CN117311385A - Unmanned aerial vehicle protection system and method based on multidimensional detection data - Google Patents
Unmanned aerial vehicle protection system and method based on multidimensional detection data Download PDFInfo
- Publication number
- CN117311385A CN117311385A CN202311286240.8A CN202311286240A CN117311385A CN 117311385 A CN117311385 A CN 117311385A CN 202311286240 A CN202311286240 A CN 202311286240A CN 117311385 A CN117311385 A CN 117311385A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- module
- distance
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 title abstract description 13
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims abstract description 23
- 230000001133 acceleration Effects 0.000 claims abstract description 5
- 238000004088 simulation Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims description 27
- 230000009471 action Effects 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 13
- 230000004927 fusion Effects 0.000 claims description 12
- 238000011065 in-situ storage Methods 0.000 claims description 3
- 239000000523 sample Substances 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Abstract
The invention provides a unmanned aerial vehicle protection system and method based on multidimensional detection data, comprising an image acquisition module, a control module and a control module, wherein the image acquisition module is used for acquiring image information of the environment in multiple angles; the inertial navigation module is used for measuring the three-axis attitude angle, the speed and the acceleration of the unmanned aerial vehicle; the panoramic module realizes the full scene simulation restoration of the position where the unmanned plane is located, and an obtained panoramic restoration map; the distance measuring module is used for detecting the distance between the unmanned aerial vehicle and surrounding obstacles in real time; the radar module plans the navigation route of the unmanned aerial vehicle in real time; the positioning navigation module optimizes the navigation route of the unmanned aerial vehicle in real time; the flight control module is used for controlling the unmanned aerial vehicle according to the planned navigation route; and the processing module is used for processing and fusing the acquired data information and realizing the control of the unmanned aerial vehicle. The invention adjusts and optimizes the flight track of the unmanned aerial vehicle in real time so as to avoid the obstacle and maintain the safety distance, makes a decision according to the real-time environment change, and ensures the safety operation of the unmanned aerial vehicle in the complex environment.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle protection system and method based on multidimensional detection data.
Background
The unmanned aerial vehicle for engineering operation has flexible take-off and landing operation, high operation efficiency, good control effect and obvious economic benefit, is beneficial to resource conservation and environmental protection, and is widely applicable to the engineering operation area. Because the engineering operation environment is complex, when the flying hand is far away from the engineering operation unmanned plane, the surrounding flying environment is difficult to judge. Therefore, along with the rapid development of technology, realizing autonomous recognition and effective avoidance of obstacles is one of the necessary trends of intelligent development of engineering unmanned aerial vehicles. The technical problems of high personnel operation difficulty, low environmental terrain recognition precision, low safety avoidance coefficient and the like of the existing engineering operation unmanned aerial vehicle under the condition of complex operation execution.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle protection system and method based on multidimensional detection data, which solve the technical problems of high personnel operation difficulty, low environmental terrain recognition precision and low safety avoidance coefficient under the condition of complex operation execution.
In one aspect, a method for protecting a unmanned aerial vehicle based on multidimensional detection data is provided, including:
the image acquisition module is used for acquiring image information of the environment where the unmanned aerial vehicle is located at multiple angles;
the inertial navigation module is used for measuring the three-axis attitude angle, the speed and the acceleration of the unmanned aerial vehicle;
the panoramic module is used for splicing the image information of multiple angles to realize the full scene simulation restoration of the position where the unmanned aerial vehicle is located, and the panoramic restoration map is obtained; the method is also used for acquiring information of the speed, the position and the distance of surrounding obstacles in real time;
the distance measuring module is used for detecting the distance between the unmanned aerial vehicle and surrounding obstacles in real time;
the radar module is used for planning a navigation route of the unmanned aerial vehicle in real time according to the panoramic restoration map obtained by the panoramic module and the distance between the panoramic restoration map and surrounding obstacles measured by the ranging module;
the positioning navigation module is used for obtaining the information of longitude, latitude, altitude and speed of the position where the unmanned aerial vehicle is located and optimizing the navigation route of the unmanned aerial vehicle in real time according to the information of longitude, latitude, altitude and speed;
the flight control module is used for controlling the unmanned aerial vehicle according to the navigation route planned by the radar module and the positioning navigation module, so as to realize the autonomous obstacle avoidance flight of the unmanned aerial vehicle;
and the processing module is used for processing and fusing the data information acquired by all the modules connected with the processing module to realize the control of the whole system of the unmanned aerial vehicle.
Preferably, the image acquisition module at least comprises a plurality of image pick-up devices, which are respectively used for acquiring original images of the unmanned aerial vehicle in a plurality of directions, wherein the plurality of directions at least comprise directions which are respectively up and down to the north, south, west and east by taking the unmanned aerial vehicle as a starting point.
