Path optimization method for electric power inspection robot with photovoltaic module in extremely cold area
By setting up photovoltaic components on the power inspection robot and optimizing the path planning, the power attenuation of power inspection robots in extremely cold areas has been solved, the working radius and safety are improved, and the inspection time is extended.
Patent Information
- Application Number
- CN202411099782.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-22
AI Technical Summary
In extremely cold areas, traditional power inspection robots have increased additional energy consumption due to the power attenuation of the power system, which affects the working radius and inspection efficiency of the robot.
Photovoltaic components are set up on the power inspection robot, and the optimal inspection path is generated by obtaining the task and meteorological data to be planned, and the pre-charged electrical energy of the photovoltaic components on the passable roads is used to optimize the use of electrical energy and extend the working time of the robot.
Through the optimization of photovoltaic modules, the working radius and safety of the power inspection robot are improved, inspection interruptions caused by insufficient power are avoided, and the robot's endurance is enhanced.
Smart Images

Figure CN119002492A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to path optimization, and belongs to the technical field of photovoltaic charging and path optimization. Background Art
[0002] An electric power inspection robot is a robot that can conduct equipment inspections autonomously or semi-autonomously, and can monitor, diagnose and maintain equipment using sensors, algorithms and other means. In the electric power industry, for high-voltage power transmission and transformation scenarios, there are often a large number of equipment that needs to be inspected, such as large transformers, transmission towers, etc. Such equipment is large in size and widely distributed. The traditional manual inspection process is time-consuming and labor-intensive, and the use of robots instead of manual inspections can effectively save manpower. Common electric power inspection robots have chassis configurations such as wheeled, tracked and stepping, and infrared, optoelectronic equipment and other sensors are carried on the chassis for inspection. In order to achieve a more convenient inspection process, the robot is often equipped with a battery module for power supply so that it can work without the power supply line. However, in extremely cold areas, due to the extremely low temperature (sometimes up to minus 40 degrees Celsius or lower), the power supply system of traditional electric power inspection robots is prone to problems such as power attenuation.
[0003] In the prior art, power supply systems in extremely cold regions often use electric heating to maintain battery temperature, thereby achieving a longer working time. However, this type of technical solution will cause additional energy consumption during operation due to the addition of electric auxiliary heating equipment, which will affect the working radius of the robot. Summary of the invention
[0004] The purpose of the present invention is to solve the problem that the addition of electric auxiliary heating equipment during the use of existing robots will cause additional energy consumption during work, thereby affecting the working radius of the robot. A path optimization method for an electric inspection robot equipped with photovoltaic modules in extremely cold areas is proposed.
[0005] A path optimization method for an electric power inspection robot equipped with photovoltaic modules in extremely cold regions, the method comprising the following steps:
[0006] Step 1: a photovoltaic module is arranged on the outer surface of the power inspection robot, and a task to be planned and meteorological data of the task to be planned of the power inspection robot are obtained, wherein the task to be planned includes a plurality of locations to be inspected within a predetermined area;
[0007] Step 2: Generate multiple inspection paths that traverse multiple inspection locations for the task to be planned, and each inspection path corresponds to an inspection sequence, and for each inspection sequence, there are multiple roads that traverse the inspection sequence;
[0008] Step 3: Determine whether each road is a passable road based on the geographic information on each road, and retain the passable roads;
[0009] Step 4: Input the geographic information and mileage of each passable road into the motion model, and output the estimated power consumption on each passable road;
[0010] The light intensity on a plurality of passable roads is obtained according to the meteorological data, the light coefficient on each passable road is obtained according to the geographical information on each passable road and the position of the photovoltaic components on the power inspection robot, and the pre-charged electric energy of the photovoltaic components on the power inspection robot on each passable road is obtained according to the light coefficient and the light intensity;
[0011] Step 5: According to the pre-consumed power, pre-charged power and pre-stored power of the power inspection robot of each passable road, the remaining power of each passable road is obtained, and a road with the most remaining power is selected from all passable roads corresponding to all inspection paths as the optimal inspection path;
[0012] Step 6: The power inspection robot performs inspections according to the optimal inspection path.
