Autonomous navigation obstacle avoidance system and method for intelligent substation inspection robot

Abstract

The invention relates to the technical field of intelligent inspection robots, and discloses an autonomous navigation obstacle avoidance system and method for an intelligent inspection robot of a transformer substation, and the system comprises a data collection module, the output end of the data collection module is connected with the input end of an obstacle avoidance system, and a laser radar module is used for assisting in determining the position of an obstacle. The processor can conveniently obtain a new route, so that the robot body keeps a distance from an obstacle, the robot body can conveniently bypass the obstacle, and the inspection robot can timely and accurately respond to environmental changes to normally advance, so that reliable navigation is realized, an inspection task is smoothly completed, and the adaptability to a complex field environment is high; the method has the capability of autonomously handling emergencies, can avoid the phenomenon of returning to detour due to obstacle blocking, realizes large-range beyond-visual-range sensing, and effectively improves the range and efficiency of single vehicle sensing.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent inspection robots, and in particular to an autonomous navigation obstacle avoidance system and method for an intelligent inspection robot for a substation. Background Art

[0002] A substation is a place in the power system where voltage and current are transformed, electric energy is received and distributed. The substation in a power plant is a step-up substation, and its function is to step up the electric energy generated by the generator and feed it into the high-voltage power grid. The inspection of the substation is that the on-duty personnel observe the appearance of the equipment for any abnormalities through regular inspections, such as whether the color changes, whether there are any foreign objects, whether the needle indication is normal, whether the sound of the equipment is normal, whether there are any abnormal odors, whether the temperature of the equipment that is allowed to be touched is normal, and measure the changes in the operating parameters of the electrical equipment during operation, etc., to determine whether the operating condition of the equipment is normal. The inspection system of the substation is an effective measure to ensure the normal and safe operation of the equipment. It is of great significance to prevent the occurrence of accidents and their scope of impact by understanding the operating condition of the equipment through regular inspections by on-duty personnel, grasping the operating abnormalities, and taking corresponding measures in a timely manner. To this end, the substation should formulate specific inspection methods based on the actual working conditions of the operating equipment and summarizing the lessons learned from previous handling of equipment accidents, obstacles and defects.

[0003] The transmission and transformation lines are relatively complex and there are many types of electrical equipment. It is difficult to accurately identify various types of devices. At the same time, if there are people walking or temporarily placed safety fences during the inspection process, the inspection vehicle cannot respond to environmental changes in a timely and accurate manner and cannot move normally, and thus cannot achieve reliable navigation, resulting in the inspection task cannot be completed smoothly. These situations show that the existing intelligent inspection robots are not adaptable to complex on-site environments and lack the ability to handle emergencies autonomously. During the inspection process, the robot cannot remind staff to clear obstacles on the road according to the inspection situation, and cannot completely replace manual inspections. Summary of the invention

[0004] In view of the above-mentioned existing problems, the existing intelligent inspection robot of the present invention has poor adaptability to complex on-site environments and insufficient ability to handle emergencies autonomously. During the inspection process, the robot cannot remind staff to clear obstacles on the road according to the inspection situation and cannot completely replace manual inspections.

[0005] In order to solve the above technical problems, an autonomous navigation and obstacle avoidance system of a substation intelligent inspection robot is proposed, which is characterized by comprising a data acquisition module, an obstacle avoidance system, a robot, a large database and a control terminal.

[0006] The output end of the data acquisition module is connected to the input end of the obstacle avoidance system, and the obstacle avoidance system is bidirectionally connected with the robot, the big database and the control terminal respectively.

[0007] The obstacle avoidance system includes a control center, the output end of the control center is respectively connected to the input ends of the upper monitoring station, the data receiving module, the path planning module, the positioning unit, the navigation control module and the planning control module, and the control center is bidirectionally connected with the obstacle avoidance module.

[0008] The robot includes a central processing unit, the input end of which is respectively connected to the output ends of a laser radar ranging module, a driving module, a power supply module, a binocular camera and a measuring instrument, and the central processing unit is bidirectionally connected to an interaction unit.

[0009] As a preferred solution of the autonomous navigation and obstacle avoidance system of the substation intelligent inspection robot described in the present invention, the path planning module calculates the initial shortest route from the starting point to the end point through the GPS positioning of the intelligent inspection robot and the calibration of the target point, and then plans the shortest path through the GIS map. The upper monitoring station is used to receive the measurement data sent by the data acquisition module and the status information of the intelligent inspection robot itself, and display them visually on the display, and support users to issue task instructions in the visual display interface.