Preferably, the ranging module at least comprises a plurality of ultrasonic wave transmitting and receiving devices for transmitting ultrasonic waves to the obstacle and receiving ultrasonic waves returned by the obstacle, and determining the distance between the unmanned aerial vehicle and the obstacle according to the returned ultrasonic signals.
On the other hand, the invention also provides a unmanned aerial vehicle protection method based on multidimensional detection data, which is realized by the system and comprises the following steps:
determining an operation task of the unmanned aerial vehicle, and downloading a flight task program to a flight control module of the unmanned aerial vehicle;
starting the unmanned aerial vehicle, receiving data information in real time, and sending the received data information to a processing module;
the processing module carries out preprocessing on all the collected category information, and fuses the category information after preprocessing, so as to realize fusion of the data information collected by all the modules connected with the processing module;
after information fusion is completed, the collected distance value between the unmanned aerial vehicle and the obstacle is compared with a specified safety distance to generate an obstacle avoidance strategy, and the flight control module controls the unmanned aerial vehicle to autonomously complete the obstacle avoidance action so as to ensure the flight safety of the unmanned aerial vehicle.
Preferably, the method further comprises:
when the obstacle avoidance action is finished, going to the target point of the operation task continuously, if an obstacle exists on the flight path, preprocessing all collected information, and fusing after preprocessing, so as to fuse the data information collected by all modules connected with the obstacle avoidance action;
after information fusion is completed, the collected distance value between the unmanned aerial vehicle and the obstacle is compared with a specified safety distance to generate an obstacle avoidance strategy, and the flight control module controls the unmanned aerial vehicle to autonomously complete the obstacle avoidance action until the unmanned aerial vehicle finishes a work task.
Preferably, the preprocessing of all collected category information by the processing module includes:
if the radar module, the image acquisition module and the ranging module acquire the distance of the front long-distance obstacle at the same time, shielding the distance information of the long-distance obstacle detected by the image acquisition module and the ranging module;
if the image acquisition module detects the distance information of the same obstacle from a plurality of directions at the same time, selecting the minimum value of the distance information obtained by the image acquisition module as the distance between the unmanned aerial vehicle and the obstacle at the moment;
if the distance measuring module detects the distance information of the same obstacle from a plurality of directions at the same time, selecting the minimum value of the distance information obtained by the distance measuring module as the distance between the unmanned aerial vehicle and the obstacle at the moment;
and if the positioning navigation module acquires the geographical position of the current unmanned aerial vehicle, acquiring the shortest distance between the current position of the unmanned aerial vehicle and the target point of the operation task.
Preferably, the fusing the data information collected by all the modules connected with the fusing comprises:
the information acquired by the image acquisition module is processed, scanned and identified by the panorama module, and then preprocessed by the processing module, so that distance values between a plurality of unmanned aerial vehicles and obstacles are obtained;
preprocessing information acquired by a ranging module to obtain distance values between a plurality of unmanned aerial vehicles and obstacles;
preprocessing information acquired by a radar module to obtain distance values between a plurality of unmanned aerial vehicles and obstacles;
preprocessing the information of the current position of the unmanned aerial vehicle obtained by the positioning navigation module to obtain the shortest navigation route between the current position of the unmanned aerial vehicle and the target point of the operation task;
and the information data acquired by all the modules are fused, and the optimal safe flight route of the unmanned aerial vehicle to the target point of the operation task is determined.
Preferably, the generating the obstacle avoidance strategy includes:
if the distance value between the unmanned aerial vehicle and the surrounding obstacles is always larger than the safe distance, the current state of the unmanned aerial vehicle is maintained, and navigation is continued according to the current formulated route;
if the distance between the unmanned aerial vehicle and the surrounding obstacles is equal to the safety distance, the unmanned aerial vehicle autonomously completes obstacle avoidance actions according to the optimal obstacle avoidance strategy generated by the processing module;
if the distance between the unmanned aerial vehicle and the surrounding obstacles is smaller than the safety distance, the unmanned aerial vehicle goes to the boundary which is detected and is closest to the surrounding obstacles and keeps the safety distance according to the optimal obstacle avoidance strategy generated by the processing module, and the obstacle avoidance action is completed after the boundary is reached.
Preferably, the method further comprises:
if a certain module is detected to be faulty, judging whether the faulty module affects the normal flight and obstacle avoidance functions of the unmanned aerial vehicle, and closing the faulty module when determining whether the faulty module affects the normal flight and obstacle avoidance functions of the unmanned aerial vehicle, so that the unmanned aerial vehicle continues to execute the operation tasks.
Preferably, the method further comprises:
if the radar module and the ranging module are faulty and the unmanned aerial vehicle can fly normally, the sensors in the radar module and the ranging module which are faulty are closed, and the unmanned aerial vehicle continues to execute the operation tasks;
if the image acquisition module fails and the unmanned aerial vehicle can fly normally, the failed sensor in the image acquisition module is closed, and the unmanned aerial vehicle returns the three-dimensional panoramic global map obtained before to the starting point position;
if the unmanned aerial vehicle cannot normally fly, the unmanned aerial vehicle stops in situ, remotely calls an operator, and waits for a next instruction.
