CN117389305A - Unmanned aerial vehicle inspection path planning method, system, equipment and medium - Google Patents
Unmanned aerial vehicle inspection path planning method, system, equipment and medium Download PDFInfo
- Publication number
- CN117389305A CN117389305A CN202311596698.3A CN202311596698A CN117389305A CN 117389305 A CN117389305 A CN 117389305A CN 202311596698 A CN202311596698 A CN 202311596698A CN 117389305 A CN117389305 A CN 117389305A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- point cloud
- unmanned aerial
- aerial vehicle
- cloud data
- 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 52
- 238000007689 inspection Methods 0.000 title claims abstract description 37
- 230000005540 biological transmission Effects 0.000 claims abstract description 39
- 238000013178 mathematical model Methods 0.000 claims abstract description 37
- 238000010586 diagram Methods 0.000 claims abstract description 34
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 33
- 238000001914 filtration Methods 0.000 claims abstract description 33
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 230000004888 barrier function Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 230000008447 perception Effects 0.000 abstract description 10
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000003287 optical effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of unmanned aerial vehicle inspection and obstacle avoidance, and discloses an unmanned aerial vehicle inspection path planning method, system, equipment and medium, wherein the method comprises the following steps: acquiring three-dimensional point cloud data of an electric power facility; establishing an environment mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model; filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle; updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle diagram; calculating Euclidean distances among the obstacles in the obstacle diagram through a fast travelling algorithm; and planning a patrol path of the electric power facility according to the obstacle diagram and the Euclidean distance. The invention realizes rapid and accurate three-dimensional perception based on the depth information environment three-dimensional perception technology; and realizing high-performance dynamic path planning by using environment sensing and positioning information.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle inspection and obstacle avoidance, in particular to an unmanned aerial vehicle inspection path planning method, system, equipment and medium.
Background
The distribution overhead line equipment has wide points, scattered regions and complex branch lines, and the increasing distribution line equipment brings huge pressure to the stable operation of the distribution network of a company. Compared with the power line, the power distribution line has relatively short distance, dense grids and complex branch line paths, so that the traditional unmanned aerial vehicle line type radiation inspection mode of the power line is difficult to be suitable for. The distribution lines are large in space distribution density, large in cross parallelism and high in cost, the environment where the distribution lines are located is changed rapidly, the fact that the number of pictures taken is different according to the shooting angles of different distribution equipment unmanned aerial vehicles and the space environment is updated constantly is considered, the operation path is required to be planned repeatedly, the cost is high, and the distribution unmanned aerial vehicles still need to be developed deeply for realizing autonomous inspection and autonomous tracking shooting equipment.
Currently, developing unmanned aerial vehicle inspection of distribution line equipment based on edge computing has become an urgent need and has preliminary applications such as: the German university of Willzburg uses low-cost ultrasonic and infrared distance meters as distance sensors, uses inertial and optical flow sensors as distance derivatives of references, improves data fusion, enables an unmanned aerial vehicle to perform collision avoidance of distance control, has simple solution, low calculation burden, and does not need memory and time-consuming simultaneous positioning and mapping for obstacle avoidance; the barrage camera is used by the Indian scientific research institute, so that the unmanned aerial vehicle quadrotor can autonomously avoid collision with an obstacle in an unstructured and unknown indoor environment, however, the control method for unmanned aerial vehicle obstacle avoidance by using monocular images is seriously dependent on environmental information, and the proposed unmanned aerial vehicle Obstacle Avoidance (OA) method based on deep reinforcement learning provides better results in terms of collision-free coverage distance; the system of the university of Mitsui roller calibration machinery and aerospace engineering in the United states puts forward a dual-mode control strategy, namely a 'safe mode' and a 'dangerous mode', in the aspect of unmanned aerial vehicle obstacle avoidance strategy, obstacle avoidance is respectively carried out by adopting different strategies, so that the generation of the track of the unmanned aerial vehicle in the free and obstacle-full environment for formation flight is realized, and the generated track is tracked by a tracking controller based on model prediction control; the korean university is equipped with a vision sensor for acquiring obstacle information and based on the platform, a reactive collision avoidance algorithm is proposed to achieve safe autonomous flight in the presence of multiple dynamic obstacles, the algorithm incorporating upcoming obstacle movements into a collision avoidance frame, the processing pipeline consisting of independent components for each sequential task in obstacle sensing and tracking, calculating a spherical bounding box for each obstacle followed by a discrete time kalman filter for predicting obstacle trajectories to detect potential collisions; aiming at the problem of unmanned aerial vehicle obstacle avoidance, beijing information technology university computer college provides an unmanned aerial vehicle obstacle avoidance control method based on ultrasonic waves, the number of the ultrasonic waves is increased to form a circle on the basis of the traditional ultrasonic obstacle avoidance scheme, the information of a plurality of ultrasonic sensors is fused, and the obstacle avoidance flight of the multi-rotor unmanned aerial vehicle is realized according to the distance between the unmanned aerial vehicle and an obstacle and the channel value of a remote controller; aiming at the problem that the state consistency of individuals in a group is poor due to the fact that a few individuals easily fall into local minima when encountering barriers, the college of science and photoelectric technology provides an unmanned aerial vehicle cluster obstacle avoidance algorithm based on the local interaction of barrier information; the computer science and technology system of Nanjing aviation aerospace university provides an obstacle recognition model based on monocular vision feature points. However, the distribution network lines are intricate and dense, the background environment is complex in dynamic state, and the problems of limited image acquisition angle, background dynamic interference, high complexity of autonomous flight route planning and the like exist in the operation process of the unmanned aerial vehicle of the distribution network lines, so that the precise positioning navigation and equipment defect identification technology of the unmanned aerial vehicle still needs to be deeply involved and promoted. Therefore, a solution is needed to solve the above problems.