[0010] The planning control module is used to obtain the data in front of the robot and the data on the left and right sides based on the normalized feasible area, and determine whether to enter the obstacle avoidance state based on the safety factor in front of the robot. In the obstacle avoidance state, the offset waypoint is determined, and the robot speed and turning angle are determined. In the non-obstacle avoidance state, the relative speed between the obstacle in front and the robot is calculated, and the robot's own speed is dynamically adjusted. The navigation control module is used to correct the preset target position based on the distance deviation, perform path planning according to the navigation map and the corrected target position, and control the robot to move to the corrected target position according to the obtained planned path.

[0011] As a preferred solution of the autonomous navigation and obstacle avoidance system of the substation intelligent inspection robot described in the present invention, the obstacle avoidance module includes an obstacle avoidance task generation unit and an obstacle avoidance task self-check unit. The obstacle avoidance task generation unit is used to analyze and process the relevant information and parameters in the large database within the system, and generate the obstacle avoidance task of the intelligent inspection robot. The obstacle avoidance task self-check unit is used to self-check the execution progress of the obstacle avoidance task generated by the obstacle avoidance task generation unit.

[0012] The obstacle avoidance module analyzes and processes the information of obstacles and their surrounding environment collected on-site based on the sensors and binocular cameras of the intelligent inspection robot, generates obstacle avoidance behavior tasks, and sends the obstacle avoidance behavior tasks to the control center through the communication module to control the intelligent inspection robot to perform obstacle avoidance behavior.

[0013] As a preferred solution of the autonomous navigation and obstacle avoidance system of the substation intelligent inspection robot described in the present invention, the data acquisition module includes orientation measurement data and robot status information, and the positioning unit is used to detect the position of the inspection robot.

[0014] The measuring instrument includes an infrared thermometer, a thermal imager and a temperature and humidity measuring instrument. The binocular camera is used to photograph the surrounding environment to obtain depth image data.

[0015] The laser radar ranging module is used to measure the distance between the robot body and the obstacle, and send the distance data to the central processor. The driving module includes a driving wheel and a driven wheel arranged at the bottom of the robot.

[0016] Another object of the present invention is to provide an autonomous navigation and obstacle avoidance method for a substation intelligent inspection robot. This method aims to realize autonomous navigation and obstacle avoidance of the substation intelligent inspection robot. Through precise data collection, processing and path planning, it ensures that the robot can complete the inspection task safely and efficiently in a complex environment, reduce labor costs, and improve inspection efficiency and safety.

[0017] As a preferred solution of the autonomous navigation and obstacle avoidance method of the substation intelligent inspection robot described in the present invention, it is characterized by including: a data acquisition module measures the orientation data of the substation that needs to be inspected and generates a map, and at the same time collects the robot status information and transmits it to the obstacle avoidance system.

[0018] The data receiving module receives the data, the path planning module calculates the initial shortest route from the starting point to the end point through the GPS positioning of the intelligent inspection robot and the calibration of the target point, and then plans the shortest path through the GIS map. The obstacle avoidance module analyzes and processes the information of obstacles and their surrounding environment collected on-site by the various sensors and binocular cameras of the intelligent inspection robot, and generates obstacle avoidance behavior tasks, which are sent to the control center through the communication module to control the intelligent inspection robot to perform obstacle avoidance behavior.

[0019] The laser radar ranging module measures the distance between the robot body and the obstacle, and sends the distance data to the central processor. The binocular camera takes pictures of the surrounding environment to obtain depth image data, and the actual distance deviation is obtained through the depth image data.

[0020] The navigation control module corrects the preset target position according to the distance deviation, performs path planning according to the navigation map and the corrected target position, and controls the robot to move to the corrected target position according to the obtained planned path. The planning control module is used to obtain the data in front of the robot and the data on the left and right sides based on the normalized feasible area, determine whether to enter the obstacle avoidance state based on the safety factor in front of the robot, and determine the offset waypoints, robot speed and turning angle in the obstacle avoidance state; in the non-obstacle avoidance state, calculate the relative speed between the obstacle in front and the robot, and dynamically adjust the robot's own speed.

[0021] As a preferred solution of the autonomous navigation and obstacle avoidance method of the substation intelligent inspection robot described in the present invention, the shortest path includes a path planning module that calculates the initial shortest route Route from the starting point to the end point through the GPS positioning of the intelligent inspection robot and the calibration of the target point:

[0022]

[0023] Among them, Route represents the starting point x 0 To the end point x 1 The total route length, x 0 is the horizontal position of the intelligent inspection robot located by GPS, i.e. the starting point of the route, x 1 is the calibrated horizontal position of the target point, i.e., the end point of the route, A is the weight for adjusting the obstacle avoidance path, λ is the attenuation coefficient, and d i is the distance from the robot to the ith obstacle, Filter(d i ,θ) is the impact of obstacles on the path, θ is the filtering threshold, and n represents the number of obstacles. represents the slope of the path and calculates the length of the curve, and y represents the vertical position of the robot on the map.