In summary, the embodiment of the invention has the following beneficial effects:
according to the unmanned aerial vehicle protection system and method based on the multidimensional detection data, the unmanned aerial vehicle can acquire the data of the surrounding environment in real time by using the high-precision sensor such as the camera, the laser radar and the ultrasonic sensor. The sensors can sense information such as obstacles, terrains, meteorological conditions and the like, and necessary input is provided for a subsequent intelligent algorithm; based on the environmental data acquired by the sensing and detecting technology, the unmanned aerial vehicle can analyze and understand the environment by using an advanced machine learning algorithm and a computer vision algorithm. The unmanned plane can identify and track the obstacles in real time according to the guidance of the algorithm and forecast the motion trail and possible threats of the obstacles; based on the results of the sensing and detecting technology and the intelligent algorithm, the autonomous flight control system can adjust and optimize the flight trajectory of the unmanned aerial vehicle in real time so as to avoid obstacles and maintain a safe distance. The method can make a decision according to the real-time environment change, and ensure the safe operation of the unmanned aerial vehicle in a complex environment.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that it is within the scope of the invention to one skilled in the art to obtain other drawings from these drawings without inventive faculty.
Fig. 1 is a schematic diagram of a protection system of a unmanned aerial vehicle based on multidimensional detection data in an embodiment of the invention.
Fig. 2 is a schematic flow chart of a method for protecting an unmanned aerial vehicle based on multidimensional detection data according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent.
Fig. 1 is a schematic diagram of an embodiment of a multi-dimensional probe data-based unmanned aerial vehicle protection system according to the present invention. In this embodiment, the system comprises:
the image acquisition module is used for acquiring image information of the environment where the unmanned aerial vehicle is located at multiple angles;
the inertial navigation module is used for measuring the three-axis attitude angle, the speed and the acceleration of the unmanned aerial vehicle;
the panoramic module is used for splicing the image information of multiple angles to realize the full scene simulation restoration of the position where the unmanned aerial vehicle is located, and the panoramic restoration map is obtained; the method is also used for acquiring information of the speed, the position and the distance of surrounding obstacles in real time;
the distance measuring module is used for detecting the distance between the unmanned aerial vehicle and surrounding obstacles in real time;
the radar module is used for planning a navigation route of the unmanned aerial vehicle in real time according to the panoramic restoration map obtained by the panoramic module and the distance between the panoramic restoration map and surrounding obstacles measured by the ranging module;
the positioning navigation module is used for obtaining the information of longitude, latitude, altitude and speed of the position where the unmanned aerial vehicle is located and optimizing the navigation route of the unmanned aerial vehicle in real time according to the information of longitude, latitude, altitude and speed;
the flight control module is used for controlling the unmanned aerial vehicle according to the navigation route planned by the radar module and the positioning navigation module, so as to realize the autonomous obstacle avoidance flight of the unmanned aerial vehicle;
and the processing module is used for processing and fusing the data information acquired by all the modules connected with the processing module to realize the control of the whole system of the unmanned aerial vehicle.
Specifically, the image acquisition module at least comprises a plurality of camera devices which are respectively used for acquiring original images of the unmanned aerial vehicle in a plurality of directions, wherein the plurality of directions at least comprise directions which are respectively up and down to the north, south and north by taking the unmanned aerial vehicle as a starting point. The distance measuring module at least comprises a plurality of ultrasonic wave transmitting and receiving devices which are used for transmitting ultrasonic waves to the obstacle and receiving ultrasonic waves returned by the obstacle, and determining the distance between the unmanned aerial vehicle and the obstacle according to the returned ultrasonic signals. The unmanned aerial vehicle navigation system comprises a processing module (CPU), and a laser radar module (radar module), an unmanned aerial vehicle flight control module, a camera (image acquisition module), a 360 panoramic module (panoramic module), an ultrasonic ranging module, an IMU inertial navigation module (inertial navigation module) and a Beidou positioning navigation module which are respectively connected with the CPU; the cameras are provided with 6 cameras in total and are used for collecting images to obtain original images of six directions up and down in southeast, northwest and the like respectively; the IMU inertial navigation module is used for measuring three-axis attitude angles, speeds and accelerations of the unmanned aerial vehicle; the 360 panoramic module is used for completing the splicing of the original images of the upper and lower six directions of the north and the south, realizing the full scene simulation restoration of the position of the unmanned aerial vehicle, and acquiring the information of the speed, the position, the distance and the like of surrounding obstacles in real time; the ultrasonic ranging module is provided with 4 ultrasonic transmitting and receiving devices in total and is used for transmitting ultrasonic waves to the obstacle and receiving ultrasonic waves returned by the obstacle, and detecting the distance between the unmanned aerial vehicle and surrounding obstacles in real time; the laser radar module is used for planning a navigation route of the unmanned aerial vehicle according to the panoramic restoration map obtained by the 360 panoramic module and the ultrasonic ranging module; the Beidou positioning navigation module is used for acquiring longitude, latitude, altitude, speed and other information of the position of the unmanned aerial vehicle, and can further optimize the navigation route of the unmanned aerial vehicle; the unmanned aerial vehicle flight control module is used for controlling the unmanned aerial vehicle according to the navigation route planned by the laser radar module and the Beidou positioning navigation module, so as to realize autonomous obstacle avoidance flight of the unmanned aerial vehicle; and the CPU module is used for processing and fusing the data information acquired by all the modules connected with the CPU module, so as to realize the control of the whole unmanned aerial vehicle system.