Disclosure of Invention
The invention provides a method, a system, equipment and a medium for planning an unmanned aerial vehicle inspection path, which solve the problems that obstacle recognition and calculation are complex and quick route planning cannot be realized during unmanned aerial vehicle inspection.
In order to solve the technical problem, a first aspect of the present invention provides a method for planning an inspection path of an unmanned aerial vehicle, including:
acquiring three-dimensional point cloud data of an electric power facility;
establishing an environment mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model;
filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle;
updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle diagram;
calculating Euclidean distances among the obstacles in the obstacle diagram through a fast travelling algorithm;
and planning a patrol path of the electric power facility according to the obstacle diagram and the Euclidean distance.
Further, the acquiring three-dimensional point cloud data of the electric power facility includes:
gridding a two-dimensional space, and adjusting the size of the grid according to the type of the electric power facility and the density of the point cloud;
extracting and combining the characteristic information in each grid to obtain three-dimensional point cloud data of the electric power facilities; the characteristic information includes at least average height, point cloud density, and color information.
Further, establishing an environment mathematical model according to the three-dimensional point cloud data, including:
representing the shape and the position of the power transmission tower in the three-dimensional point cloud data through a geometric body or a three-dimensional model, and marking the height and the occupied area of the power transmission tower to obtain the power transmission tower model;
modeling a transformer substation in the three-dimensional point cloud data in a building form, and adding a transformer and switching equipment to obtain the modeling of the transformer substation;
and representing the starting point, the ending point and the line type of the power transmission line in the three-dimensional point cloud data through line segments or curves to obtain the power transmission line model.
Further, filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle, including:
determining the number of filter windows according to the grids, so that the number of the grids is equal to the number of the windows; the size of the window is odd;
traversing each grid in each window, sorting the values of all grids in the neighborhood of the grid according to the size, and selecting the value of the middle position as the median value to replace the value of the grid;
and determining the obstacle and the position thereof according to the cruising altitude and the value of the grid.
Further, updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle map, wherein the method comprises the following steps:
taking the confidence coefficient of the obstacle at the previous moment as the prior probability;
calculating the likelihood of the obstacle through the density and the height of points in the point cloud;
multiplying the prior probability with likelihood, and carrying out normalization processing to obtain posterior probability;
setting a confidence coefficient threshold value, comparing the confidence coefficient threshold value with posterior probability, and updating the obstacle according to a comparison result;
and combining the updated barriers to form a barrier map.
Further, calculating the Euclidean distance between each obstacle in the obstacle map through a fast travelling algorithm comprises the following steps:
creating a wave front queue to store a grid where an obstacle at a distance to be updated is located; the expected arrival distances of the grids from the target points are arranged in order from small to large;
adding the known position obstacle in the obstacle diagram into the wave front queue, and performing initial distance marking;
taking out the grids to be calculated from the wave front queue in sequence, calculating the expected arrival distance of the adjacent non-accessed grids, deleting the grids to be calculated from the wave front queue if the calculation result is not smaller than the expected arrival distance of the grids to be calculated, and taking the expected arrival distance of the grids to be calculated as the Euclidean distance from the grids to be calculated to the target point;
and repeating the calculation process of the grid to be calculated and the adjacent non-accessed grids in the wave front queue until the wave front queue is empty, and obtaining the Euclidean distance between the obstacles in the obstacle diagram.
Further, after calculating the expected arrival distance of the adjacent non-accessed grids, the method further comprises:
and if the calculated result is smaller than the expected arrival distance of the head grid, adding the non-accessed grids adjacent to the head grid into the wave front queue, and taking the calculated result as the expected arrival distance of the grid.