[0024] Filter(d i ,θ) is the influence of the obstacle on the path:

[0025]

[0026] Among them, β is the tuning parameter that controls the shape of the hyperbolic function, and γ is the shape parameter of the error function.

[0027] Assume that the straight-line distance between the GPS position of the robot (3) and the calibration of the target point is d min , when Route≤α and Filter(d i ,θ)≤1.5,α=1.1d min , indicating that the obstacle has little impact on the route, and the route with the smallest Route in the current route is selected as the nearest path.

[0028] When Filter(d i ,θ)>α and Filter(d i When ,θ)>1.5, it indicates that the obstacles on the route have a great impact on the route. Through the GIS map, three optimal paths are planned, and the influence of the optimal path is optimized until the influence is no more than α. The Route distance of the optimal path is calculated, and the one with the shortest Route distance is selected as the nearest path.

[0029] As a preferred solution of the autonomous navigation and obstacle avoidance method of the substation intelligent inspection robot described in the present invention, the correction includes obtaining the actual distance deviation Δ through the depth image data:

[0030]

[0031] Among them, d m Indicates the depth value of the mth pixel, d ref represents the reference depth value, and M represents the total number of pixels.

[0032] Correct the preset target position in the GIS map according to the distance deviation:

[0033]

[0034] Among them, x 0 and x 1 Indicates the starting and ending positions of the integration on the x-axis, y 0 and 1 Indicates the starting and ending positions of the integration on the y-axis, z 0 and z 1 represents the starting and ending positions of the integration on the z-axis, σ represents the square of the standard deviation of the depth value, which is used to quantify the discreteness of the depth data; f(·) represents information filtering, which is used to process the depth image data; d(x), d(y) and d(z) represent the depth values ​​of the pixels at the target position in the depth image data, μ represents the arithmetic mean of the depth value, h(x) represents the integrated depth image data, δ is an adjustment positive constant, which is used to adjust the strength of the error correction; L is a limit constant, which is used to limit the size of the correction value to prevent over-correction; g(y) is a normalization function, which is used to normalize the correction value to within the range to ensure the comparability and consistency of the correction value.

[0035] Re-plan the path according to the navigation map and the corrected target position, input position (x', y', z') into Route to recalculate the nearest path planning and control the robot to move to the corrected target position according to the obtained planned path.

[0036] As a preferred solution of the autonomous navigation obstacle avoidance method of a substation intelligent inspection robot described in the present invention, the obstacle avoidance state includes determining whether to enter the obstacle avoidance state based on the safety factor S in front of the robot according to the data obtained in front of the robot and the data on the left and right sides:

[0037]

[0038] Where D is the distance of the robot's front detection area, N is the number of obstacles in the robot's front detection area, and P i is the danger level weight of the ith obstacle, l i is the horizontal distance between the ith obstacle and the robot, ρ is the standard deviation of the weighted distribution of the obstacle danger level, J is the number of obstacles in the detection area on the left and right sides of the robot, Q j is the danger level weight of the j-th obstacle, R j is the horizontal distance from the jth obstacle to the robot, and a represents the continuous distance from the starting point directly in front of the robot, that is, the position of the robot to the front distance D.

[0039] If S>1.5, the area directly in front of the robot is considered safe, the robot is set to a non-obstacle avoidance state, the relative speed between the obstacle in front and the robot is calculated, and the robot's own speed is dynamically adjusted.

[0040]

[0041] Among them, v ref is the relative speed between the front obstacle and the robot, v obstacle , is the speed of the ith obstacle, v robot is the current speed of the robot, and ζ is the speed adjustment coefficient.

[0042] If S≤1.5, the area directly in front of the robot is considered dangerous, and the robot is set to obstacle avoidance state. It needs to take obstacle avoidance measures and determine the offset waypoint E in the obstacle avoidance state. way , determine the robot speed And the rotation angle ω:

[0043]

[0044] Among them, x 0 ,y 0 is the current coordinate of the robot, is the waypoint offset coefficient, ε is the standard deviation of the obstacle distance weight distribution, v is the robot's turning angle, The update speed of the robot.

[0045] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of a method described in the autonomous navigation and obstacle avoidance method of a substation intelligent inspection robot are implemented.

[0046] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method described in the autonomous navigation and obstacle avoidance method of a substation intelligent inspection robot are implemented.