[0013] Preferably, in step 3, whether each road is a passable road is determined based on the geographical information on each road, and the passable roads are retained. The specific process is:
[0014] Step 31: Generate a road grid point between every two adjacent locations to be inspected on each road, and map grid information to the road grid point according to geographic information; the grid information includes the ground type and average slope of the road grid point;
[0015] Step 32: between each two adjacent locations to be inspected on each road, select available road grid points according to the grid information and connect them to form a directed interval path;
[0016] Step 33: Use a depth-first algorithm to search all directional paths between the starting point and the end point of the task to be planned to obtain multiple passable roads.
[0017] Preferably, in step 4, the motion model is expressed as:
[0018]
[0019] In the formula, W1 is the pre-consumed electric energy, l is the mileage, and c is the friction coefficient corresponding to the geographic information.
[0020] Preferably, in step 5, the remaining electric energy W of each passable road is expressed as:
[0021] W=W2+W3-W1
[0022] Wherein, W2 is the pre-stored electric energy of the power inspection robot, and W3 is the pre-charged electric energy.
[0023] Preferably, in step 4, the pre-charged electric energy is expressed as:
[0024] W3=G×r×η×s
[0025] Where G is the light intensity, r is the light coefficient, η is the photovoltaic module conversion efficiency, and s is the photovoltaic module area.
[0026] The beneficial effects of the present invention are:
[0027] In view of the problems in the existing technology that robots in extremely cold regions have high power consumption and unsatisfactory working radius during operation, photovoltaic modules are introduced into the power supply system of the robot in extremely cold regions, and a specific optimization method is configured. Before the power inspection robot starts inspection, the meteorological data related to the inspection location is collected in advance, and the feasible inspection paths are planned separately, and the remaining electric energy on the corresponding path is simulated, that is, the path output with the largest power redundancy coefficient, which improves the safety of the robot inspection and avoids being restricted by the working radius. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 A flow chart of a path optimization method for an electric inspection robot equipped with photovoltaic modules in extremely cold regions;
[0029] Figure 2 It is a multiple inspection route diagram that traverses the four inspection locations ABCD; among them, Figure 2 (a) is the inspection route diagram along ABCD. Figure 2 (b) is the inspection route diagram along the ADCB inspection. Figure 2 (c) is the inspection route diagram along the ACDB inspection;
[0030] Figure 3 This is a schematic diagram showing that there are multiple accessible roads between each two adjacent locations to be inspected. DETAILED DESCRIPTION
[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0032] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.
[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.
[0034] Example:
[0035] Combination Figure 1 This embodiment describes a path optimization method for an electric power inspection robot equipped with photovoltaic modules in an extremely cold region, the method comprising the following steps:
[0036] Step 1: a photovoltaic module is arranged on the outer surface of the power inspection robot, and a task to be planned and meteorological data of the task to be planned of the power inspection robot are obtained, wherein the task to be planned includes a plurality of locations to be inspected within a predetermined area;
[0037] Step 2: Generate multiple inspection paths that traverse multiple inspection locations for the task to be planned, and each inspection path corresponds to an inspection sequence, and for each inspection sequence, there are multiple roads that traverse the inspection sequence;
[0038] Step 3: Determine whether each road is a passable road based on the geographic information on each road, and retain the passable roads;
[0039] Step 4: Input the geographic information and mileage of each passable road into the motion model, and output the estimated power consumption on each passable road;
[0040] The light intensity on a plurality of passable roads is obtained according to the meteorological data, the light coefficient on each passable road is obtained according to the geographical information on each passable road and the position of the photovoltaic components on the power inspection robot, and the pre-charged electric energy of the photovoltaic components on the power inspection robot on each passable road is obtained according to the light coefficient and the light intensity;
[0041] Step 5: According to the pre-consumed power, pre-charged power and pre-stored power of the power inspection robot of each passable road, the remaining power of each passable road is obtained, and a road with the most remaining power is selected from all passable roads corresponding to all inspection paths as the optimal inspection path;
[0042] Step 6: The power inspection robot performs inspections according to the optimal inspection path.