The second aspect of the present invention provides an unmanned aerial vehicle inspection path planning system, comprising:
the data acquisition module is used for acquiring three-dimensional point cloud data of the electric power facility;
the model construction module is used for building an environment mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model;
the data filtering module is used for filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle;
the obstacle updating module is used for updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle map;
the distance calculation module is used for calculating Euclidean distances among the obstacles in the obstacle diagram through a fast travelling algorithm;
and the path planning module is used for planning a routing inspection path of the electric power facility according to the obstacle diagram and the Euclidean distance.
A third aspect of the present invention provides an electronic device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the unmanned aerial vehicle inspection path planning method according to any one of the first aspects above when executing the computer program.
A fourth aspect of the present invention provides a computer readable storage medium, the computer readable storage medium including a stored computer program, wherein when the computer program is executed, the device on which the computer readable storage medium is located is controlled to execute the unmanned aerial vehicle inspection path planning method according to any one of the first aspect.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
the invention provides a method, a system, equipment and a medium for planning an inspection path of an unmanned aerial vehicle, wherein the method comprises the following steps: acquiring three-dimensional point cloud data of an electric power facility; establishing an environment mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model; filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle; updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle diagram; calculating Euclidean distances among the obstacles in the obstacle diagram through a fast travelling algorithm; and planning a patrol path of the electric power facility according to the obstacle diagram and the Euclidean distance. The invention realizes rapid and accurate three-dimensional perception based on the depth information environment three-dimensional perception technology; and by utilizing environment sensing and positioning information, the unmanned aerial vehicle dynamic path planning with high maneuver and high performance is realized, and the smoothness and safety of the flight track are improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for planning an inspection path of an unmanned aerial vehicle according to an embodiment of the present invention;
FIG. 2 is a flow chart of step S1 provided in an embodiment of the present invention;
FIG. 3 is a flowchart of step S2 provided in an embodiment of the present invention;
FIG. 4 is a flowchart of step S3 provided in an embodiment of the present invention;
FIG. 5 is a comparison of median alignment provided by one embodiment of the present invention, (a) before alignment and (b) after alignment;
FIG. 6 is a flowchart of step S4 provided in an embodiment of the present invention;
FIG. 7 is a flowchart of step S5 provided in an embodiment of the present invention;
fig. 8 is a device diagram of an unmanned aerial vehicle inspection path planning system according to an embodiment of the present invention;
fig. 9 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings and examples, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the step numbers used herein are for convenience of description only and are not limiting as to the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
In an embodiment, as shown in fig. 1, a first aspect of the present invention provides a method for planning an inspection path of an unmanned aerial vehicle, including:
s1, acquiring three-dimensional point cloud data of an electric power facility;
in one embodiment, step S1, as shown in fig. 2, includes:
s11, meshing a two-dimensional space, and adjusting the size of the mesh according to the type of the electric power facility and the point cloud density;
s12, extracting and combining characteristic information in each grid to obtain three-dimensional point cloud data of the electric power facilities; the characteristic information includes at least average height, point cloud density, and color information.
Specifically, a laser scanner or other sensor equipment acquires three-dimensional point cloud data of an electric power facility; the three-dimensional point cloud data comprise point cloud information of electric power facilities such as a power transmission tower, a transformer substation and a power transmission line. The specific acquisition process comprises the following steps: firstly, dividing a two-dimensional space into regular square units, wherein each unit is called a grid; for each grid cell, statistical values, such as average values, median values, etc., of the attributes of the point cloud data contained therein may be calculated as the attributes of the grid. Then, determining the size of the grid lattice, and selecting a proper grid lattice size according to the density of the point cloud data and an application scene, wherein the grid lattice size is too small, information loss can be caused, and the accuracy can be reduced due to too large; the grids may be set to equal sizes using average meshing; adaptive settings may also be used. Because the size of the grid determines the precision of establishing a model and the consumption of computing resources, selecting the proper size of the grid according to the characteristics and actual requirements of the electric power facilities; and the grid size is dynamically adjusted according to the specific conditions of the electric power facilities and the point cloud density so as to ensure the precision and the efficiency in different areas. While the feature information in each grid may be used for subsequent modeling and analysis. Step S1 is a visual information preprocessing stage, and after the stage-step S1, the method further comprises the step of processing the point cloud image acquired by the unmanned aerial vehicle through median filtering, replacing the value of the pixel with the median of the pixel value, removing salt and pepper noise and impulse noise, and improving the signal to noise ratio, so that the subsequent processing is more accurate and reliable. Meanwhile, the point cloud data is discretized by adopting gridding treatment, and a foundation is provided for the subsequent construction of an environment mathematical model.