[0047] The beneficial effects of the present invention are as follows: the present invention uses a laser radar module to assist in determining the location of obstacles, which facilitates the processor to obtain a new route, keeps the robot body at a distance from the obstacle, facilitates the robot body to bypass the obstacle, and enables the inspection robot to respond to environmental changes in a timely and accurate manner to move normally, thereby achieving reliable navigation and successfully completing the inspection task. It has strong adaptability to complex on-site environments and has the ability to independently handle emergencies. It can avoid the need to return and take a detour due to obstacles, achieve large-scale beyond-visual-range perception, and effectively improve the range and efficiency of single-vehicle perception. In a wide range of applications, it effectively saves computing resources; secondly, on the preferred path, the intelligent inspection robot's own sensors and cameras are used to generate more accurate obstacle avoidance instructions, achieve efficient and accurate obstacle avoidance, and improve the sensitivity and reaction speed of obstacle avoidance behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0049] Figure 1 A block diagram of the structural principles of an autonomous navigation and obstacle avoidance system for a substation intelligent inspection robot provided in one embodiment of the present invention.

[0050] Figure 2 A structural principle block diagram of a data acquisition module of an autonomous navigation and obstacle avoidance system of a substation intelligent inspection robot provided by an embodiment of the present invention.

[0051] Figure 3 A block diagram of the structural principles of a robot of an autonomous navigation and obstacle avoidance system for an intelligent inspection robot for a substation provided by an embodiment of the present invention.

[0052] Figure 4 A structural principle block diagram of an obstacle avoidance system of an autonomous navigation and obstacle avoidance system for a substation intelligent inspection robot provided by an embodiment of the present invention.

[0053] Figure 5 This is a schematic flowchart of a scheme for an autonomous navigation and obstacle avoidance method of an intelligent inspection robot for a substation provided by an embodiment of the present invention.

[0054] In the figure: 1 data acquisition module; 2 obstacle avoidance system; 21 control center; 22 upper monitoring station; 23 data receiving module; 24 path planning module; 25 positioning unit; 26 navigation control module; 27 planning control module; 28 obstacle avoidance module; 281 obstacle avoidance task generation unit; 282 obstacle avoidance task self-check unit; 3 robot; 31 central processing unit; 32 lidar ranging module; 33 driving module; 34 power supply module; 35 binocular camera; 36 measuring instrument; 361 infrared thermometer; 362 thermal imager; 363 temperature and humidity measuring instrument; 37 interaction unit; 4 large database; 5 control terminal. Specific embodiments

[0055] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific embodiments of the present invention in detail with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0056] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0057] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is separately or selectively mutually exclusive with other embodiments.

[0058] The present invention is described in detail in conjunction with the schematic diagrams. When detailing the embodiments of the present invention, for the convenience of explanation, the cross-sectional views showing the device structure will be enlarged locally not in accordance with the general ratio, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0059] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0060] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0061] Example 1, reference Figure 1-Figure 4 , which is the first embodiment of the present invention, provides an autonomous navigation and obstacle avoidance system for a substation intelligent inspection robot, including a data acquisition module 1, an obstacle avoidance system 2, a robot 3, a large database 4 and a control terminal 5.

[0062] The output end of the data acquisition module 1 is connected to the input end of the obstacle avoidance system 2, and the obstacle avoidance system 2 is bidirectionally connected with the robot 3, the big database 4 and the control terminal 5 respectively.

[0063] Preferably, the data acquisition module 1 includes orientation measurement data and robot status information, and the positioning unit 25 is used to detect the position of the inspection robot 3 .

[0064] Preferably, the path planning module 24 calculates the initial shortest route from the starting point to the end point through the GPS positioning of the intelligent inspection robot 3 and the calibration of the target point, and then plans the shortest path through the GIS map. The upper monitoring station 22 is used to receive the measurement data sent by the data acquisition module 1 and the status information of the intelligent inspection robot 3 itself, and display them visually on the display, and support users to issue task instructions in the visual display interface.

[0065] Preferably, the planning control module 27 is used to obtain the data in front of the robot 3 and the data on the left and right sides based on the normalized feasible area, and determine whether to enter the obstacle avoidance state based on the safety factor in front of the robot 3. And in the obstacle avoidance state, determine the offset waypoints, and determine the robot speed and turning angle. In the non-obstacle avoidance state, calculate the relative speed between the obstacle in front and the robot 3, and dynamically adjust the speed of the robot 3 itself. The navigation control module 26 is used to correct the preset target position based on the distance deviation, perform path planning according to the navigation map and the corrected target position, and control the robot 3 to move to the corrected target position according to the obtained planned path.

[0066] Preferably, the obstacle avoidance module 28 includes an obstacle avoidance task generation unit 281 and an obstacle avoidance task self-check unit 282, wherein the obstacle avoidance task generation unit 281 is used to analyze and process the relevant information and parameters in the large database 4 in the system, and generate an obstacle avoidance task for the intelligent inspection robot 3, and the obstacle avoidance task self-check unit 282 is used to self-check the execution progress of the obstacle avoidance task generated by the obstacle avoidance task generation unit.