Fig. 2 is a schematic diagram of an embodiment of a method for protecting a unmanned aerial vehicle based on multidimensional detection data according to the present invention. In this embodiment, the method comprises the steps of:
step S1, determining an operation task of the unmanned aerial vehicle, and downloading a flight task program to a flight control module of the unmanned aerial vehicle; that is, according to Beidou satellite navigation, working tasks of the unmanned aerial vehicle are formulated, and flight task programs are downloaded to the unmanned aerial vehicle flight control module.
Step S2, starting the unmanned aerial vehicle, receiving data information in real time, and sending the received data information to a processing module; that is, start the entire system of the unmanned aerial vehicle designed, laser radar module, unmanned aerial vehicle flight control module, camera module, 360 panorama modules, ultrasonic ranging module, IMU inertial navigation module, big dipper location navigation module receive data information in real time to send to the CPU module.
Step S3, the processing module carries out preprocessing on all collected category information, and fuses the category information after preprocessing, so that data information collected by all modules connected with the processing module is fused; that is, the CPU pre-processes all collected category information, and fuses the collected category information after pre-processing; the CPU module is used for fusing the data information collected by all the modules connected with the CPU module.
In a specific embodiment, the preprocessing the collected all kinds of information by the processing module includes: if the radar module, the image acquisition module and the ranging module acquire the distance of the front long-distance obstacle at the same time, shielding the distance information of the long-distance obstacle detected by the image acquisition module and the ranging module; if the image acquisition module detects the distance information of the same obstacle from a plurality of directions at the same time, selecting the minimum value of the distance information obtained by the image acquisition module as the distance between the unmanned aerial vehicle and the obstacle at the moment; if the distance measuring module detects the distance information of the same obstacle from a plurality of directions at the same time, selecting the minimum value of the distance information obtained by the distance measuring module as the distance between the unmanned aerial vehicle and the obstacle at the moment; and if the positioning navigation module acquires the geographical position of the current unmanned aerial vehicle, acquiring the shortest distance between the current position of the unmanned aerial vehicle and the target point of the operation task.
That is, the laser radar module acquires the distance of the front long-distance obstacle, if the camera and the ultrasonic ranging module acquire the distance of the long-distance obstacle at the same time, the CPU automatically shields the distance information of the long-distance obstacle detected by the camera module and the ultrasonic ranging module which are input, thereby reducing the workload of the CPU module, avoiding frequent intervention on the flight control of the unmanned aerial vehicle, and improving the stability and accuracy of the unmanned aerial vehicle for completing the obstacle avoidance action;
the camera module obtains the distance from the obstacle in six directions, namely the upper direction and the lower direction, the lower direction and the north direction, if more than one sensor of the six cameras simultaneously detects the distance information of the same obstacle, the minimum value of the obtained distance information is selected as the distance between the unmanned aerial vehicle and the obstacle at the moment; if the laser radar module and the ultrasonic ranging module also acquire the distance of the medium-distance obstacle at the same time, the CPU automatically shields the distance information of the medium-distance obstacle detected by the laser radar module and the ultrasonic ranging module, so that the workload of the CPU is reduced, frequent intervention on flight control of the unmanned aerial vehicle is avoided, and the stability and accuracy of the unmanned aerial vehicle for completing obstacle avoidance action are improved;
the ultrasonic ranging module acquires the distance between four places of the close distance obstacles in the southwest and the northwest, and if more than one ultrasonic sensor detects the distance information of the same obstacle at the same time, the minimum value of the distance information acquired by the ultrasonic ranging module is selected as the distance between the unmanned aerial vehicle and the obstacle at the moment; if the laser radar module and the camera module also acquire the distance of the close-range obstacle at the same time, the CPU automatically shields the distance information of the close-range obstacle detected by the laser radar module and the camera module, so that the workload of the CPU is reduced, frequent intervention on flight control of the unmanned aerial vehicle is avoided, and the stability and accuracy of the unmanned aerial vehicle for completing obstacle avoidance action are improved;
the Beidou positioning navigation module acquires the geographic position of the current unmanned aerial vehicle, and acquires the shortest distance between the current position of the unmanned aerial vehicle and the target point of the operation task.