S2, establishing an environment mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model;
in one embodiment, step S2, as shown in fig. 3, includes:
s21, representing the shape and the position of the power transmission tower in the three-dimensional point cloud data through a geometric body or a three-dimensional model, and marking the height and the occupied area of the power transmission tower to obtain the power transmission tower model; wherein the geometry includes cubes, cylinders, etc.;
s22, modeling a transformer substation in the three-dimensional point cloud data in a building form, and adding a transformer and switching equipment to obtain the modeling of the transformer substation;
s23, representing the starting point, the ending point and the line type of the power transmission line in the three-dimensional point cloud data through line segments or curves to obtain the power transmission line model.
Specifically, the construction of the environment mathematical model is realized by a proper coordinate system and mapping the point cloud data or the gridded data into a unified mathematical model; such as a geographic coordinate system (e.g., latitude and longitude) and selects the appropriate data structure to store the model information according to the particular application requirements.
In addition, environmental features such as terrain, vegetation and the like can be also incorporated into the model according to actual conditions so as to more accurately reflect the actual conditions; corresponding attributes, such as color, material, status information, etc., are set for each part of the model, and these attributes can be used for subsequent analysis and visualization. And determining the precision and resolution of the model according to actual requirements so as to ensure the accuracy and the calculation efficiency of the model. For example, in the inspection, the accuracy may be set to 1 meter for a power transmission tower or a substation, or to 0.2 meter or 0.1 meter (i.e., the side length of each pixel point) for a specific power transmission line.
The models can be used for electric power inspection work such as real-time monitoring, anomaly detection, facility state evaluation and the like, and the established models are utilized for analyzing electric power facilities, so that anomaly conditions can be identified, facility state evaluation and the like; meanwhile, the model can be presented through a visualization technology, so that workers can intuitively know the condition of the electric power facility.
S3, filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle; specifically, the point cloud filtering algorithm adopted in the application is specifically a two-dimensional median filtering method.
In one embodiment, step S3, as shown in fig. 4, includes:
s31, determining the number of filter windows according to the grids, so that the number of the grids is equal to the number of the windows; the size of the window is odd; the method comprises the steps of firstly determining the size and the number of filter windows, wherein the number of the filter windows is the same as that of grids, and each window corresponds to one grid area (namely one grid) in a two-dimensional space; the size of the window should be selected according to the particular application and data characteristics, and is typically an odd number. For example, a 3*3 window (when the accuracy is 1 meter, the 5*5 window is 5 meters by 5 meters), and the filter window with an odd number of sizes is selected in the median filtering to ensure the uniqueness of the median; if a window with even size is selected, two values are arranged in the middle of the window, and a unique median value cannot be obtained; and the odd-sized windows can explicitly calculate the median; the same reasoning applies to both two-dimensional and three-dimensional cases. The selection of an odd-sized window may ensure that there is a unique median value in the local neighborhood, which is the basis for the median filtering operation. In addition, the window with the odd size can ensure that the center position of the filtering window is an exact pixel instead of a position between pixels, so that estimation errors can be reduced, and the filtering result is more accurate.
S32, traversing each grid in each window, sorting the values of all grids in the grid neighborhood according to the size, and selecting the value of the middle position as the median value to replace the value of the grid; wherein within each window, each cell is traversed, the values of all cells within its neighborhood are ordered by size, and then the value of the middle position (i.e., the height value) is selected as the median value to replace the value of the cell (where numerical value represents height, where height is typically 1 meter). Finally, for cells at edges, since their neighborhood may exceed the image boundary, a suitable edge extension or boundary processing strategy is needed, which is a way of zero padding; i.e. zero values are filled outside the image boundaries, the two-dimensional 3*3 window median adjustment front-back comparison graph is shown in fig. 5, 5 (a) is the median filter graph before adjustment, and 5 (b) is the median filter graph after adjustment. The median value of the figure is 4, the outermost circle is the zero-filled portion, in other cases, if the difference in height in space is large, the highest value calibration may be used to avoid collisions.
S33, determining the obstacle and the position thereof according to the cruising altitude and the grid value; taking the unmanned aerial vehicle cruising height as an example, the area with the height of more than ten meters (namely more than or equal to 10 in fig. 5 and only the distance) is marked as an obstacle, and the cruising height is selected to be bypassed or lifted when the obstacle is encountered.
S4, updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle diagram;
in one embodiment, step S4, as shown in fig. 6, includes:
s41, taking the confidence coefficient of the obstacle at the previous moment as the prior probability;
s42, calculating the likelihood of the obstacle through the density and the height of the points in the point cloud;
s43, multiplying the prior probability with likelihood, and carrying out normalization processing to obtain posterior probability;
s44, a confidence coefficient threshold value is set, the confidence coefficient threshold value is compared with posterior probability, and the obstacle is updated according to a comparison result;
s45, combining the updated barriers to form a barrier map.