[0067] The obstacle avoidance module 28 analyzes and processes the information of obstacles and their surrounding environment collected on-site based on the sensors and binocular camera 35 of the intelligent inspection robot 3, generates an obstacle avoidance behavior task, and sends the obstacle avoidance behavior task to the control center 21 through the communication module to control the intelligent inspection robot 3 to perform obstacle avoidance behavior.

[0068] Furthermore, the obstacle avoidance system 2 includes a control center 21, the output end of the control center 21 is respectively connected to the input ends of the upper monitoring station 22, the data receiving module 23, the path planning module 24, the positioning unit 25, the navigation control module 26 and the planning control module 27, and the control center 21 is bidirectionally connected with the obstacle avoidance module 28.

[0069] It should be noted that the robot 3 includes a central processing unit 31, the input end of the central processing unit 31 is respectively connected to the output ends of the laser radar ranging module 32, the driving module 33, the power supply module 34, the binocular camera 35 and the measuring instrument 36, and the central processing unit 31 is bidirectionally connected with the interaction unit 37.

[0070] Preferably, the laser radar ranging module 32 is used to measure the distance between the robot 3 body and the obstacle, and send the distance data to the central processor 31, and the driving module 33 includes a driving wheel and a driven wheel arranged at the bottom of the robot 3.

[0071] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0072] Embodiment 2, the second embodiment of the present invention, provides an autonomous navigation and obstacle avoidance method for a substation intelligent inspection robot. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0073] In a simulated substation environment, multiple inspection points are set up to simulate real inspection tasks; the intelligent inspection robot is started, the substation map is generated through the data acquisition module, and the status information is transmitted to the obstacle avoidance system; the path planning module calculates the initial shortest route using GPS positioning and target point calibration, and plans the optimal path through the GIS map; the robot detects obstacles along the way and collects depth image data through the binocular camera to correct the target position; the navigation control module replans the path according to the corrected target position and controls the robot movement; the time and path efficiency of the entire robot inspection, as well as the obstacle avoidance success rate, are recorded.

[0074] The performance of the intelligent inspection robot and the reference robot in the inspection task is shown in Table 1.

[0075] Table 1

[0076]

[0077] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0078] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that:

[0079] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0080] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0081] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0082] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0083] Example 4, reference Figure 5 , which is the fourth embodiment of the present invention, and provides an autonomous navigation and obstacle avoidance method for a substation intelligent inspection robot, comprising:

[0084] S1: The data acquisition module 1 measures the position data of the substation that needs to be inspected and generates a map. At the same time, it collects the robot status information and transmits it to the obstacle avoidance system 2.

[0085] S2: The data receiving module 23 receives the data, the path planning module 24 calculates the initial shortest route from the starting point to the end point through the GPS positioning of the intelligent inspection robot 3 and the calibration of the target point, and then plans the shortest path through the GIS map. The obstacle avoidance module 28 analyzes and processes the information of obstacles and their surrounding environment collected on-site according to the sensors and binocular camera 35 of the intelligent inspection robot 3, and generates an obstacle avoidance behavior task, and sends the obstacle avoidance behavior task to the control center 21 through the communication module to control the intelligent inspection robot 3 to perform obstacle avoidance behavior.

[0086] Furthermore, the shortest path includes the path planning module 24 calculating the initial shortest route Route from the starting point to the end point through the GPS positioning of the intelligent inspection robot 3 and the calibration of the target point:

[0087]

[0088] Among them, Route represents the starting point x 0 To the end point x 1 The total route length, x 0 is the horizontal position of the GPS positioning of the intelligent inspection robot 3, that is, the starting point of the route, x 1 is the calibrated horizontal position of the target point, i.e., the end point of the route, A is the weight for adjusting the obstacle avoidance path, λ is the attenuation coefficient, and d i is the distance from the robot to the ith obstacle, Filter(d i ,θ) is the impact of obstacles on the path, θ is the filtering threshold, and n represents the number of obstacles. Let \(x\) represent the length of the slope calculation curve of the path, and \(y\) represent the vertical position of the robot on the map.

[0089] Filter(d i , θ) is the degree of influence of the obstacle on the path:

[0090]

[0091] Among them, β is the adjustment parameter that controls the shape of the hyperbolic function, and γ is the shape parameter of the error function.

[0092] Set the straight-line distance between the GPS positioning of the robot (3) and the calibration of the target point to be d min , when Route ≤ α and Filter(d i , θ) ≤ 1.5, α = 1.1d min , indicating that the influence of the obstacle on the route is small, and select the route with the smallest Route in the current route as the nearest path.

[0093] When Filter(d i , θ) > α and Filter(d i , θ) > 1.5, it indicates that the influence of the obstacle on the route is large. Through the GIS map, three optimal paths are planned, and the influence degree of the optimal path is optimized until the influence degree is not greater than α. Calculate the Route distance of the optimal path, and select the one with the nearest Route distance as the nearest path.

