40results about How to "Realize autonomous flight" patented technology

The invention provides an image perspective-based micro unmanned aerial vehicle indoor autonomous navigation method. An indoor environment is divided into a corridor, a step and a room, a environmental form is determined by analyzing perspective characteristics of a visual image, obstacle detection is further performed by methods with vanish points, center lines or light streams to obtain corresponding navigation and control information, and micro unmanned aerial vehicle indoor autonomous obstacle avoidance and flight can be realized. An environmental three-dimensional model is not needed, the algorithm operating time can be greatly shortened, the real-time property of a control instruction is improved, and the method has high autonomous property and high reliability. The method is low in calculated amount, high in real-time property, low in hardware requirement and high in positioning accuracy and provides a feasible technical scheme for engineering application to indoor navigation of a micro unmanned aerial vehicle.

The invention provides a multi-rotor type unmanned aircraft system with a fire detecting function. Six engine arms and a frame form a body frame of the multi-rotor type unmanned aircraft system; a motor and an electronic speed regulator are connected with each other to control the rotation speed of propeller blades; a landing gear is used for an aircraft to stably land during landing; an unmanned aircraft flight control system is used for controlling stable postures of the aircraft; a sensor is connected with the unmanned aircraft flight control system; a small-sized control computer is connected with laser distance measuring sensors through communication; a processed signal is input into the unmanned aircraft flight control system to control three-dimensional positions and postures of the aircraft indoors; high-definition cameras are connected with an image transmitting device to collect video images of environment; and the image transmitting device is used for transmitting a video image signal to a ground station device so as to realize real-time observation. The multi-rotor type unmanned aircraft system with the fire detecting function, provided by the invention, is advantaged in that the multi-rotor type unmanned aircraft system can autonomously fly under a complicated environment, automatically detect fires in real time, automatically avoid obstacles and protect personal safety; remote monitoring and remote real-time communication are realized; data can be saved and replayed and so on.

The invention provides an unmanned aerial vehicle (UAV) trajectory smoothing method based on Bessel curve transition, comprising the following steps: constructing a Bessel transition function according to known linear route segments, and quickly establishing flight trajectory geometrical characteristics satisfying curvature continuity; with the length of the linear route segments and the allowed maximum trajectory smoothing error as constraints, establishing and solving an optimization problem of the smoothing transition length of each Bessel curve; determining maximum speed, acceleration and jerk constraints, and determining the maximum flight speed of transition segments based on the nature of the Bessel function; performing S-shaped motion planning for all linear segments, and determining the acceleration and deceleration time of each linear segment; iteratively searching and planning the flight speed of each segment to ensure the kinematic compatibility; and performing real-time interpolation to complete flight path generation. The flight performance of UAV can be improved greatly under the premise of guaranteeing the calculation efficiency.

The present invention discloses a rotor unmanned aerial vehicle automatic cruise method and system based on deep learning. The method can avoid barriers along the line based on the deep learning, namely add eyes for the unmanned aerial vehicle to assist in the ultrasonic ranging method and timely avoid the barriers in the close range. The system comprises an image collection module, a barrier identification module, an ultrasonic wave distance detection module, a flight control module and a location module based on a Beidou satellite. The rotor unmanned aerial vehicle automatic cruise method and system based on deep learning are especially suitable for the logistics system and can realize the point-to-point unmanned aerial vehicle automatic cargo transport function so as to greatly save the manpower.

The invention discloses a cloud control-based automatic express delivery system employing an unmanned aerial vehicle. The system comprises a self-tightening blade (1), a satellite positioning module (2), a camera module (3), a triaxial pan-tilt (4), an unmanned aerial vehicle master control module (5), a lifting bracket (6), a high-performance brushless motor (7), an optical flow sensor (8), an ultrasonic module (9), a high-performance electron speed regulator (10), an express loading box (11), an express loading box controller (12), an infrared grating (13), a fingerprint scanning module (14), a high-precision stepper motor (15) and a lithium battery pack (16). The unmanned aerial vehicle is uniformly controlled by adopting cloud; the unmanned aerial vehicle senses the surroundings by virtue of various sensors to achieve autonomous flight; the flight security is high; and the express can be accurately delivered to the scheduled place, the identity of an express recipient is checked and photo evidence is carried out on the express recipient through the carried camera module (3) after the express is delivered, so that safe and accurate delivery of the express is ensured.