Specifically, the present application estimates the confidence of an obstacle through the bayesian estimation principle. When using the bayesian estimation principle, a priori probabilities and likelihoods are first defined: the prior probability is the initial belief or confidence in the presence of an obstacle without new observations. It is derived based on previous information or experience. In bayesian updating, the prior probability is typically the obstacle confidence value at the previous moment. For example, if the confidence value of the obstacle at the previous moment is 0.8, it may be taken as a priori probability, which indicates the confidence of the existence of the obstacle without new observation data, and thus, the present application takes the confidence of the obstacle at the previous moment as a priori probability; likelihood refers to the probability of the presence of an obstacle given sensor data, which reflects the degree of support of the presence of an obstacle by the observed data. The likelihood is generally calculated based on characteristics of the sensor data and a detection algorithm for the obstacle, for example, in the LiDAR data, the likelihood of the obstacle may be calculated in consideration of information such as density, height, and the like of points in the point cloud. Thus, the present application calculates the likelihood of the obstruction from the density and height of points in the point cloud.
In the Bayesian updating process, the prior probability and the likelihood are multiplied, and normalization processing is carried out, so that the new posterior probability is obtained. This posterior probability will be used as an updated obstacle confidence value reflecting the confidence in the presence of an obstacle after new observations are considered. That is, the prior probability is based on past information and the likelihood is based on current observations that together affect the update process of the obstacle confidence. Setting a confidence coefficient threshold value, and comparing the confidence coefficient threshold value with the posterior probability; if the confidence threshold is 0.5, then the obstacle is considered to be present when the confidence threshold is above 0.5, and if the confidence is below 0.5, then the obstacle is considered to be absent; updating the obstacle calibration according to the confidence coefficient and the confidence coefficient threshold value, and combining the updated obstacles to form an obstacle map. According to the Bayesian estimation principle, the confidence coefficient of the obstacle contained in the update space is updated, and a basis is provided for dynamic path planning decision.
S5, calculating Euclidean distances among the obstacles in the obstacle diagram through a fast travelling algorithm;
in one embodiment, step S5, as shown in fig. 7, includes:
s51, creating a wave front queue to store a grid where the obstacle with the distance to be updated is located; the expected arrival distances of the grids from the target points are arranged in order from small to large;
s52, adding the known position obstacle in the obstacle diagram into the wave front queue, and performing initial distance marking;
s53, taking out the grids to be calculated from the wave front queue in sequence, calculating the expected arrival distance of the adjacent non-accessed grids, deleting the grids to be calculated from the wave front queue if the calculation result is not smaller than the expected arrival distance of the grids to be calculated, and taking the expected arrival distance of the grids to be calculated as the Euclidean distance from the grids to be calculated to the target point; in an embodiment, if the calculation result is smaller than the expected arrival distance of the head grid, adding an unaccessed grid adjacent to the head grid into the wavefront queue, and taking the calculation result as the expected arrival distance of the grid;
s54, repeating the calculation process of the grid to be calculated and the adjacent non-accessed grids in the wave front queue until the wave front queue is empty, and obtaining the Euclidean distance between the obstacles in the obstacle diagram.
Specifically, the method adopts an occupied grid model, divides a flight space into a space containing barriers and an idle space, adopts Euclidean distance to represent distance information of the occupied grid, designs an efficient distance updating method, namely a fast walking algorithm, and rapidly constructs an Euclidean distance field, thereby realizing rapid sensing and barrier identification of electric facilities.
The present application marks the position of a known obstacle as 0, indicating a distance from the obstacle of 0. The distances of other unknown regions are set to a larger initial value (e.g., to infinity). A wavefront queue is created for storing a grid of distances to be updated, which are ordered in accordance with the expected distance to the target point. The positions of all known obstacles are added to the queue and marked with a distance of 0, and the grid at the head of the queue (the point where the distance is the earliest is expected) is removed from the wave front queue.
For each adjacent unvisited grid, calculating a new expected arrival distance, if the new expected arrival distance is less than the original expected arrival distance, updating the expected arrival distance and adding the grid to the wavefront queue; and if the new predicted distance is not smaller than the original predicted distance, deleting the grid at the head of the queue from the wavefront queue, and taking the predicted arrival distance of the grid at the head of the queue as the Euclidean distance from the grid at the head of the queue to the target point.