[0094] S3: The lidar ranging module 32 measures the distance between the robot 3 body and the obstacle, and sends the distance data to the central processor 31. The binocular camera 35 takes pictures of the surrounding environment to obtain depth image data, and obtains the actual distance deviation through the depth image data.

[0095] Furthermore, the actual distance deviation Δ is obtained through the depth image data:

[0096]

[0097] Among them, d m represents the depth value of the m-th pixel point, d ref represents the reference depth value, and M represents the total number of pixel points.

[0098] S4: The navigation control module 26 corrects the preset target position according to the distance deviation, performs path planning according to the navigation map and the corrected target position, and controls the robot 3 to move to the corrected target position according to the obtained planned path. The planning control module 27 is used to obtain the data in front of the robot 3 and the data on the left and right sides based on the normalized feasible area, and determines whether to enter the obstacle avoidance state based on the safety factor in front of the robot 3, and in the obstacle avoidance state, determines the offset waypoints, and determines the robot speed and turning angle. In the non-obstacle avoidance state, the relative speed between the obstacle in front and the robot 3 is calculated, and the speed of the robot 3 itself is dynamically adjusted.

[0099] It should be noted that the preset target position is corrected in the GIS map according to the distance deviation:

[0100]

[0101] Among them, x 0 and x 1 Indicates the starting and ending positions of the integration on the x-axis, y 0 and 1 Indicates the starting and ending positions of the integration on the y-axis, z 0 and z 1 represents the starting and ending positions of the integration on the z-axis, σ represents the square of the standard deviation of the depth value, which is used to quantify the discreteness of the depth data; f(·) represents information filtering, which is used to process the depth image data; d(x), d(y) and d(z) represent the depth values ​​of the pixels at the target position in the depth image data, μ represents the arithmetic mean of the depth value, h(x) represents the integrated depth image data, δ is an adjustment positive constant, which is used to adjust the strength of the error correction; L is a limit constant, which is used to limit the size of the correction value to prevent over-correction; g(y) is a normalization function, which is used to normalize the correction value to within the range to ensure the comparability and consistency of the correction value.

[0102] Re-plan the path according to the navigation map and the corrected target position, input position (x', y', z') into Route to recalculate the nearest path planning, and control the robot 3 to move to the corrected target position according to the obtained planned path.

[0103] It should also be noted that, by obtaining the data in front of the robot 3 and the data on the left and right sides, it is determined whether to enter the obstacle avoidance state based on the safety factor S in front of the robot 3:

[0104]

[0105] Where D is the distance of the robot's front detection area, N is the number of obstacles in the robot's front detection area, and P iis the danger level weight of the ith obstacle, l i is the horizontal distance between the ith obstacle and the robot, ρ is the standard deviation of the weighted distribution of the obstacle danger level, J is the number of obstacles in the detection area on the left and right sides of the robot, Q j is the danger level weight of the j-th obstacle, R j is the horizontal distance from the jth obstacle to the robot, and a represents the continuous distance from the starting point directly in front of the robot, that is, the position of the robot to the front distance D.

[0106] If S>1.5, the area directly in front of the robot is considered safe, the robot is set to a non-obstacle avoidance state, the relative speed between the obstacle in front and the robot 3 is calculated, and the speed of the robot 3 itself is dynamically adjusted.

[0107]

[0108] Among them, v ref is the relative speed between the front obstacle and the robot, v obstacle, is the velocity of the ith obstacle, v robot is the current speed of the robot, and ζ is the speed adjustment coefficient.

[0109] If S≤1.5, the area directly in front of the robot is considered dangerous, and the robot is set to obstacle avoidance state. It needs to take obstacle avoidance measures and determine the offset waypoint E in the obstacle avoidance state. way , determine the robot speed And the rotation angle ω:

[0110]

[0111] Among them, x 0 ,y 0 is the current coordinate of the robot, is the waypoint offset coefficient, ε is the standard deviation of the obstacle distance weight distribution, v is the robot's turning angle, The update speed of the robot.

[0112] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An autonomous navigation and obstacle avoidance system for a substation intelligent inspection robot, characterized in that: It includes a data acquisition module (1), an obstacle avoidance system (2), a robot (3), a large database (4) and a control terminal (5); The output end of the data acquisition module (1) is connected to the input end of the obstacle avoidance system (2), and the obstacle avoidance system (2) is bidirectionally connected with the robot (3), the large database (4) and the control terminal (5) respectively; The obstacle avoidance system (2) comprises a control center (21), the output end of the control center (21) is respectively connected to the input ends of an upper monitoring station (22), a data receiving module (23), a path planning module (24), a positioning unit (25), a navigation control module (26) and a planning control module (27), and the control center (21) is bidirectionally connected to the obstacle avoidance module (28); The robot (3) comprises a central processing unit (31), the input end of the central processing unit (31) is respectively connected to the output ends of a laser radar ranging module (32), a driving module (33), a power supply module (34), a binocular camera (35) and a measuring instrument (36), and the central processing unit (31) is bidirectionally connected to an interaction unit (37).