The invention discloses a power line patrol unmanned aerial vehicle wireless charging relay station, a charging flight control system and a charging flight control method. The unmanned aerial vehiclewireless charging relay station comprises: a charging platform which is arranged on a power transmission tower and is provided with a wireless charging area for charging an unmanned aerial vehicle; anelectromagnetic locking device, wherein the electromagnetic locking device is used for generating magnetic attraction force to attract the unmanned aerial vehicle onto the charging platform when theunmanned aerial vehicle is charged, and generating magnetic repulsive force to enable the unmanned aerial vehicle to catapult and take off when the unmanned aerial vehicle takes off; a clamping device, wherein the clamping device is used for clamping the unmanned aerial vehicle in the wireless charging area in the transverse direction and the longitudinal direction; a CT power taking device, wherein the CT power taking device takes power from the power transmission line and supplies power to the charging platform, the electromagnetic locking device and the clamping device; and a controller. wherein the controller is connected with the transmitting end of the wireless charging system, the electromagnetic locking device and the clamping device in the wireless charging area. And the unmannedaerial vehicle automatically searches the nearest wireless charging relay station for electric energy supply, and long-distance uninterrupted autonomous line patrol is carried out.

The invention belongs to the technical field of driving safety monitoring, and discloses an unmanned aerial vehicle inspection control method and system, a storage medium, a program and a terminal. The method comprises the following steps of editing an unmanned aerial vehicle flight route, identifying an image by the program and adjusting a pod angle to enable an expressway to be located in the center of a picture; automatically identifying lane lines and objects in the expressway, and analyzing to find illegal driving behaviors and road condition potential safety hazards in the expressway; automatically capturing license plates of the illegal driving behaviors with evidences reserved, and giving a voice prompt for the road condition potential safety hazards; and displaying the expresswaycondition and illegal driving behavior information in real time. The program is adopted for control in the whole process, and an intelligent identification control algorithm is combined, so that a traditional manual inspection mode is completely replaced; the inspection hidden danger is reduced; manpower, material resources and financial resources are saved; the inspection efficiency is improved;and more illegal events can be handled. Meanwhile, the defect that a fixed blind area exists in traffic block port equipment monitoring is overcome.

The invention discloses a long-endurance flexible wing controllable platform which comprises a machine body and a flexible parafoil. The machine body comprises a parafoil cabin capable of being separated from the machine body under the control of a flight control system. The flexible parafoil is arranged in the parafoil cabin before being expanded and connected to the machine body through parafoil ropes. The machine body is provided with a tangent plane which is provided with two power arms, fixing structures for folding and limiting the power arms and rotating mechanisms driving the power arms to be expanded and locking the power arms when the two power arms are expanded to one straight line. The far end of each power arm is provided with a motor controlled by the flight control system and a propeller driven by the motor to rotate. The long-endurance flexible wing controllable platform has relatively good controllability, the double motors of the power arms are under differential motion control to supply steering capacity to the platform, and autonomous flight of the platform is achieved.

The invention discloses a fixed-wing unmanned aerial vehicle cluster control collision avoidance method and device based on deep reinforcement learning. The method comprises the steps of S1, establishing an unmanned aerial vehicle kinematic model and D3QN, updating network parameters by using historical interaction data in the interaction process of each wing plane and the environment; training toform a D3QN model, constructing a joint state between the wing planes and a lead plane according to the environment state in the interaction process, performing situation assessment construction to obtain a local map, and inputting the local map into the D3QN model to obtain control instruction output of each wing plane; S2, obtaining state information in real time by each wing plane to form a joint state between the current wing plane and the lead plane, carrying out situation assessment in real time to construct a local map, and inputting the joint state constructed in real time and the local map into the D3QN network model to obtain a control instruction of each wing plane. The method has the advantages that the implementation method is simple, the expandability is good, cluster control over the fixed-wing unmanned aerial vehicles can be achieved, and meanwhile, collision is avoided.

The invention discloses an unmanned aerial vehicle bionic intelligent obstacle-avoiding method based on light streams and belongs to the field of artificial intelligence and computer vision. Obstacle-avoiding flight of an unmanned aerial vehicle is realized through combination of software and hardware. The method comprises the specific steps that an image sequence is captured through a monocular camera carried on the unmanned aerial vehicle, an LK (Lucas Kanade) method is used for calculating a light stream field according to a front frame image and a rear frame image, and noise light streams are filtered; each image is divided into an edge, a left middle part and a right middle part, and whether large obstacles exist on the left side and the right side or not is judged based on an SVM classifier; the sum of TTC in all columns is calculated, free sections and obstacle sections are calibrated and interpolated, and a maximum free communicating section is obtained; a translation amount and a rotation amount are obtained in combination with a left and right light stream balancing strategy, and therefore the unmanned aerial vehicle is controlled to fly avoiding obstacles. By means of the method, real-time obstacle-avoiding flight of the unmanned aerial vehicle in an unknown disordered environment can be realized.

The invention provides a flight camera. The flight camera comprises a processing unit which is used for generating image code stream according to an input signal of the camera, a flight control unit which is used for calculating the flight trajectory of the flight camera according to the flight status information of the flight camera and generating a flight control command, and a drive unit which is used for driving the flight mechanism of the flight camera according to the flight control command. According to the flight camera, the camera can carry out shooting in any angle and at any position.