In one embodiment, the fusing the data information collected by all the modules connected with the fusion includes: the information acquired by the image acquisition module is processed, scanned and identified by the panorama module, and then preprocessed by the processing module, so that distance values between a plurality of unmanned aerial vehicles and obstacles are obtained; preprocessing information acquired by a ranging module to obtain distance values between a plurality of unmanned aerial vehicles and obstacles; preprocessing information acquired by a radar module to obtain distance values between a plurality of unmanned aerial vehicles and obstacles; preprocessing the information of the current position of the unmanned aerial vehicle obtained by the positioning navigation module to obtain the shortest navigation route between the current position of the unmanned aerial vehicle and the target point of the operation task; and the information data acquired by all the modules are fused, and the optimal safe flight route of the unmanned aerial vehicle to the target point of the operation task is determined. That is, the information collected by the camera is processed and scanned and identified by the 360 panoramic module, and then is preprocessed by the CPU to finally obtain n distance values between the unmanned aerial vehicle and the obstacle (n is the number of surrounding obstacles identified by the 360 panoramic module); after preprocessing information acquired by an ultrasonic ranging module, distance values (m is the number of surrounding obstacles identified by the ultrasonic ranging module) between m unmanned aerial vehicles and the obstacles are obtained; preprocessing information acquired by a laser radar module to obtain distance values (o is the number of obstacles identified by the laser radar module) between o unmanned aerial vehicles and the obstacles; preprocessing information of the current position of the unmanned aerial vehicle obtained by the Beidou positioning navigation module to obtain the shortest navigation route of the current position of the unmanned aerial vehicle and a target point of an operation task; and (3) fusing the information data acquired by the multiple modules, and finally calculating the optimal safe flight route of the unmanned aerial vehicle to the target point of the operation task.
And S4, after information fusion is completed, comparing the collected distance value between the unmanned aerial vehicle and the obstacle with a specified safety distance to generate an obstacle avoidance strategy, and controlling the unmanned aerial vehicle to autonomously complete the obstacle avoidance action by a flight control module to ensure the flight safety of the unmanned aerial vehicle. That is, after the information fusion is completed by the CPU, the collected distance value between the unmanned aerial vehicle and the obstacle is compared with the specified safety distance, so as to generate an obstacle avoidance strategy, and the unmanned aerial vehicle flight control module can control the unmanned aerial vehicle to autonomously complete the obstacle avoidance action.
In a specific embodiment, the generating the obstacle avoidance strategy includes: if the distance value between the unmanned aerial vehicle and the surrounding obstacles is always larger than the safe distance, the current state of the unmanned aerial vehicle is maintained, and navigation is continued according to the current formulated route; if the distance between the unmanned aerial vehicle and the surrounding obstacles is equal to the safety distance, the unmanned aerial vehicle autonomously completes obstacle avoidance actions according to the optimal obstacle avoidance strategy generated by the processing module; if the distance between the unmanned aerial vehicle and the surrounding obstacles is smaller than the safety distance, the unmanned aerial vehicle goes to the boundary which is detected and is closest to the surrounding obstacles and keeps the safety distance according to the optimal obstacle avoidance strategy generated by the processing module, and the obstacle avoidance action is completed after the boundary is reached.
In one embodiment, after the obstacle avoidance action is completed, the vehicle continues to go to the target point of the operation task, if an obstacle exists on the flight path is detected, all collected information is preprocessed again, and fusion is carried out after preprocessing, so that data information collected by all modules connected with the vehicle is fused; after information fusion is completed, the collected distance value between the unmanned aerial vehicle and the obstacle is compared with a specified safety distance to generate an obstacle avoidance strategy, and the flight control module controls the unmanned aerial vehicle to autonomously complete the obstacle avoidance action until the unmanned aerial vehicle finishes a work task. That is, after the unmanned aerial vehicle completes the obstacle avoidance action, the unmanned aerial vehicle continues to go to the target point of the operation task, and if the obstacle is detected again, the unmanned aerial vehicle is repeatedly executed according to the above procedure.
In one embodiment, if a module is detected to fail, determining whether the failed module affects normal flight and obstacle avoidance functions of the unmanned aerial vehicle, and when determining whether the failed module affects normal flight and obstacle avoidance functions of the unmanned aerial vehicle, closing the failed module, and continuing to execute the operation task by the unmanned aerial vehicle. It can be appreciated that if a module fails, the designed unmanned opportunity is handled according to the corresponding method according to the following several cases: if the failed module does not influence the normal flight and obstacle avoidance functions of the unmanned aerial vehicle, the system automatically closes the failed module, and the unmanned aerial vehicle continues to execute the operation tasks.