2. The autonomous navigation and obstacle avoidance system of a substation intelligent inspection robot according to claim 1, characterized in that: The path planning module (24) calculates the initial shortest route from the starting point to the end point through the GPS positioning of the intelligent inspection robot (3) and the calibration of the target point, and then plans the shortest path through the GIS map. The upper monitoring station (22) is used to receive the measurement data sent by the data acquisition module (1) and the state information of the intelligent inspection robot (3) itself, and visually display them on the display, and support the user to issue task instructions in the visual display interface; The planning control module (27) is used to obtain the data in front of the robot (3) and the data on the left and right sides based on the normalized feasible area, and determine whether to enter the obstacle avoidance state based on the safety factor in front of the robot (3); and in the obstacle avoidance state, determine the offset waypoint, determine the robot speed and turning angle; in the non-obstacle avoidance state, calculate the relative speed between the obstacle in front and the robot (3), and dynamically adjust the speed of the robot (3) itself. The navigation control module (26) is used to correct the preset target position based on the distance deviation, perform path planning according to the navigation map and the corrected target position, and control the robot (3) to move to the corrected target position according to the obtained planned path.

3. The autonomous navigation and obstacle avoidance system of a substation intelligent inspection robot according to claim 2, characterized in that: The obstacle avoidance module (28) comprises an obstacle avoidance task generation unit (281) and an obstacle avoidance task self-checking unit (282); the obstacle avoidance task generation unit (281) is used to analyze and process relevant information and parameters in a large database (4) in the system, and generate an obstacle avoidance task for the intelligent inspection robot (3); and the obstacle avoidance task self-checking unit (282) is used to self-check the execution progress of the obstacle avoidance task generated by the obstacle avoidance task generation unit; The obstacle avoidance module (28) analyzes and processes information on obstacles and their surroundings collected on site based on the sensors and binocular camera (35) of the intelligent inspection robot (3), generates an obstacle avoidance behavior task, and sends the obstacle avoidance behavior task to the control center (21) via the communication module to control the intelligent inspection robot (3) to perform obstacle avoidance behavior.

4. The autonomous navigation and obstacle avoidance system of a substation intelligent inspection robot according to claim 3, characterized in that: The data acquisition module (1) includes orientation measurement data and robot status information, and the positioning unit (25) is used to detect the position of the inspection robot (3); The measuring instrument (36) includes an infrared thermometer (361), a thermal imager (362) and a temperature and humidity measuring instrument (363), and the binocular camera (35) is used to photograph the surrounding environment to obtain depth image data; The laser radar distance measurement module (32) is used to measure the distance between the robot (3) body and the obstacle, and send the distance data to the central processor (31); the driving module (33) comprises a driving wheel and a driven wheel arranged at the bottom of the robot (3).

5. A method using an autonomous navigation and obstacle avoidance system of a substation intelligent inspection robot as claimed in any one of claims 1 to 4, characterized in that: include, The data acquisition module (1) measures the position data of the substation to be inspected and generates a map, and at the same time collects the robot status information and transmits it to the obstacle avoidance system (2); The data receiving module (23) receives the data, the path planning module (24) calculates the initial shortest route from the starting point to the end point through the GPS positioning of the intelligent inspection robot (3) and the calibration of the target point, and then plans the shortest path through the GIS map, the obstacle avoidance module (28) analyzes and processes the information of obstacles and their surrounding environment collected on site based on the sensors and binocular camera (35) of the intelligent inspection robot (3), and generates an obstacle avoidance behavior task, and sends the obstacle avoidance behavior task to the control center (21) through the communication module to control the intelligent inspection robot (3) to perform obstacle avoidance behavior; The laser radar ranging module (32) measures the distance between the robot (3) body and the obstacle, and sends the distance data to the central processor (31); the binocular camera (35) photographs the surrounding environment to obtain depth image data, and the actual distance deviation is obtained through the depth image data; The navigation control module (26) corrects the preset target position according to the distance deviation, performs path planning according to the navigation map and the corrected target position, and controls the robot (3) to move to the corrected target position according to the obtained planned path. The planning control module (27) is used to obtain the data in front of the robot (3) and the data on the left and right sides based on the normalized feasible area, determine whether to enter the obstacle avoidance state based on the safety factor in front of the robot (3), and determine the offset waypoints, the robot speed and the turning angle in the obstacle avoidance state; in the non-obstacle avoidance state, calculate the relative speed between the obstacle in front and the robot (3), and dynamically adjust the speed of the robot (3) itself.