[0043] Specifically, the power inspection robot is provided with a composite power supply system, which includes at least one set of battery modules and photovoltaic charging components;
[0044] The battery module includes a main power module and a backup power module. The main power module uses high-performance lithium batteries or other batteries as the main power source, which is responsible for providing the required power for the power inspection robot under normal circumstances. Through the built-in heating device, when charging at low temperatures, the main power source is heated first, and the main power source is charged after the temperature reaches the set value, ensuring that the main power source is always maintained in a good charging environment for charging, thereby extending the service life of the main power source.
[0045] The backup power module uses lithium titanate batteries or other low-temperature batteries (such as supercapacitors, etc.) as backup power sources. Such batteries have good low-temperature performance and long life characteristics. They can meet the long-term use in low-temperature conditions. Moreover, lithium titanate batteries have low self-discharge and high-rate charge and discharge performance, which meet the requirements of low-temperature backup power. They can also be used as a heating source for the main power supply, heating the main power supply while using it at low temperatures, improving the discharge performance of the main power supply. At the same time, a good use environment can also extend the service life of the main power supply.
[0046] In addition, when the main power supply is insufficient or fails, the backup power supply can output synchronously with the main power supply to meet the load power requirements, and can quickly take over when the main power supply fails to work, providing emergency power for the robot and ensuring that it can return smoothly to the charging station or maintenance point, effectively reducing the risk of the inspection robot crashing midway.
[0047] The main power supply is designed with a tap emergency power output function to ensure that in the event of a fault, when both the backup power supply and the photovoltaic components fail, a forced discharge function is implemented to minimize the impact of downtime during operation on maintenance work.
[0048] The photovoltaic module is responsible for generating electricity to heat the battery compartment as a whole in the presence of light, ensuring that the entire system can work uninterruptedly in a good temperature environment, effectively improving the endurance of the inspection robot. When there is sufficient light, it can promptly supply power to the main and backup power supplies, extending the use time of the inspection robot. It can also provide emergency power to the inspection robot when the main and backup power supplies are discharged or one or both power supplies fail, ensuring that it can smoothly return to the charging station or maintenance point, effectively reducing the risk of the inspection robot shutting down midway due to running out of power or main power failure.
[0049] The power control component is responsible for the on and off of the main and backup power supplies, the opening and closing of the heating device, the charging and discharging hardware switches, and the access to photovoltaic energy. By executing the commands of the core management component, the power inspection robot can work reliably.
[0050] The core management component is responsible for real-time monitoring of the voltage, temperature, current and other states of the main power supply, backup power supply and photovoltaic modules. It executes the threshold protection commands issued by the core management component through the power control component to realize the switching of the power supply, backup power supply and photovoltaic modules, avoid accidents such as overcharging, over-discharging and overcurrent, protect the safe and reliable operation of the power inspection robot, and display the main parameters of the power inspection robot in real time through the display screen to realize human-computer interaction.
[0051] The display is equipped with an intuitive and easy-to-use display screen, which displays important information such as the voltage of the power supply of the power inspection robot, the remaining power (SOC), the status of various sensors of the robot, and the ambient temperature through the interactive interface of the display screen. Operators can remotely monitor and control the power supply system through the interactive interface to improve the convenience and flexibility of operation.
[0052] The charging interface is responsible for charging the inspection robot. The interface adopts a fixed quick-plug method. The external charging device can realize the automatic charging and power-off functions of the inspection robot by exchanging information with the core management component.
[0053] The photovoltaic module is fixed on the robot or attached to the surface of the robot shell through a bracket. When the photovoltaic panel area is large, a combination of an unfolded bracket and a flexible photovoltaic module can also be used. The photovoltaic module can charge the battery module under the control of the control device, and can also shunt power, such as supplying power to the power load on the robot and / or charging the battery module. Depending on the number of battery modules, the battery modules can also be charged separately.
[0054] The task to be planned refers to the workflow determined before the robot sets out for inspection, which is to be carried out in a predetermined area, such as a substation plant or a larger area of power transmission and distribution equipment. It often involves multiple locations to be inspected that need to be reached during this inspection. In order to achieve better planning results, the tasks to be planned need to collect and add corresponding digital maps in advance to record the geographic information in the predetermined area, including the longitude and latitude coordinates of each location to be inspected, the passable area in the predetermined area, etc. In some larger scenarios, such as inspecting multiple transmission towers, terrain height information and basic landform information should be included.
[0055] Meteorological data refers to the meteorological data involved in the time period when the robot performs the inspection task obtained through the external meteorological system, mainly including weather information in the predetermined area, such as sunny, cloudy, rainy area, etc. In order to improve the accuracy of task planning, historical statistical data should also be included, such as the local common solar altitude angle, sunrise and sunset time and average light intensity on the date corresponding to the planned task.
[0056] The inspection path is a plurality of routes that can traverse each inspection location obtained by simulating the inspection location, including a plurality of directed paths distributed in a predetermined area. The robot moves in sequence along the directed paths to pass through each inspection location. In the inspection path, the weather conditions at the corresponding time point and the corresponding position can be obtained according to the meteorological data, so as to determine whether there are weather conditions for power replenishment through photovoltaic modules at a certain point. If so, a charging node is added to the corresponding interval, and the possible power received by the robot under the weather conditions is estimated.
[0057] like Figure 2 As shown, there may be multiple routes, that is, multiple inspection paths, to complete the inspection of multiple locations to be inspected.
[0058] The following further describes that in step 3, based on the geographic information on each road, it is determined whether each road is a passable road, and the passable roads are retained. The specific process is as follows:
[0059] Step 31: Generate a road grid point between every two adjacent locations to be inspected on each road, and map grid information to the road grid point according to geographic information; the grid information includes the ground type and average slope of the road grid point;
[0060] Step 32: between each two adjacent locations to be inspected on each road, select available road grid points according to the grid information and connect them to form a directed interval path;
[0061] Step 33: Use a depth-first algorithm to search all directional paths between the starting point and the end point of the task to be planned to obtain multiple passable roads.
[0062] Specifically, after extracting the location to be inspected, the geographical information related to the vicinity of the location to be inspected is parsed from the digital map to obtain the latitude and longitude, ground type (paved road, unpaved road, uneven area, gravel surface, inaccessible area, etc.), height, etc.
[0063] According to geographic information, a directed interval path is created between each inspection location, such as from A to B or from B to A, etc. In the actual driving process, the energy consumption will be different due to the different slopes passed. When setting the directed interval path, it should bypass the inaccessible area according to the geographic information.
[0064] Since the load of the robot itself is fixed, it is easy to determine the energy consumption required for the robot to travel unit mileage on different slopes and road types by looking up the table according to the geographic information and the robot motion model obtained in advance. Combined with the length of the directed interval path, the estimated power consumption on each directed interval path can be obtained.
[0065] Finally, the directed interval paths are assembled to obtain the paths to be screened that can traverse each location to be inspected, and the power consumption is estimated to sort the paths to be screened to obtain multiple inspection paths with low overall energy consumption output.
[0066] In order to achieve an effective estimation process for the road, the task area where the inspection site is located is first gridded and divided into quadrilateral grid surfaces or other equivalent grid surfaces. Then, the grid information is mapped to the road grid points according to the geographic information, including landform division according to satellite images. Then, the road grid points are mapped to different ground types, including impassable areas, and each road grid point is mapped to a different height according to the contour map. Then, a sliding window, such as a 3*3 window, is used to search for each road grid point, and the average slope of each road grid point is calculated according to the height change of adjacent road grid points.
[0067] Then, the available road grid points are screened according to the grid information between each inspection location and connected to form a directed interval path, including screening the road type to exclude impassable areas, and removing areas that the robot cannot pass according to the average slope, etc., and then each inspection location is connected to form a directed interval path.
[0068] Finally, the pre-consumed power is generated according to the grid information and motion.
[0069] In order to compare each path, the depth-first algorithm is first used to search the directed interval path from the starting point of the task to be planned to obtain multiple paths to be screened that can pass through all the inspection locations. Among them, the constraint condition of the depth-first algorithm should be set to pass through each inspection location, and each inspection location should only be passed once.
[0070] In order to effectively control the path length, the grid points passed by are counted during the depth-first algorithm search, and a larger counting threshold is configured to eliminate the paths that are obviously too long to be screened.
[0071] Subsequently, for each path to be screened, the path estimated power consumption is generated according to the estimated power consumption corresponding to the directed interval path contained in the path to be screened. Finally, the paths to be screened are sorted according to the path estimated power consumption and multiple inspection paths with the lowest path estimated power consumption are output, such as the lowest five paths.
[0072] In order to achieve a better charging condition estimation process, for the inspection path and the departure time of the task to be planned, the time node interval of the power inspection robot when it is moving along the inspection path is calculated respectively, including the position-time comparison relationship, and then the information of the corresponding time in the meteorological data is read, including the sun's altitude position, cloud map and other information, and then the weather at a specific location at a specific time is determined by referring to the position, and the local available light conditions, including illumination, sun direction, etc., are determined in combination with historical observation data. Combined with the parameters of the photovoltaic components set on the robot, including the type of photovoltaic components, the direction and area of light received, and the minimum illumination that can be charged, a comprehensive comparison is made to determine the actual available light conditions that can be used for charging. Finally, a charging node is added to the time node interval according to the available light conditions. The charging node includes the time when charging can start, the charging power estimated according to the illumination in the available light conditions, and the location where charging can be performed. In order to improve the accuracy of the record, the charging node is marked with the above-mentioned grid points, that is, each charging node includes multiple grid points in the corresponding time period.
[0073] In order to achieve better estimation results, for each path to be screened, the road grid points passed on the path to be screened were read respectively, and then the travel speed data obtained from the robot's preliminary test was compared with the geographic information to determine the time required for the robot to pass a certain road grid point. The grid point time was then mapped to the path to be screened in turn, and the departure time was used as the mapping starting point to obtain the time node interval and realize an accurate mapping process.
[0074] In order to effectively determine the available lighting conditions, the search vector is assembled according to the road grid points corresponding to the time node interval. The search vector includes two dimensions: road grid points and time. Subsequently, the meteorological data is searched using the search vector to determine the meteorological information at the corresponding road grid point and time, mainly including whether it is located below the clouds, the height of the sun and other information. According to this part of information combined with geographic information, including mountain occlusion, etc., it is easy to determine its lighting conditions, and combined with the robot's fixed parameters, including photovoltaic panel area, orientation, etc., to determine the available lighting conditions.
[0075] In order to achieve a better path screening effect, after adding charging nodes to the path, the light intensity in the time node interval corresponding to the charging node is determined according to the available lighting conditions, and the light coefficient is determined according to the road information corresponding to the road grid point. This part of the light coefficient is obtained by comprehensive calculation of the following parameters: ground slope, robot's passing direction, initial installation angle of photovoltaic panels, and shading conditions.
[0076] Among them, the initial installation angle of the photovoltaic module is the angle of the photovoltaic module on the robot to the ground when the robot is on a horizontal plane, which is reflected as a three-dimensional posture vector. On this basis, combined with the ground slope and the passing direction of the robot, the actual posture vector of the photovoltaic module when passing through the road grid point can be calculated. The normal vector of the actual posture vector is calculated with the sunlight angle, and an illumination angle coefficient is easily obtained;
[0077] Then, according to the obstruction conditions, such as mountains, trees or buildings, the illumination angle coefficient is multiplied by the obstruction coefficient to easily obtain the illumination coefficient. Combined with the estimated charging power, the actual charging power of the road grid point can be obtained.
[0078] On this basis, the average power consumption and passing time in the time node interval are determined according to the road information, and the charge change of the robot when passing each road grid point can be calculated. The charge change curve is fitted according to this part of information, and the task path with the maximum remaining charge (remaining electric energy) is output according to the charge change curve.
[0079] The following further describes that in step 4, the motion model is expressed as:
[0080]
[0081] Where W1 is the pre-consumed electric energy, l is the mileage, and c is the friction coefficient corresponding to the geographic information.
[0082] As further described below, in step 5, the remaining electrical energy W of each passable road is expressed as:
[0083] W=W2+W3-W1
[0084] Wherein, W2 is the pre-stored electric energy of the power inspection robot, and W3 is the pre-charged electric energy.
[0085] The following further describes that in step 4, the pre-charged electric energy is expressed as:
[0086] W3=G×r×η×s
[0087] Where G is the light intensity, r is the light coefficient, η is the photovoltaic module conversion efficiency, and s is the photovoltaic module area.
[0088] Although the present invention is described herein with reference to specific embodiments, it should be understood that these embodiments are merely examples of the principles and applications of the present invention. It should therefore be understood that many modifications may be made to the exemplary embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that the various dependent claims and features described herein may be combined in a manner different from that described in the original claims. It should also be understood that features described in conjunction with individual embodiments may be used in other described embodiments.
Claims
1. A path optimization method for a power inspection robot equipped with photovoltaic modules in extremely cold regions, characterized in that: The method comprises the following steps: Step 1: a photovoltaic module is arranged on the outer surface of the power inspection robot, and a task to be planned and meteorological data of the task to be planned of the power inspection robot are obtained, wherein the task to be planned includes a plurality of locations to be inspected within a predetermined area; Step 2: Generate multiple inspection paths that traverse multiple inspection locations for the task to be planned, and each inspection path corresponds to an inspection sequence, and for each inspection sequence, there are multiple roads that traverse the inspection sequence; Step 3: Determine whether each road is a passable road based on the geographic information on each road, and retain the passable roads; Step 4: Input the geographic information and mileage of each passable road into the motion model, and output the estimated power consumption on each passable road; The light intensity on a plurality of passable roads is obtained according to the meteorological data, the light coefficient on each passable road is obtained according to the geographical information on each passable road and the position of the photovoltaic components on the power inspection robot, and the pre-charged electric energy of the photovoltaic components on the power inspection robot on each passable road is obtained according to the light coefficient and the light intensity; Step 5: According to the pre-consumed power, pre-charged power and pre-stored power of the power inspection robot of each passable road, the remaining power of each passable road is obtained, and a road with the most remaining power is selected from all passable roads corresponding to all inspection paths as the optimal inspection path; Step 6: The power inspection robot performs inspections according to the optimal inspection path.
2. The path optimization method of the power inspection robot equipped with photovoltaic modules in extremely cold regions according to claim 1 is characterized in that: In step 3, based on the geographic information on each road, determine whether each road is a passable road, and retain the passable roads. The specific process is as follows: Step 31: Generate a road grid point between every two adjacent locations to be inspected on each road, and map grid information to the road grid point according to geographic information; the grid information includes the ground type and average slope of the road grid point; Step 32: between each two adjacent locations to be inspected on each road, select available road grid points according to the grid information and connect them to form a directed interval path; Step 33: Use a depth-first algorithm to search all directional paths between the starting point and the end point of the task to be planned to obtain multiple passable roads.
3. The path optimization method of the power inspection robot equipped with photovoltaic modules in extremely cold regions according to claim 1 is characterized in that: In step 4, the motion model is expressed as: In the formula, W1 is the pre-consumed electric energy, l is the mileage, and c is the friction coefficient corresponding to the geographic information.
4. The path optimization method for an electric power inspection robot equipped with photovoltaic modules in extremely cold regions according to claim 4 is characterized in that: In step 5, the remaining electrical energy W of each drivable road is expressed as: W=W2+W3-W1 Wherein, W2 is the pre-stored electric energy of the power inspection robot, and W3 is the pre-charged electric energy.
5. The path optimization method for an electric power inspection robot equipped with photovoltaic modules in extremely cold regions according to claim 4, characterized in that: In step 4, the pre-charged electric energy is expressed as: W3=G×r×η×s Where G is the light intensity, r is the light coefficient, η is the photovoltaic module conversion efficiency, and s is the photovoltaic module area.
Citation Information
Patent Citations
Generating capacity prediction system and method
CN111723962A
Photovoltaic charging station electric energy scheduling method based on weather prediction
CN115765041A
Photovoltaic power abrupt change prediction method
CN115811044A
Photovoltaic power station cleaning intelligent management system
CN117458979A
Charging control method, device and system and vehicle
CN118405002A
Cited By
Self-adaptive path tracking control method and device for unmanned ship
CN120215512A
Distributed mobile robot cooperative control method and system
CN121143165A
Power plant patrol operation robot patrol path planning method and system
CN122237608A
A method and system for inspection path planning of a power plant inspection robot
CN122237608B