The invention discloses an autonomous flight path planning method for a small-sized unmanned aerial vehicle. The method comprises the following steps that: S1, GPS positioning is carried out: the GPSof a four-axis aircraft is adopted to locate the position of the small-sized unmanned aerial vehicle; S2, an improved A-Star algorithm is used as a flight path planning algorithm to achieve the flightpath tracking of the small-sized unmanned aerial vehicle; S3, an ant colony evolution algorithm is adopted to optimize feasible flight paths: a flight path calculated by the improved A-Star algorithmin the S2 is inputted to the ant colony algorithm, and the ant colony algorithm optimizes the feasible flight paths and calculates a shortest flight path; and S4, post-processing is performed on an optimal flight path: all flight path points on the same line are summarized into a straight line segment containing a head end point and a tail end point. A traditional small-sized unmanned aerial vehicle is controlled by a remote control device, the movement range of the small-sized unmanned aerial vehicle is easily limited to the sight distance range of a controller, and as a result, the autonomous flight of the small-sized unmanned aerial vehicle cannot be realized, and the small-sized unmanned aerial vehicle cannot have a wider movement range, while, with the method of the invention adopted, the above problem can be solved.

The invention relates to a dedicated flight control system for a multi-rotor unmanned aerial vehicle. The system comprises a multi-rotor unmanned aerial on which a liquid spraying device is carried; and ground liquid supply equipment connected with the multi-rotor unmanned aerial vehicle through a transfusion hose and used for supplying liquid, required by the liquid spraying device in work, for the multi-rotor unmanned aerial vehicle in the work process of the multi-rotor unmanned aerial vehicle; the system further comprises ground power supply equipment connected with the multi-rotor unmanned aerial vehicle through a power supply line and used for supplying electric energy for the multi-rotor unmanned aerial vehicle in the work process of the multi-rotor unmanned aerial vehicle; the multi-rotor unmanned aerial vehicle comprises an unmanned aerial vehicle comprehensive management module, a height control submodule, an airway navigation control submodule, and a spraying control submodule. The flight control for driving the multi-rotor unmanned aerial vehicle is realized, the plant protection work can be performed along a preset flight airway, the system can deal with various complex terrains, relieve the labor intensity of a remote operator, and avoid missing spraying or re-spraying of the pesticide.

The invention discloses an indoor unmanned aerial vehicle, a control method thereof and a computer readable storage medium, and the method comprises the steps: enabling the unmanned aerial vehicle toshoot a picture in real time, recognizing a symbolic object in the picture, and estimating the position of the unmanned aerial vehicle in a map through employing the recognized symbolic object as a reference object; taking the estimated position as the position of the unmanned aerial vehicle to plan a path from the position of the unmanned aerial vehicle to an end point, and controlling the unmanned aerial vehicle to fly based on the planned path. The method includes: shooting a picture in real time and identifying the picture in a flight process, estimating the position of the unmanned aerialvehicle in a map by taking a newly identified symbolic object as a reference object when the symbolic object is identified, correcting the position of the unmanned aerial vehicle based on the estimated position, and planning a path from the position of the unmanned aerial vehicle to an end point again after the position is corrected. According to the invention, autonomous positioning, path planning and autonomous flight can be achieved; furthermore, the invention also provides a traffic sign recognition method based on a deep learning framework, and the method can help to correct the positionof the unmanned aerial vehicle and perfect and update a map.

The invention discloses a technology for achieving linkage with an Internet-of-things sensing device through an unmanned aerial vehicle (UAV). The technology includes the following technical steps: an environmental monitoring device is deployed in an area needing to be monitored; a video surveillance image is acquired through a video surveillance device in the area; the environmental monitoring device and the video surveillance device are connected with a GIS system; the GIS system is in data linkage with a data processing terminal; the data processing terminal is in data linkage with a UAV; the UAV is in data linkage with a user terminal; and if the environment information of the flight path changes, the changed environment information is integrated and transmitted to the data processing terminal through the GIS, and the data processing terminal changes the flight path in time according to the environment information received to enable the UAV to fly autonomously. Emergencies can be handled in advance, and manual control is no longer needed. The crash probability of unmanned aerial vehicles is reduced.

The invention relates to a small unmanned helicopter flight control computer system. The system comprises a communication processor, a programmable gate array, a power module, a clock module, a wireless communication module, an electronic compass, a GPS, an ultrasonic sensor, a debugging serial port, an Ethernet port, a remote-control receiver, a steering engine, a height gauge, a gyroscope and anaccelerometer, wherein the power module is connected with the communication processor and the programmable gate array; the clock module is connected with the communication processor and the programmable gate array; the wireless communication module, the electronic compass, the GPS, the ultrasonic sensor, the debugging serial port and the Ethernet port are respectively connected with the communication processor; the remote-control receiver, the steering engine, the height gauge, the gyroscope and the accelerometer are respectively connected with the programmable gate array; and the steering engine is connected with an unmanned aerial vehicle. The small unmanned helicopter flight control computer system has the characteristics of being small in volume, compact in structure, low in power consumption and strong in processing ability, and is capable of successfully realizing autonomous flight of small unmanned helicopters on the basis.