6. The autonomous navigation and obstacle avoidance method of a substation intelligent inspection robot according to claim 5, characterized in that: The shortest path includes a path planning module (24) that calculates the initial shortest route Route from the starting point to the end point through the GPS positioning of the intelligent inspection robot (3) and the calibration of the target point: Wherein, Route represents the total route length from the starting point x0 to the end point x1, x0 is the horizontal position of the GPS positioning of the intelligent inspection robot (3), that is, the starting point of the route, x1 is the calibrated horizontal position of the target point, that is, the end point of the route, A is the weight for adjusting the obstacle avoidance path, λ is the attenuation coefficient, and d i is the distance from the robot to the ith obstacle, Filter(d i ,θ) is the impact of obstacles on the path, θ is the filtering threshold, and n represents the number of obstacles. represents the slope of the path and the length of the curve, and y represents the vertical position of the robot on the map; Filter(d i ,θ) is the influence of the obstacle on the path: Among them, β is the adjustment parameter that controls the shape of the hyperbolic function, and γ is the shape parameter of the error function; Assume that the straight-line distance between the GPS position of the robot (3) and the calibration of the target point is d min , when Route≤α and Filter(d i ,θ)≤1.5,α=1.1d min , indicating that the obstacle has little impact on the route, and the route with the smallest Route in the current route is selected as the nearest path; When Filter(d i ,θ)>α and Filter(d i When ,θ)>1.5, it indicates that the obstacles on the route have a great impact on the route. Through the GIS map, three optimal paths are planned, and the influence of the optimal path is optimized until the influence is no more than α. The Route distance of the optimal path is calculated, and the one with the shortest Route distance is selected as the nearest path.

7. The autonomous navigation and obstacle avoidance method of a substation intelligent inspection robot according to claim 6, characterized in that: The correction includes obtaining the actual distance deviation Δ through the depth image data: Among them, d m Indicates the depth value of the mth pixel, d ref represents the reference depth value, M represents the total number of pixels; Correct the preset target position in the GIS map according to the distance deviation: Wherein, x0 and x1 represent the starting and ending positions of the integration on the x-axis, y0 and y1 represent the starting and ending positions of the integration on the y-axis, z0 and z1 represent the starting and ending positions of the integration on the z-axis, σ represents the square of the standard deviation of the depth value, which is used to quantify the discreteness of the depth data; f(·) represents information filtering, which is used to process the depth image data; d(x), d(y) and d(z) represent the depth values ​​of the pixels at the target position in the depth image data, μ represents the arithmetic mean of the depth value, h(x) represents the integrated depth image data, δ is an adjustment positive constant, which is used to adjust the strength of the error correction; L is a limit constant, which is used to limit the size of the correction value to prevent over-correction; g(y) is a normalization function, which is used to normalize the correction value to within a range to ensure the comparability and consistency of the correction value; Re-plan the path according to the navigation map and the corrected target position, input position (x', y', z') into Route to recalculate the nearest path plan, and control the robot (3) to move to the corrected target position according to the obtained planned path.

8. The autonomous navigation and obstacle avoidance method of a substation intelligent inspection robot according to claim 7, characterized in that: The obstacle avoidance state includes obtaining data in front of the robot (3) and data on the left and right sides, and determining whether to enter the obstacle avoidance state based on a safety factor S in front of the robot (3): Where D is the distance of the robot's front detection area, N is the number of obstacles in the robot's front detection area, and P i is the danger level weight of the ith obstacle, l i is the horizontal distance between the ith obstacle and the robot, ρ is the standard deviation of the weighted distribution of the obstacle danger level, J is the number of obstacles in the detection area on the left and right sides of the robot, Q j is the danger level weight of the j-th obstacle, R j is the horizontal distance between the jth obstacle and the robot, a represents the continuous distance from the starting point directly in front of the robot, that is, the position of the robot to the front distance D; If S>1.5, the area directly in front of the robot is considered safe, the robot is set to a non-obstacle avoidance state, the relative speed between the obstacle in front and the robot (3) is calculated, and the speed of the robot (3) itself is dynamically adjusted. Among them, v ref is the relative speed between the front obstacle and the robot, v obstacle, is the velocity of the ith obstacle, v robot is the current speed of the robot, ζ is the speed adjustment coefficient; If S≤1.5, the area directly in front of the robot is considered dangerous, and the robot is set to obstacle avoidance state. It needs to take obstacle avoidance measures and determine the offset waypoint E in the obstacle avoidance state. way , determine the robot speed And the rotation angle ω: Among them, x0 and y0 are the current coordinates of the robot. is the waypoint offset coefficient, ε is the standard deviation of the obstacle distance weight distribution, v is the robot's turning angle, The update speed of the robot.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 5 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 5 to 8 are implemented.

Images