If the radar module and the ranging module are faulty and the unmanned aerial vehicle can fly normally, the sensors in the radar module and the ranging module which are faulty are closed, and the unmanned aerial vehicle continues to execute the operation tasks; it can be understood that if the laser radar module and the ultrasonic ranging module fail, and the unmanned aerial vehicle can fly normally, the system automatically closes the failed sensor in the laser radar module and the ultrasonic ranging module, the camera module will replace the function of realizing the failure of the laser radar module and the ultrasonic ranging module, and the unmanned aerial vehicle continues to execute the operation task.
If the image acquisition module fails and the unmanned aerial vehicle can fly normally, the failed sensor in the image acquisition module is closed, and the unmanned aerial vehicle returns the three-dimensional panoramic global map obtained before to the starting point position; it can be understood that if the camera module fails and the unmanned aerial vehicle can fly normally, the system automatically turns off the failed sensor in the camera module, and the unmanned aerial vehicle returns to the starting point according to the three-dimensional panoramic global map obtained by the previous system.
If the unmanned aerial vehicle cannot normally fly, the unmanned aerial vehicle stops in situ, remotely calls an operator, and waits for a next instruction. It will be appreciated that if the drone is unable to fly normally, the drone will stay in place, remotely call the worker, and wait for the next instruction.
In one embodiment, a 360 panoramic module is combined with a laser radar module and a Beidou positioning navigation module, acquired data information is processed and fused by a CPU to obtain a remote visual three-dimensional panoramic global map, and an optimal flight path and obstacle avoidance strategy of the unmanned aerial vehicle are formulated according to the obtained three-dimensional panoramic global map, so that operation safety of the unmanned aerial vehicle is ensured;
after the visual three-dimensional panoramic global map is processed and fused by the CPU, the designed unmanned aerial vehicle system can automatically generate new functions besides the three-dimensional information of surrounding obstacles, so as to further improve the detection of the unmanned aerial vehicle on the surrounding environment, and the generated new functions are as follows:
function 1: according to the visual three-dimensional panoramic global map, an optimal obstacle avoidance route can be generated in advance;
function 2: judging whether surrounding obstacles are static or dynamic, obtaining the moving speed of the obstacle which is in dynamic state, and predicting the moving track of the obstacle;
function 3: according to the detected motion speed, motion track and three-dimensional information of the dynamic obstacle, comparing the detected motion speed, motion track and three-dimensional information with the flight speed, flight route and three-dimensional information of the unmanned aerial vehicle, judging whether the dynamic obstacle is about to collide with the unmanned aerial vehicle, and if the probability of collision is not about to occur, continuing to navigate according to the current route by the unmanned aerial vehicle; if the probability of collision exists, a collision point is calculated, and when the safety distance between the unmanned aerial vehicle and the collision point is reached, the flying speed or the flying route of the unmanned aerial vehicle is adjusted and changed automatically according to the three-dimensional information of the dynamic obstacle, so that the purpose of avoiding the dynamic obstacle is achieved.
In summary, the embodiment of the invention has the following beneficial effects:
according to the unmanned aerial vehicle protection system and method based on the multidimensional detection data, the unmanned aerial vehicle can acquire the data of the surrounding environment in real time by using the high-precision sensor such as the camera, the laser radar and the ultrasonic sensor. The sensors can sense information such as obstacles, terrains, meteorological conditions and the like, and necessary input is provided for a subsequent intelligent algorithm; based on the environmental data acquired by the sensing and detecting technology, the unmanned aerial vehicle can analyze and understand the environment by using an advanced machine learning algorithm and a computer vision algorithm. The unmanned plane can identify and track the obstacles in real time according to the guidance of the algorithm and forecast the motion trail and possible threats of the obstacles; based on the results of the sensing and detecting technology and the intelligent algorithm, the autonomous flight control system can adjust and optimize the flight trajectory of the unmanned aerial vehicle in real time so as to avoid obstacles and maintain a safe distance. The method can make a decision according to the real-time environment change, and ensure the safe operation of the unmanned aerial vehicle in a complex environment.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (10)
1. A multi-dimensional probe data based unmanned aerial vehicle protection system, comprising:
the image acquisition module is used for acquiring image information of the environment where the unmanned aerial vehicle is located at multiple angles;
the inertial navigation module is used for measuring the three-axis attitude angle, the speed and the acceleration of the unmanned aerial vehicle;
the panoramic module is used for splicing the image information of multiple angles to realize the full scene simulation restoration of the position where the unmanned aerial vehicle is located, and the panoramic restoration map is obtained; the method is also used for acquiring information of the speed, the position and the distance of surrounding obstacles in real time;
the distance measuring module is used for detecting the distance between the unmanned aerial vehicle and surrounding obstacles in real time;
the radar module is used for planning a navigation route of the unmanned aerial vehicle in real time according to the panoramic restoration map obtained by the panoramic module and the distance between the panoramic restoration map and surrounding obstacles measured by the ranging module;
the positioning navigation module is used for obtaining the information of longitude, latitude, altitude and speed of the position where the unmanned aerial vehicle is located and optimizing the navigation route of the unmanned aerial vehicle in real time according to the information of longitude, latitude, altitude and speed;
the flight control module is used for controlling the unmanned aerial vehicle according to the navigation route planned by the radar module and the positioning navigation module, so as to realize the autonomous obstacle avoidance flight of the unmanned aerial vehicle;
and the processing module is used for processing and fusing the data information acquired by all the modules connected with the processing module to realize the control of the whole system of the unmanned aerial vehicle.
