasuring point in a deceleration mode according to the set deceleration rule, and hovering operation is conducted. According to the embodiment, through the combination of terrain characteristics of operation land parcels, the accurate pesticide use-amount control is achieved by controlling the flight speed.

The invention discloses an unmanned surface ship track tracking method based on actuator faults, comprising the following steps: S1: analyzing various types of information of actuator faults, and modeling the actuator faults of an unmanned ship; S2: performing coordinate conversion of the velocity [Nu] in a mathematical model M1 of the unmanned surface ship in S1 to obtain a new velocity [Omega] and a new model M1'; S3: establishing an actuator fault observation device based on a track and speed tracking error model M in S2, and reconfiguring the actuator faults and external disturbance; S4: according to the track and speed tracking error model M in S2, establishing an integral sliding mode surface and a precise track tracking control law [Tau] of the unmanned surface ship with actuator faults; and S5: measuring the actual unmanned ship position to determine whether the unmanned surface ship reaches the end point of the actual track [Eta]d in S1.

The present invention provides an unmanned surface vehicle course motion control method. The method comprises the steps of receiving an unmanned surface vehicle real-time course angle acquired by a sensor module, wherein the sensor module comprises a gyroscope, an accelerometer and a magnetic field intensity sensor; comparing the real-time course angle and a set course angle to obtain an unmanned surface vehicle course deviation and a course deviation ratio; adopting a fuzzy PID control algorithm to determine an instruction rudder angle according to the course deviation and the course deviation ratio, wherein the instruction rudder angle comprises a steering direction and a steering speed; sending the instruction rudder angle to a motor driver; using the motor driver to control the unmanned surface vehicle motion according to the steering direction and the steering speed. The unmanned surface vehicle course motion control method of the present invention realizes the unmanned surface vehicle course control, and enables the steady-state performance, the dynamic performance and the control precision of the unmanned surface vehicle course motion to be improved and the course control adjustment time to be reduced.

The invention discloses an unmanned aerial vehicle-based autonomous polling method for towers. The method comprises the following steps of: S1, data acquisition: manually controlling an unmanned aerial vehicle to carry out polling, acquiring a track key point coordinate, a photographing point coordinate, a photographing point nose angle and cloud a deck angle of flight of the unmanned aerial vehicle in the polling process; S2, task generation: generating an autonomous flight line and an autonomous photographing task of the unmanned aerial vehicle according to acquired key data and a takeoff point of the unmanned aerial vehicle; and S3, polling operation: uploading the generated polling task to the unmanned aerial vehicle to ensure that the unmanned aerial vehicle autonomously flies according to the task flight line, when the photographing point is reached, automatically adjusting the nose heading and the cloud deck angle, after the adjustment is in place, triggering a camera to a takephoto, continuously executing subsequent tasks after the photographing until the task is completed, and returning to the takeoff point. The method is capable of improving the polling efficiency and isbeneficial to ensure the consistency and safety of the polling.

The embodiment of the invention discloses an allocation method and device for multitasking of an unmanned aerial vehicle. The method comprises the steps that location information of the unmanned aerial vehicle and multiple target points and motion parameters of the unmanned aerial vehicle and a wind field are obtained; according to the location information and a preset genetic algorithm, an initial population taking an European-style flight path as an individual is built; the flight state of the unmanned aerial vehicle and the running time of the track passage of the European-style flight path are determined according to the motion parameters of the initial population, the unmanned aerial vehicle and the wind field, and the running time corresponding to chromosomes in the initial population is obtained according to the running time of the track passage and an SUAV-VS-EVRP model; on the basis of the genetic algorithm, cross and mutation processing is conducted on the chromosomes in the initial population, and after the predetermined number of iterations is achieved, the European-style flight path with the shortest running time is selected as the optimal flight path of the unmanned aerial vehicle. Accordingly, the unmanned aerial vehicle track planning problem is combined with the actual flight environment of the unmanned aerial vehicle, and the optimal flight path scheme obtained through planning is superior to the unmanned aerial vehicle constant speed scheme.