The expected arrival distances of the individual grids are updated step by repeatedly diffusing the wavefront. In this way, propagation of distance information is achieved by continually retrieving grids from the queue and updating the distances of their neighbors. The above steps are repeated until the wavefront queue is empty, indicating that the expected arrival distances for all reachable grids have been updated. Once the wavefront queue is empty, the expected arrival distance information for all reachable grids has been updated, at which point the euclidean distance field is built. During the update process, the occupancy grid is traversed. For each occupied grid, the Euclidean distance of the current grid is updated according to the distance information of the adjacent grids around the occupied grid. The algorithm used here is essentially a solution to the euclidean distance, which is calculated in two dimensions to simplify the calculation, and to calculate again whether the drone can pass this height. The Euclidean distance is used as distance measurement, and the Euclidean distance field is efficiently constructed through a rapid distance propagation algorithm, so that rapid perception and obstacle recognition of the electric power facilities are realized.
S6, planning a patrol path of the electric power facility according to the obstacle diagram and the Euclidean distance
According to the method, by combining the obstacle map, the Euclidean distance, the target task and the environmental information, the environment perception map is quickly inquired, and the collision-free global track is planned; furthermore, a B-spline optimization algorithm is adopted, unmanned aerial vehicle dynamic constraint conditions are combined, unmanned aerial vehicle tracks are optimized, and smoothness and safety of flight tracks are improved.
In the embodiment of the application, based on the problem that the obstacle recognition and calculation are complex and quick route planning cannot be realized when the unmanned aerial vehicle is patrolled, the unmanned aerial vehicle patrolling path planning method is designed, and three-dimensional point cloud data of an electric power facility are obtained; establishing an environment mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model; filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle; updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle diagram; calculating Euclidean distances among the obstacles in the obstacle diagram through a fast travelling algorithm; planning a technical scheme of a patrol path of the electric power facility according to the obstacle diagram and the Euclidean distance; the invention realizes rapid and accurate three-dimensional perception based on the depth information environment three-dimensional perception technology; and by utilizing environment sensing and positioning information, the unmanned aerial vehicle dynamic path planning with high maneuver and high performance is realized, and the smoothness and safety of the flight track are improved.
Although the steps in the flowcharts described above are shown in order as indicated by arrows, these steps are not necessarily executed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders.
In another embodiment, as shown in fig. 8, a second aspect of the present invention provides a system for planning an inspection path of a drone, including:
a data acquisition module 10 for acquiring three-dimensional point cloud data of an electric power facility;
a model construction module 20, configured to establish an environmental mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model;
the data filtering module 30 is configured to filter the three-dimensional point cloud data by using a point cloud filtering algorithm to obtain an obstacle;
an obstacle updating module 40, configured to update the confidence level of the obstacle in the environmental mathematical model according to a bayesian estimation principle, so as to obtain an obstacle map;
a distance calculating module 50, configured to calculate a euclidean distance between the obstacles in the obstacle map through a fast-travelling algorithm;
and a path planning module 60, configured to plan a patrol path of the electric power facility according to the obstacle map and the euclidean distance.
It should be noted that, each module in the unmanned aerial vehicle-based inspection path planning system may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules. For a specific limitation of the unmanned aerial vehicle inspection path planning system, see the limitation of the unmanned aerial vehicle inspection path planning method, the two have the same functions and roles, and are not described herein.
A third aspect of the present invention provides an electronic device comprising:
a processor, a memory, and a bus;
the bus is used for connecting the processor and the memory;
the memory is used for storing operation instructions;
the processor is configured to, by invoking the operation instruction, cause the processor to execute an operation corresponding to the unmanned aerial vehicle routing path planning method according to the first aspect of the present application.
In an alternative embodiment, an electronic device is provided, as shown in fig. 9, the electronic device 5000 shown in fig. 9 includes: a processor 5001 and a memory 5003. The processor 5001 is coupled to the memory 5003, e.g., via bus 5002. Optionally, the electronic device 5000 may also include a transceiver 5004. Note that, in practical applications, the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 is not limited to the embodiment of the present application.
The processor 5001 may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. The processor 5001 may also be a combination of computing functions, e.g., including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
Bus 5002 may include a path to transfer information between the aforementioned components. Bus 5002 may be a PCI bus or an EISA bus, among others. The bus 5002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 9, but not only one bus or one type of bus.
The memory 5003 may be, but is not limited to, ROM or other type of static storage device, RAM or other type of dynamic storage device, which can store static information and instructions, EEPROM, CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disc, etc.), magnetic disk storage or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer.
The memory 5003 is used for storing application program codes for executing the aspects of the present application and is controlled by the processor 5001 for execution. The processor 5001 is operative to execute application code stored in the memory 5003 to implement what has been shown in any of the method embodiments described previously.
Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like.
A fourth aspect of the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method for unmanned aerial vehicle inspection path planning as set forth in the first aspect of the present application.
Yet another embodiment of the present application provides a computer readable storage medium having stored thereon a computer program which, when run on a computer, causes the computer to perform the corresponding content of the foregoing method embodiments.
Furthermore, an embodiment of the present invention proposes a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements the steps of the above-mentioned method.