2. The system of claim 1, wherein the image acquisition module comprises at least a plurality of cameras respectively configured to acquire original images of the unmanned aerial vehicle in a plurality of directions, wherein the plurality of directions at least comprises directions respectively from the unmanned aerial vehicle to the north, south, and north.
3. The system of claim 2, wherein the ranging module comprises at least a plurality of ultrasonic transceivers for transmitting ultrasonic waves to the obstacle and receiving ultrasonic waves returned from the obstacle, and determining the distance of the drone from the obstacle based on the returned ultrasonic signals.
4. A method of unmanned aerial vehicle protection based on multidimensional probe data, implemented by a system according to any of claims 1-3, comprising the steps of:
determining an operation task of the unmanned aerial vehicle, and downloading a flight task program to a flight control module of the unmanned aerial vehicle;
starting the unmanned aerial vehicle, receiving data information in real time, and sending the received data information to a processing module;
the processing module carries out preprocessing on all the collected category information, and fuses the category information after preprocessing, so as to realize fusion of the data information collected by all the modules connected with the processing module;
after information fusion is completed, the collected distance value between the unmanned aerial vehicle and the obstacle is compared with a specified safety distance to generate an obstacle avoidance strategy, and the flight control module controls the unmanned aerial vehicle to autonomously complete the obstacle avoidance action so as to ensure the flight safety of the unmanned aerial vehicle.
5. The method as recited in claim 4, further comprising:
when the obstacle avoidance action is finished, going to the target point of the operation task continuously, if an obstacle exists on the flight path, preprocessing all collected information, and fusing after preprocessing, so as to fuse the data information collected by all modules connected with the obstacle avoidance action;
after information fusion is completed, the collected distance value between the unmanned aerial vehicle and the obstacle is compared with a specified safety distance to generate an obstacle avoidance strategy, and the flight control module controls the unmanned aerial vehicle to autonomously complete the obstacle avoidance action until the unmanned aerial vehicle finishes a work task.
6. The method of claim 5, wherein the processing module pre-processing all collected category information comprises:
if the radar module, the image acquisition module and the ranging module acquire the distance of the front long-distance obstacle at the same time, shielding the distance information of the long-distance obstacle detected by the image acquisition module and the ranging module;
if the image acquisition module detects the distance information of the same obstacle from a plurality of directions at the same time, selecting the minimum value of the distance information obtained by the image acquisition module as the distance between the unmanned aerial vehicle and the obstacle at the moment;
if the distance measuring module detects the distance information of the same obstacle from a plurality of directions at the same time, selecting the minimum value of the distance information obtained by the distance measuring module as the distance between the unmanned aerial vehicle and the obstacle at the moment;
and if the positioning navigation module acquires the geographical position of the current unmanned aerial vehicle, acquiring the shortest distance between the current position of the unmanned aerial vehicle and the target point of the operation task.
7. The method of claim 6, wherein the enabling fusion of data information collected by all modules connected thereto comprises:
the information acquired by the image acquisition module is processed, scanned and identified by the panorama module, and then preprocessed by the processing module, so that distance values between a plurality of unmanned aerial vehicles and obstacles are obtained;
preprocessing information acquired by a ranging module to obtain distance values between a plurality of unmanned aerial vehicles and obstacles;
preprocessing information acquired by a radar module to obtain distance values between a plurality of unmanned aerial vehicles and obstacles;
preprocessing the information of the current position of the unmanned aerial vehicle obtained by the positioning navigation module to obtain the shortest navigation route between the current position of the unmanned aerial vehicle and the target point of the operation task;
and the information data acquired by all the modules are fused, and the optimal safe flight route of the unmanned aerial vehicle to the target point of the operation task is determined.