In summary, the invention relates to the technical field of unmanned aerial vehicle inspection and obstacle avoidance, and discloses an unmanned aerial vehicle inspection path planning method, system, equipment and medium, wherein the method comprises the following steps: acquiring three-dimensional point cloud data of an electric power facility; establishing an environment mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model; filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle; updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle diagram; calculating Euclidean distances among the obstacles in the obstacle diagram through a fast travelling algorithm; and planning a patrol path of the electric power facility according to the obstacle diagram and the Euclidean distance. The invention realizes rapid and accurate three-dimensional perception based on the depth information environment three-dimensional perception technology; and realizing high-performance dynamic path planning by using environment sensing and positioning information.
In this specification, each embodiment is described in a progressive manner, and all the embodiments are directly the same or similar parts referring to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments. It should be noted that, any combination of the technical features of the foregoing embodiments may be used, and for brevity, all of the possible combinations of the technical features of the foregoing embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few preferred embodiments of the present application, which are described in more detail and are not thereby to be construed as limiting the scope of the invention. It should be noted that modifications and substitutions can be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and substitutions should also be considered to be within the scope of the present application. Therefore, the protection scope of the patent application is subject to the protection scope of the claims.
Claims (10)
1. The unmanned aerial vehicle inspection path planning method is characterized by comprising the following steps of:
acquiring three-dimensional point cloud data of an electric power facility;
establishing an environment mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model;
filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle;
updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle diagram;
calculating Euclidean distances among the obstacles in the obstacle diagram through a fast travelling algorithm;
and planning a patrol path of the electric power facility according to the obstacle diagram and the Euclidean distance.
2. The unmanned aerial vehicle inspection path planning method of claim 1, wherein the acquiring three-dimensional point cloud data of the electric power facility comprises:
gridding a two-dimensional space, and adjusting the size of the grid according to the type of the electric power facility and the density of the point cloud;
extracting and combining the characteristic information in each grid to obtain three-dimensional point cloud data of the electric power facilities; the characteristic information includes at least average height, point cloud density, and color information.
3. The unmanned aerial vehicle inspection path planning method according to claim 1, wherein the establishing an environmental mathematical model according to the three-dimensional point cloud data comprises:
representing the shape and the position of the power transmission tower in the three-dimensional point cloud data through a geometric body or a three-dimensional model, and marking the height and the occupied area of the power transmission tower to obtain the power transmission tower model;
modeling a transformer substation in the three-dimensional point cloud data in a building form, and adding a transformer and switching equipment to obtain the modeling of the transformer substation;
and representing the starting point, the ending point and the line type of the power transmission line in the three-dimensional point cloud data through line segments or curves to obtain the power transmission line model.
4. The unmanned aerial vehicle inspection path planning method according to claim 2, wherein the filtering the three-dimensional point cloud data by the point cloud filtering algorithm to obtain an obstacle comprises:
determining the number of filter windows according to the grids, so that the number of the grids is equal to the number of the windows; the size of the window is odd;
traversing each grid in each window, sorting the values of all grids in the neighborhood of the grid according to the size, and selecting the value of the middle position as the median value to replace the value of the grid;
and determining the obstacle and the position thereof according to the cruising altitude and the value of the grid.
5. The unmanned aerial vehicle routing path planning method according to claim 1, wherein updating the confidence of the obstacle in the environmental mathematical model by the bayesian estimation principle to obtain an obstacle map comprises:
taking the confidence coefficient of the obstacle at the previous moment as the prior probability;
calculating the likelihood of the obstacle through the density and the height of points in the point cloud;
multiplying the prior probability with likelihood, and carrying out normalization processing to obtain posterior probability;
setting a confidence coefficient threshold value, comparing the confidence coefficient threshold value with posterior probability, and updating the obstacle according to a comparison result;
and combining the updated barriers to form a barrier map.
6. The unmanned aerial vehicle routing path planning method according to claim 1, wherein the calculating the euclidean distance between the obstacles in the obstacle diagram by the fast travelling algorithm comprises:
creating a wave front queue to store a grid where an obstacle at a distance to be updated is located; the expected arrival distances of the grids from the target points are arranged in order from small to large;
adding the known position obstacle in the obstacle diagram into the wave front queue, and performing initial distance marking;
taking out the grids to be calculated from the wave front queue in sequence, calculating the expected arrival distance of the adjacent non-accessed grids, deleting the grids to be calculated from the wave front queue if the calculation result is not smaller than the expected arrival distance of the grids to be calculated, and taking the expected arrival distance of the grids to be calculated as the Euclidean distance from the grids to be calculated to the target point;
and repeating the calculation process of the grid to be calculated and the adjacent non-accessed grids in the wave front queue until the wave front queue is empty, and obtaining the Euclidean distance between the obstacles in the obstacle diagram.
7. The unmanned aerial vehicle routing path planning method of claim 6, wherein after calculating the estimated arrival distance of the neighboring unvisited grids, further comprising:
and if the calculated result is smaller than the expected arrival distance of the head grid, adding the non-accessed grids adjacent to the head grid into the wave front queue, and taking the calculated result as the expected arrival distance of the grid.
8. An unmanned aerial vehicle inspection path planning system, comprising:
the data acquisition module is used for acquiring three-dimensional point cloud data of the electric power facility;
the model construction module is used for building an environment mathematical model according to the three-dimensional point cloud data; the environment mathematical model at least comprises a power transmission tower model, a transformer substation model and a power transmission line model;
the data filtering module is used for filtering the three-dimensional point cloud data through a point cloud filtering algorithm to obtain an obstacle;
the obstacle updating module is used for updating the confidence coefficient of the obstacle in the environment mathematical model through a Bayesian estimation principle to obtain an obstacle map;
the distance calculation module is used for calculating Euclidean distances among the obstacles in the obstacle diagram through a fast travelling algorithm;
and the path planning module is used for planning a routing inspection path of the electric power facility according to the obstacle diagram and the Euclidean distance.
9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the unmanned aerial vehicle inspection path planning method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program when run controls a device in which the computer readable storage medium is located to execute the unmanned aerial vehicle inspection path planning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311596698.3A CN117389305A (en) | 2023-11-27 | 2023-11-27 | Unmanned aerial vehicle inspection path planning method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311596698.3A CN117389305A (en) | 2023-11-27 | 2023-11-27 | Unmanned aerial vehicle inspection path planning method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117389305A true CN117389305A (en) | 2024-01-12 |
Family
ID=89437518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311596698.3A Pending CN117389305A (en) | 2023-11-27 | 2023-11-27 | Unmanned aerial vehicle inspection path planning method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117389305A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117848350A (en) * | 2024-03-05 | 2024-04-09 | 湖北华中电力科技开发有限责任公司 | Unmanned aerial vehicle route planning method for power transmission line construction engineering |
-
2023
- 2023-11-27 CN CN202311596698.3A patent/CN117389305A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117848350A (en) * | 2024-03-05 | 2024-04-09 | 湖北华中电力科技开发有限责任公司 | Unmanned aerial vehicle route planning method for power transmission line construction engineering |
| CN117848350B (en) * | 2024-03-05 | 2024-05-07 | 湖北华中电力科技开发有限责任公司 | Unmanned aerial vehicle route planning method for power transmission line construction engineering |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3384360B1 (en) | Simultaneous mapping and planning by a robot | |
| CN108319655B (en) | Method and device for generating grid map | |
| Xuexi et al. | SLAM algorithm analysis of mobile robot based on lidar | |
| KR102548282B1 (en) | High-precision mapping method and device | |
| CN110531760B (en) | Boundary exploration autonomous mapping method based on curve fitting and target point neighborhood planning | |
| CN109509210B (en) | Obstacle tracking method and device | |
| US8199977B2 (en) | System and method for extraction of features from a 3-D point cloud | |
| EP3822852B1 (en) | Method, apparatus, computer storage medium and program for training a trajectory planning model | |
| Weng et al. | Pole-based real-time localization for autonomous driving in congested urban scenarios | |
| CN108280866B (en) | Road point cloud data processing method and system | |
| CN108267141B (en) | Road point cloud data processing system | |
| Jaspers et al. | Multi-modal local terrain maps from vision and lidar | |
| US11880931B2 (en) | High-definition city mapping | |
| CN117389305A (en) | Unmanned aerial vehicle inspection path planning method, system, equipment and medium | |
| CN111886597A (en) | Obstacle detection method and device for movable platform and movable platform | |
| AU2020375559B2 (en) | Systems and methods for generating annotations of structured, static objects in aerial imagery using geometric transfer learning and probabilistic localization | |
| CN113376638A (en) | Unmanned logistics trolley environment sensing method and system | |
| CN113554705A (en) | Robust positioning method for laser radar in changing scene | |
| CN112433193A (en) | Multi-sensor-based mold position positioning method and system | |
| CN117553820B (en) | Path planning method, system and equipment in off-road environment | |
| CN115061499B (en) | Unmanned aerial vehicle control method and unmanned aerial vehicle control device | |
| Gu et al. | A Review on Different Methods of Dynamic Obstacles Detection | |
| Arukgoda | Vector Distance Transform Maps for Autonomous Mobile Robot Navigation | |
| Zhan et al. | ROS-based Mobile Robot for Pavement Defect Detection | |
| CN116126022A (en) | Control method, control terminal and readable storage medium of inspection unmanned aerial vehicle |
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 |