8. The method of claim 7, wherein the generating an obstacle avoidance strategy comprises comparing the collected distance value between the drone and the obstacle with a prescribed safety distance:
if the distance value between the unmanned aerial vehicle and the surrounding obstacles is always larger than the safe distance, the current state of the unmanned aerial vehicle is maintained, and navigation is continued according to the current formulated route;
if the distance between the unmanned aerial vehicle and the surrounding obstacles is equal to the safety distance, the unmanned aerial vehicle autonomously completes obstacle avoidance actions according to the optimal obstacle avoidance strategy generated by the processing module;
if the distance between the unmanned aerial vehicle and the surrounding obstacles is smaller than the safety distance, the unmanned aerial vehicle goes to the boundary which is detected and is closest to the surrounding obstacles and keeps the safety distance according to the optimal obstacle avoidance strategy generated by the processing module, and the obstacle avoidance action is completed after the boundary is reached.
9. The method as recited in claim 8, further comprising:
if a certain module is detected to be faulty, judging whether the faulty module affects the normal flight and obstacle avoidance functions of the unmanned aerial vehicle, and closing the faulty module when determining whether the faulty module affects the normal flight and obstacle avoidance functions of the unmanned aerial vehicle, so that the unmanned aerial vehicle continues to execute the operation tasks.
10. The method as recited in claim 9, further comprising:
if the radar module and the ranging module are faulty and the unmanned aerial vehicle can fly normally, the sensors in the radar module and the ranging module which are faulty are closed, and the unmanned aerial vehicle continues to execute the operation tasks;
if the image acquisition module fails and the unmanned aerial vehicle can fly normally, the failed sensor in the image acquisition module is closed, and the unmanned aerial vehicle returns the three-dimensional panoramic global map obtained before to the starting point position;
if the unmanned aerial vehicle cannot normally fly, the unmanned aerial vehicle stops in situ, remotely calls an operator, and waits for a next instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311286240.8A CN117311385A (en) | 2023-09-28 | 2023-09-28 | Unmanned aerial vehicle protection system and method based on multidimensional detection data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311286240.8A CN117311385A (en) | 2023-09-28 | 2023-09-28 | Unmanned aerial vehicle protection system and method based on multidimensional detection data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117311385A true CN117311385A (en) | 2023-12-29 |
Family
ID=89242225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311286240.8A Pending CN117311385A (en) | 2023-09-28 | 2023-09-28 | Unmanned aerial vehicle protection system and method based on multidimensional detection data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117311385A (en) |
-
2023
- 2023-09-28 CN CN202311286240.8A patent/CN117311385A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109029422B (en) | Method and device for building three-dimensional survey map through cooperation of multiple unmanned aerial vehicles | |
| US20210358315A1 (en) | Unmanned aerial vehicle visual point cloud navigation | |
| CN110069071B (en) | Unmanned aerial vehicle navigation method and device, storage medium and electronic equipment | |
| CN110609570A (en) | Autonomous obstacle avoidance inspection method based on unmanned aerial vehicle | |
| EP3850455B1 (en) | Control and navigation systems | |
| EP3850456B1 (en) | Control and navigation systems, pose optimisation, mapping, and localisation techniques | |
| EP3128386A1 (en) | Method and device for tracking a moving target from an air vehicle | |
| CN107783545A (en) | Post disaster relief rotor wing unmanned aerial vehicle obstacle avoidance system based on OODA ring multi-sensor information fusions | |
| US10921825B2 (en) | System and method for perceptive navigation of automated vehicles | |
| CN111413708A (en) | Unmanned aerial vehicle autonomous landing site selection method based on laser radar | |
| JP7126366B2 (en) | movement control system | |
| US20230073120A1 (en) | Method for Controlling an Unmanned Aerial Vehicle for an Inspection Flight to Inspect an Object and Inspection Unmanned Aerial Vehicle | |
| EP4180767A1 (en) | Route planning for a ground vehicle through unfamiliar terrain | |
| KR101911353B1 (en) | Autonomic flight method when gnss signal loss and unmanned aerial vehicle for the same | |
| CN117311385A (en) | Unmanned aerial vehicle protection system and method based on multidimensional detection data | |
| EP3989034B1 (en) | Automatic safe-landing-site selection for unmanned aerial systems | |
| CN111610800B (en) | Loosely-coupled unmanned aerial vehicle control system | |
| Kovalev et al. | UAV's autonomous navigation principe based on Earth remote sensing data | |
| CN117472082B (en) | Unmanned aerial vehicle route generation method and device based on AI vision assistance | |
| KR102515245B1 (en) | Method and apparatus for preventing loss of unmanned air vehicle | |
| KR102461405B1 (en) | Drone and drone control methods that enable autonomous flight using spatial analysis | |
| RU2793982C1 (en) | Device and method for optimizing aircraft trajectory | |
| CN114995507B (en) | Safety inspection method, device, equipment and storage medium | |
| US20240126275A1 (en) | Obstacle avoidance system and method for unmanned vehicle | |
| Klymenko et al. | Development of software tools for testing the autonomous navigation system of UAVs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |