Intelligent robot path planning system based on Internet of Things

Abstract

The invention discloses an intelligent robot path planning system based on the Internet of Things, and relates to the technical field of robot path planning. The method comprises the following steps: an initial path module for acquiring a starting point position and a final point position of the intelligent robot and generating an initial path; the weather information module is used for acquiring the moving time of the intelligent robot and collecting corresponding moving weather information; the path convenience module is used for evaluating the path convenience of the initial path according to the mobile weather information; the moving convenience module is used for collecting shielding object information in the initial path and analyzing the moving convenience of the robot in combination with the moving weather information; and the path planning module combines the path convenience and the movement convenience to calculate the adaptation degree of the initial path, the initial path with the highest adaptation degree is selected as a target path, and the intelligent robot moves according to the target path. According to the invention, the accuracy of path planning of the intelligent robot based on the Internet of Things is improved.

Description

Technical Field

[0001] The present application relates to the technical field of robot path planning, and in particular to an intelligent robot path planning system based on the Internet of Things. Background Art

[0002] An intelligent robot is a mechanical device integrating a variety of advanced technologies, with the abilities of perception, decision-making and execution. It can imitate or execute human behaviors and tasks, and is a product of the high combination of physical labor and intellectual labor, constructing an artificial machine that can "think". As a technology involving quite a lot of disciplinary knowledge, intelligent robots have almost emerged along with artificial intelligence. And intelligent robots are becoming more and more important in today's society, and more and more fields and positions require the participation of intelligent robots. And the movement of robots is the basic function of robots. In order to make robots more intelligent, general robots will actively plan paths and choose more suitable paths to move. The existing robot path planning mainly considers the obstacle avoidance problem, selects the route with fewer obstacles, and reduces the collision probability. However, in path planning, only fixed obstacles are often considered, and other potential influencing factors affecting the movement of robots are not considered, resulting in inaccurate and incomplete robot path planning. Summary of the Invention

[0003] The purpose of the present invention is to provide an intelligent robot path planning system based on the Internet of Things to solve the problems raised in the above background art.

[0004] An intelligent robot path planning system based on the Internet of Things provided by the present application adopts the following technical solutions: An initial path module, which obtains the starting position and the ending position of the intelligent robot, and generates a path according to the starting position and the ending position, denoted as the initial path; A weather information module, which obtains the moving time of the intelligent robot and collects the weather information corresponding to the moving time, denoted as the moving weather information; A path convenience module, which evaluates the convenience degree of the initial path according to the moving weather information to obtain the path convenience degree of the initial path; A movement convenience module, which collects the occlusion information in the initial path, and analyzes and obtains the convenience degree of the robot movement in combination with the moving weather information, denoted as the movement convenience degree; A path planning module, which calculates the adaptability degree of the initial path by combining the path convenience degree and the movement convenience degree, selects the initial path with the highest adaptability degree as the target path, and the intelligent robot moves according to the target path.

[0005] Preferably, the step of evaluating the convenience degree of the initial path according to the moving weather information to obtain the path convenience degree of the initial path is specifically as follows: Extract the road surface information of the initial path, where the road surface information includes road surface flatness, road surface slope, and road surface skid resistance; Evaluate the convenience of moving on the initial path based on the road surface information, denoted as the basic convenience of the initial path; Evaluate the degree of influence of the weather on the initial path based on the moving weather information to obtain the influence convenience; Subtract the influence convenience from the basic convenience to obtain the path convenience of the initial path.

[0006] Preferably, the step of evaluating the degree of influence of the weather on the initial path based on the moving weather information to obtain the influence convenience is specifically as follows: Judge whether the physical properties of the road surface are affected by the weather according to the road surface information. If the physical properties of the road surface are affected by the weather, extract the weather influence factors that affect the physical properties of the road surface; Collect the required standard values of the road surface for the weather influence factors, and extract the real-time values of the weather influence factors according to the moving weather information; Calculate the difference between the required standard value and the real-time value, denoted as the factor difference, and superimpose the factor differences of all weather influence factors as the influence convenience; If the physical properties of the road surface are not affected by the weather, obtain the historical accident information of the initial path; Statistically form a weather-accident probability table for the historical accident occurrence probabilities of different weathers, and find the corresponding accident probability according to the moving weather information, denoted as the real-time probability; Collect the minimum value of the historical accident probability of the initial path, denoted as the minimum probability, and calculate the difference between the real-time probability and the minimum probability as the influence convenience.

[0007] Preferably, the step of collecting the occlusion information in the initial path, analyzing the convenience of the robot's movement in combination with the moving weather information, and denoting it as the movement convenience is specifically as follows: Judge whether the intelligent robot is affected by the weather according to the moving weather information. If it is affected by the weather, judge whether the interference can be reduced through occlusion; If the interference is reduced through occlusion, collect the occlusion information in the initial path, and evaluate the movement convenience in combination with the moving weather information; If the interference cannot be reduced through occlusion, estimate the number of pedestrians and vehicles on the initial path according to the moving weather information, and obtain the movement convenience according to the number of pedestrians and vehicles; If the intelligent robot is not affected by the weather, count the number of obstacles on the initial path, and obtain the movement convenience according to the number of obstacles.

[0008] Preferably, the step of, if the interference is reduced through occlusion, collecting the occlusion information in the initial path, and evaluating the movement convenience in combination with the moving weather information is specifically as follows: Collect the information of the obstacles in the initial path, and extract the occlusion distance and occlusion area according to the obstacle information; Calculate the basic occlusion degree of the initial path based on the occlusion distance and occlusion area; Classify the obstacles into plant occlusions and non-plant occlusions according to the obstacle information, extract the plant information, and obtain the plant influence degree according to the plant information; Extract the non-plant information, obtain the non-plant influence degree according to the non-plant information, and superimpose the plant influence degree to obtain the occlusion influence degree; Calculate the movement convenience of the intelligent robot on the initial path by subtracting the occlusion influence degree from the basic occlusion degree.

[0009] Preferably, the step of extracting the plant information and obtaining the plant influence degree according to the plant information is specifically as follows: Statistically calculate the average shedding rate of the plants during the movement time as the basic shedding rate according to the plant information; Statistically calculate the average value of the increased shedding rate of the plants under different weather conditions to form a weather-shedding increase rate table, and find the corresponding shedding increase rate according to the movement weather information; Superimpose the basic shedding rate and the shedding increase rate to obtain the plant shedding rate of the plants; Extract the shedding substances of the plants according to the plant information, obtain the substance information of the shedding substances, and analyze the interference degree of the shedding substances on the intelligent robot according to the substance information, which is recorded as the substance interference degree; Statistically calculate the plant occlusion distance, and comprehensively obtain the influence degree of the plants on the intelligent robot, which is recorded as the plant influence degree, in combination with the plant shedding rate and the substance interference degree.

[0010] Preferably, the step of obtaining the substance information of the shedding substances and analyzing the interference degree of the shedding substances on the intelligent robot according to the substance information, which is recorded as the substance interference degree, is specifically as follows: Collect the average height, average weight, and average falling speed of the shedding substances, and calculate the average impact force of the shedding substances based on the average height, average weight, and average falling speed; Collect the edge shape of the shedding substances, and evaluate the average sharpness of the shedding substances according to the edge shape; Collect the average viscosity of the shedding substances, and confirm the substance interference degree of the shedding substances on the intelligent robot in combination with the average impact force and the average sharpness.

[0011] Preferably, the step of extracting the non-plant information and obtaining the non-plant influence degree according to the non-plant information is specifically as follows: Collect the occluding substances of the non-plant occlusions, and extract the service life of the occluding substances according to the non-plant information; Collect the average dropping probability corresponding to the service life of the occluding substances, and obtain the average dropping loss of the occluding substances; Collect the non-plant occlusion distance, set the weight ratios of the non-plant occlusion distance, average drop probability, and average drop loss respectively, and calculate the non-plant influence degree according to the weight ratios.

[0012] Preferably, the step of estimating the number of pedestrians and vehicles on the initial path according to the mobile weather information and obtaining the mobile convenience according to the number of pedestrians and vehicles is specifically as follows: Obtain the historical data of pedestrians and vehicles on the initial path, and extract the average number of pedestrians and average number of vehicles under different weather conditions according to the historical data of pedestrians and vehicles; Find the corresponding average number of pedestrians and average number of vehicles according to the mobile weather information, and record them as the estimated number of pedestrians and the estimated number of vehicles; Overlay the estimated number of pedestrians and the estimated number of vehicles to obtain the estimated number of obstacles; Extract the average number of pedestrians and average number of vehicles on the initial path according to the historical data of pedestrians and vehicles, and overlay the average number of pedestrians and average number of vehicles on the initial path to obtain the standard number of obstacles; Calculate the difference in the number of the standard number of obstacles and the estimated number of obstacles, and combine the occlusion influence degree to obtain the mobile convenience.

[0013] Preferably, the step of counting the number of obstacles on the initial path and obtaining the mobile convenience according to the number of obstacles is specifically as follows: Count the total distance of the initial path and count the number of fixed obstacles on the initial path; Collect the number of times the intelligent robot moves and adjusts its state on the initial path, and record it as the number of adjustments; Combine the total path distance, the number of fixed obstacles, the number of adjustments, and the occlusion influence degree to obtain the mobile convenience.

[0014] In summary, the present application includes at least one of the following beneficial technical effects: 1. Multiple initial paths are formed according to the starting position and the ending position of the intelligent robot. The road surface conditions of the initial paths are evaluated according to the weather information at the departure time of the intelligent robot. The convenience of the paths is evaluated according to the road surface conditions. The convenience degree of the movement of the intelligent robot is evaluated by combining the occlusion information and the weather information in the path. Finally, the best path is selected comprehensively. Planning the path according to the weather conditions and the occlusion conditions in the path makes the path planning more in line with the weather and the actual situation, and is more adaptable to the actual situation of the robot's movement, improving the accuracy of the path planning of the intelligent robot based on the Internet of Things.

[0015] 2. Determine whether the intelligent robot is affected by the weather according to the weather. If it is affected by the weather, check whether the interference can be reduced by occlusion. When the interference cannot be reduced by occlusion, evaluate the convenience of movement based on the estimated number of vehicles and pedestrians in the initial path and the plant information. If there is no weather interference, evaluate the convenience of movement according to the obstacle information. If it is affected by the weather and the interference can be reduced by occlusion, evaluate the convenience of movement according to the information of the occluder. Evaluate the convenience of movement on different paths according to different situations, so as to achieve path planning, which is more adaptable to the actual situation and improves the adaptability of the path planning of the intelligent robot based on the Internet of Things to changes.

[0016] 3. Classify the occluder information into plants and non-plants, and evaluate the impact of plant occluders on the intelligent robot according to the shedding situation of plants and the viscosity and sharpness of the shed substances. For non-plant occluders, evaluate the convenience of movement on the initial path according to the service life and dropping loss of the non-plant occluders. While considering the benefits of choosing occlusion, the potential impacts of occlusion are also considered, which improves the comprehensiveness of the path planning of the intelligent robot based on the Internet of Things. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of module connections of an embodiment of a path planning system for an intelligent robot based on the Internet of Things according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following combines the embodiments and Figure 1 further elaborates on the present invention in detail, but the embodiments of the present invention are not limited thereto.

[0019] The present invention discloses a path planning system for an intelligent robot based on the Internet of Things, which specifically includes the following steps: Initial path module, obtain the starting position and ending position of the intelligent robot, and generate a path based on the starting position and ending position, which is recorded as the initial path.

[0020] There are usually more than one route between the starting position and the ending position of the intelligent robot. According to the existing map information, the intelligent robot can automatically generate multiple movable routes as the initial path.

[0021] Weather information module, obtain the moving time of the intelligent robot, and collect the weather information corresponding to the moving time, which is recorded as the moving weather information.

[0022] By collecting the information of the meteorological station, extract the weather information corresponding to the moving time, including information data such as temperature, humidity, and meteorology.

[0023] Path convenience module, evaluate the convenience degree of the initial path according to the moving weather information, and obtain the path convenience degree of the initial path.

[0024] A mobile convenience module that collects information about obstacles in the initial path, analyzes the mobile weather information to obtain the convenience degree of the robot's movement, and records it as the mobile convenience degree.

[0025] A path planning module that calculates the fitness of the initial path by combining the path convenience degree and the mobile convenience degree, selects the initial path with the highest fitness as the target path, and the intelligent robot moves according to the target path.

[0026] In actual application, the weight ratios of the path convenience degree and the mobile convenience degree are set respectively, and the fitness of the initial path is calculated according to the weight ratios. For example, if the weight ratios of the path convenience degree and the mobile convenience degree are set as 40% and 60% respectively, and the path convenience degree and the mobile convenience degree are 80 and 60 respectively, then the fitness is 80×40% + 60×60% = 68. Whether the movement of the intelligent robot is convenient depends on the one hand on the condition of the path surface in direct contact, and on the other hand on the interference of some obstacles in the path. Evaluating the fitness of the initial path in combination with the weather is more in line with the actual situation, which is conducive to the intelligent robot screening a more suitable path and facilitating the movement of the intelligent robot.

[0027] The steps to evaluate the convenience degree of the initial path according to the mobile weather information and obtain the path convenience degree of the initial path are specifically as follows: Extract the road surface information of the initial path, and the road surface information includes road surface flatness, road surface slope, and road surface anti-slip degree.

[0028] Evaluate the convenience degree of moving on the initial path according to the road surface information, and record it as the basic convenience degree of the initial path.

[0029] Set the weight ratio values of the road surface flatness, road surface slope, and road surface anti-slip degree respectively, and calculate the basic convenience degree according to the weight ratio values. For example, if the road surface flatness, road surface slope, and road surface anti-slip degree are 50, 40, and 80 respectively, and the corresponding weight ratio values are set as 30%, 30%, and 40% respectively, then the basic convenience degree is 50×30% - 40×30% - 80×40% = 59. A system composed of a laser sensor and a vertical acceleration sensor can be used to detect the longitudinal section profile curve of the road surface in real time to obtain the road surface flatness. Measure and record the data with a level, and then calculate the road surface slope according to the horizontal distance and height difference between the measurement points using the trigonometric function relationship. Use a lateral force coefficient test vehicle to measure the lateral force coefficient provided by the road surface at a specific vehicle speed to evaluate the road surface anti-slip degree. It can also be obtained by the user's evaluation of the road surface information. The greater the road surface flatness, the smaller the road surface slope, and the lower the road surface anti-slip degree, the greater the basic convenience degree and the smaller the impact on the robot.

[0030] Evaluate the influence degree of the weather on the initial path according to the mobile weather information to obtain the influence convenience degree.

[0031] Subtract the impact on convenience from the basic convenience to obtain the path convenience of the initial path.

[0032] In actual application, different road surfaces use different materials. Some road surfaces are affected by the weather and will change, thus affecting the movement of the robot and increasing the interference of the road surface on the robot's movement. Therefore, on the basis of the original convenience of the road surface, it is necessary to eliminate the interference of the road surface on the robot caused by the weather, which is more in line with the actual situation, conducive to selecting a more convenient route, and improving the accuracy of the route planning of intelligent robots.

[0033] The steps to obtain the impact on convenience by evaluating the impact of the weather on the initial path according to the mobile weather information are as follows: Judge whether the physical properties of the road surface are affected by the weather according to the road surface information. If the physical properties of the road surface are affected by the weather, extract the weather impact factors that affect the physical properties of the road surface.

[0034] The physical properties of the road surface include strength, stiffness, flatness, etc. Some road surfaces will change due to the influence of the weather due to their different materials. For example, for dirt roads, when it rains, the soil will become loose, so the physical properties of the road surface will change, and the corresponding weather impact factor is rain.

[0035] Collect the required standard values of the road surface for the weather impact factors, and extract the real-time values of the weather impact factors according to the mobile weather information.

[0036] According to the road surface material, the optimal environmental standard for storing the material can be obtained, and the required standard value is extracted according to the optimal environmental standard. For example, the required standard value of the dirt road for rain is 0 ml / s, and then the real-time value corresponding to the rain in the real-time mobile weather information is obtained.

[0037] Calculate the difference between the required standard value and the real-time value and record it as the factor difference, and superimpose the factor differences of all weather impact factors as the impact on convenience.

[0038] Due to the difference in road surface materials, some road surface materials are affected by more than one weather factor. Therefore, by superimposing the factor differences of all weather impact factors, more accurate data results can be obtained. The larger the factor difference, the greater the impact on the road surface, and thus the greater the impact on the intelligent robot brought by the road surface.

[0039] If the physical properties of the road surface are not affected by the weather, obtain the historical accident information of the initial path.

[0040] Statistical the historical accident occurrence probabilities of different weathers to form a weather-accident probability table, and find the corresponding accident probability according to the mobile weather information and record it as the real-time probability.

[0041] Record the historical accident occurrence probabilities under different weather conditions and form a table for comparison one by one. Based on the mobile weather information, find the most similar weather, and use the corresponding accident probability as the real-time probability.

[0042] Collect the minimum value of the historical accident probability of the initial path and record it as the minimum probability. Calculate the difference between the real-time probability and the minimum probability as the impact on convenience.

[0043] In practical applications, when the weather does not cause changes in the physical properties of the road surface, it means that the impact of the weather on the road surface is small and can be ignored. For example, for some asphalt road surfaces, a little light rain hardly affects the movement of intelligent robots. Therefore, the accident probability is used as the evaluation criterion for the impact on convenience. When the weather is extremely bad, the interference with the road surface increases, so the accident occurrence probability will increase. The greater the accident occurrence probability, the more serious the impact on the road surface. Use the minimum value of the accident probability among all weather conditions as the minimum probability, and calculate the difference between the real-time probability and the minimum probability to measure the impact on the road surface.

[0044] The steps to collect the occlusion information in the initial path, analyze it in combination with the mobile weather information to obtain the convenience of the robot's movement and record it as the movement convenience are as follows: Judge whether the intelligent robot is interfered by the weather according to the mobile weather information. If it is interfered by the weather, then judge whether the interference can be reduced by occlusion.

[0045] The weather will interfere with the intelligent robot, but not all weather conditions will interfere with the intelligent robot. At the same time, not all interference caused by the weather can be reduced by occlusion. For example, rain will interfere with the robot, and the interference of rain can be reduced by overhead occlusion. Excessive humidity can also interfere with the robot, but the interference cannot be reduced by overhead occlusion. Sunny and cloudy days will not interfere with the intelligent robot.

[0046] If the interference is reduced by occlusion, then collect the occlusion information in the initial path, and evaluate the movement convenience in combination with the mobile weather information.

[0047] If the interference is not reduced by occlusion, then estimate the number of pedestrians and vehicles on the initial path according to the mobile weather information, and obtain the movement convenience according to the number of pedestrians and vehicles.

[0048] If the intelligent robot is not interfered by the weather, then count the number of obstacles in the initial path, and obtain the movement convenience according to the number of obstacles.

[0049] In practical applications, regarding whether the weather causes interference to the intelligent robot and whether the interference can be reduced by occlusion, the moving convenience of the robot varies in different situations. Adopting a more appropriate convenience evaluation scheme according to the actual situation is conducive to obtaining results that are more in line with the moving background. For example, when the robot is interfered by rain and there are occlusions on the path at this time, it is beneficial for the robot to move. However, when the robot is not affected by the weather, the robot no longer needs to reduce the weather interference through occlusion, and the occlusion at this time will instead interfere with the robot's movement. Therefore, analyzing specific problems specifically is conducive to obtaining more accurate path planning results.

[0050] If the interference is reduced by occlusion, the steps of collecting the occlusion information in the initial path and evaluating the moving convenience in combination with the moving weather information are specifically as follows: Collect the occlusion information in the initial path, and extract the occlusion distance and occlusion area according to the occlusion information.

[0051] Calculate the basic occlusion degree of the initial path based on the occlusion distance and occlusion area.

[0052] Respectively set the weight ratios of the occlusion distance and occlusion area, and calculate the basic occlusion degree according to the weight ratios. For example, if the occlusion distance and occlusion area are 50 meters and 30 square meters respectively, and the set corresponding weight ratios are 50% and 50% respectively, then the basic occlusion degree is 50×50% + 30×50% = 40.

[0053] Classify the occlusions into plant occlusions and non-plant occlusions according to the occlusion information, extract the plant information, and obtain the plant influence degree according to the plant information.

[0054] Extract the non-plant information, obtain the non-plant influence degree according to the non-plant information, and superimpose the plant influence degree to obtain the occlusion influence degree.

[0055] Perform data normalization processing on the plant influence degree and non-plant influence degree and then superimpose them.

[0056] The occlusions are divided into plant occlusions and non-plant occlusions. The influences brought by plant occlusions and non-plant occlusions to the intelligent robot are different. Superimpose the influence degrees of the two to obtain the accurate occlusion influence degree.

[0057] Calculate the moving convenience of the intelligent robot on the initial path by subtracting the occlusion influence degree from the basic occlusion degree.

[0058] In practical applications, the obstacles above the intelligent robot can, on the one hand, shield the intelligent robot from some impacts brought by the weather. For example, they can shield the intelligent robot from rain, snow, and excessive sunlight. However, on the other hand, the obstacles above the intelligent robot itself can also bring some potential interference effects to the intelligent robot. When the shielding distance is longer and the shielding area is larger, the shielding effect on the intelligent robot is better. And under its shielding, the intelligent robot also needs to bear the interference effects brought by the obstacles. Therefore, by subtracting the shielding influence degree from the basic shielding degree, the convenience degree of the robot moving in the path is obtained.

[0059] The steps of extracting plant information and obtaining the plant influence degree according to the plant information are specifically as follows: Statistically calculate the average shedding rate of plants during the moving time based on the plant information as the basic shedding rate.

[0060] Some substances of plants will fall off over time and seasons. For example, some plants shed leaves, some plants drop fruits, and some plants shed flowers and seeds. These are all substances that fall off from plants. Statistically calculate the shedding rate of all substances of plants during the moving time according to the plant habits and record it as the basic shedding rate. Because some plants are prone to shedding, while some plants are not, and the shedding situations are also different in different seasons and at different times, the shedding rates are different.

[0061] Statistically calculate the average value of the increase in the shedding rate of plants under different weather conditions to form a weather-shedding increase rate table, and find the corresponding shedding increase rate according to the moving weather information.

[0062] The shedding rate of plants under different weather conditions will also fluctuate due to the influence of the weather. For example, when it is windy or rainy, because the weather exerts an additional force on the plants, some substances of the plants will become more likely to fall off, increasing the shedding rate.

[0063] Superimpose the basic shedding rate and the shedding increase rate to obtain the plant shedding rate of the plants.

[0064] Extract the shedding substances of the plants according to the plant information, obtain the substance information of the shedding substances, and analyze the interference degree of the shedding substances on the intelligent robot according to the substance information and record it as the substance interference degree.

[0065] Statistically calculate the plant shielding distance, and comprehensively combine the plant shedding rate and the substance interference degree to obtain the influence degree of the plants on the intelligent robot and record it as the plant influence degree.

[0066] In practical applications, the weight ratios are obtained by separately setting the plant occlusion distance, the plant shedding rate, and the material interference degree, and the plant influence degree is calculated based on the weight ratios. For example, if the plant occlusion distance, the plant shedding rate, and the material interference degree are 100 meters, 20%, and 50 respectively, and the weight ratios of the plant occlusion distance, the plant shedding rate, and the material interference degree are 30%, 30%, and 40% respectively, the plant influence degree is 100×30% + 20%×30% + 50×40% = 50.06. The longer the plant occlusion distance, the greater the plant shedding rate, and the greater the material interference degree, the greater the impact of the plant occlusion on the intelligent robot. For example, fallen leaves can interfere with the vision of the intelligent robot, and tree fruits may hit the intelligent robot, causing damage to the intelligent robot.

[0067] The steps of obtaining the material information of the shed substances and analyzing the interference degree of the shed substances on the intelligent robot, which is recorded as the material interference degree, are specifically as follows: Collect the average height, average weight, and average falling speed of the shed substances, and calculate the average impact force of the shed substances based on the average height, average weight, and average falling speed.

[0068] The mass of an object is one of the important factors determining its impact force. The greater the mass, the greater the kinetic energy of the object at the same speed, and thus the greater the possible impact force. The speed of the object is also a key factor affecting the impact force. At the moment of collision, the speed of the object determines the size of its kinetic energy, thereby affecting the intensity of the impact force. For a freely falling object, its falling height determines its speed when it hits the ground. The speed of the object when it hits the ground can be calculated through the free fall formula, and then the impact force can be estimated. For substances whose speed is difficult to calculate through the free fall formula, the impact force is calculated by collecting their average falling speed and combining with the mass.

[0069] Collect the edge shape of the shed substances, and evaluate the average sharpness of the shed substances based on the edge shape.

[0070] The sharpness is evaluated by measuring geometric parameters such as the edge radius (i.e., the radius of the curve at the tip of the material) and the wedge angle (i.e., the angle between two planes of the material). Smaller edge radius and wedge angle usually mean sharper. The average sharpness of the shed substances can also be obtained through equipment such as a universal testing machine or methods such as expert evaluation.

[0071] Collect the average viscosity of the shed substances, and combine the average impact force and the average sharpness to confirm the material interference degree of the shed substances on the intelligent robot.

[0072] In practical applications, the weight ratios of the average viscosity, average impact force, and average sharpness of the shedding substances are set respectively, and the substance interference degree is calculated according to the weight ratios. When the average viscosity, average impact force, and average sharpness are greater, the substance interference degree is greater. For example, when the average viscosity, average impact force, and average sharpness are 2 Pa·s, 5 N, and 3 respectively, and the weight ratios of the average viscosity, average impact force, and average sharpness are 20%, 40%, and 40% respectively, the substance interference degree is 2×20% + 5×40% + 3×40% = 3.6. When the average viscosity is greater, the plant shedding substances are more likely to stick to the intelligent robot, which may interfere with the movement or vision of the intelligent robot. When the average impact force is greater, the damage caused by hitting the intelligent robot will be greater. When the average sharpness is greater, it is more likely to scratch the intelligent robot and interfere with the movement of the intelligent robot.

[0073] The steps to extract non-plant information and obtain the non-plant influence degree according to the non-plant information are as follows: Collect the shielding substances that are not blocked by plants, and extract the service life of the shielding substances according to the non-plant information.

[0074] Collect the average dropping probability corresponding to the service life of the shielding substances, and obtain the average dropping loss of the shielding substances.

[0075] Collect the non-plant shielding distance, set the weight ratios of the non-plant shielding distance, average dropping probability, and average dropping loss respectively, and calculate the non-plant influence degree according to the weight ratios.

[0076] In practical applications, non-plant shielding is generally caused by buildings or supplies built by humans that block the intelligent robot. Since it is not a natural product, human construction has its service life. The greater the service life, the greater the probability of damage and dropping. For example, for the eaves of a house, as the use time increases, wall paint may fall off. The dropping probabilities of different substances are different, and the average dropping probability of the same type of substance is found according to the service life. Since different substances have different materials and masses, the losses caused by dropping are also different. For example, heavier substances cause more serious losses when they drop. When the non-plant shielding distance is longer, the average dropping probability is greater, and the average dropping loss is greater, the non-plant influence degree is greater. For example, when the non-plant shielding distance, average dropping probability, and average dropping loss are 200 meters, 10%, and 20 yuan respectively, and the weight ratios of the non-plant shielding distance, average dropping probability, and average dropping are 10%, 40%, and 50% respectively, the non-plant influence degree is 200×10% + 10%×40% + 20×50% = 30.04.

[0077] The steps to estimate the number of pedestrians and vehicles on the initial path according to the mobile weather information and obtain the movement convenience degree according to the number of pedestrians and vehicles are as follows: Obtain the historical data of pedestrians and vehicles on the initial path, and extract the average number of pedestrians and the average number of vehicles in different weather conditions based on the historical data of pedestrians and vehicles.

[0078] Find the corresponding average number of pedestrians and the average number of vehicles according to the mobile weather information, and record them as the estimated number of pedestrians and the estimated number of vehicles.

[0079] Overlay the estimated number of pedestrians and the estimated number of vehicles to obtain the estimated number of obstacles.

[0080] Extract the average number of pedestrians and the average number of vehicles on the initial path based on the historical data of pedestrians and vehicles, and overlay the average number of pedestrians and the average number of vehicles on the initial path to obtain the standard number of obstacles.

[0081] Calculate the quantity difference between the standard number of obstacles and the estimated number of obstacles, and combine it with the occlusion influence degree to obtain the movement convenience.

[0082] In practical applications, if the intelligent robot is affected by the weather but cannot reduce the interference through occlusion, then the occlusion only has an impact. Since the weather interferes with the movement of the robot, pedestrians and vehicles will also be affected by the weather, resulting in changes in their numbers. Pedestrians and vehicles are moving obstacles for the intelligent robot. The fewer the number, the lower the probability of collision. Therefore, the greater the quantity difference between the standard number of obstacles and the estimated number of obstacles, the more pedestrians and vehicles are reduced due to the weather, which is more conducive to the movement of the intelligent robot. Set the weight ratios of the quantity difference and the occlusion influence degree respectively, and calculate the movement convenience according to the weight ratios. For example, if the quantity difference and the occlusion influence degree are 100 and 50 respectively, and the weight ratios of the quantity difference and the occlusion influence degree are 60% and 40% respectively, then the movement convenience is 100×60% - 50×40% = 40. The greater the occlusion influence degree, the smaller the movement convenience because the occlusion causes certain interference to the intelligent robot.

[0083] The steps to obtain the movement convenience according to the number of obstacles in the initial path are as follows: Statistical the total path distance of the initial path and the number of fixed obstacles in the initial path.

[0084] Collect the number of times the intelligent robot adjusts its state during the movement on the initial path, and record it as the number of adjustments.

[0085] Combine the total path distance, the number of fixed obstacles, the number of adjustments and the occlusion influence degree to obtain the movement convenience.

[0086] In actual application, on a sunny day with suitable temperature, the intelligent robot is not affected by the weather. At this time, which path to choose needs to be judged according to the actual situation of the path. When the total distance of the initial path is larger, it means that the intelligent robot needs to travel more distance, so the mobility convenience is lower. And when the number of fixed obstacles is more, the intelligent robot needs to spend more energy to avoid obstacles, and at the same time, it will increase the probability of collision, so the mobility convenience is lower. When the robot adjusts its moving state, such as accelerating or adjusting the moving direction, the more such adjustment times, the less convenient it is for the intelligent robot to move, and more operations are required, so the mobility convenience is lower. Similarly, when the obstacle does not have an obstructive effect, the obstacle instead affects the movement of the intelligent robot. The weight ratios of the total path distance, the number of fixed obstacles, the number of adjustments, and the obstruction influence degree are set respectively, and the mobility convenience is calculated according to the weight ratios. For example, if the total path distance, the number of fixed obstacles, the number of adjustments, and the obstruction influence degree are 500 meters, 10, 5 times, and 50 respectively, and the weight ratios of the total path distance, the number of fixed obstacles, the number of adjustments, and the obstruction influence degree are 10%, 20%, 50%, and 20% respectively, the mobility convenience is -500×10% - 10×20% - 5×50% - 50×20% = -64.5.

[0087] The above are all the preferred embodiments of this application, and the protection scope of this application is not limited by this. Therefore, all equivalent changes made according to the structure, shape, and principle of this application should be covered within the protection scope of this application.

Claims

1. An intelligent robot path planning system based on the Internet of Things, characterized in that: include: The initial path module obtains the starting position and the end position of the intelligent robot, and generates a path based on the starting position and the end position and records it as the initial path; The weather information module obtains the moving time of the intelligent robot and collects the weather information corresponding to the moving time as moving weather information; The path convenience module evaluates the convenience of the initial path according to the mobile weather information and obtains the path convenience of the initial path; The mobile convenience module collects the information of the obstructions in the initial path, combines it with the mobile weather information to analyze the convenience of the robot's movement and records it as the mobile convenience; The path planning module combines the path convenience and movement convenience to calculate the fitness of the initial path, selects the initial path with the highest fitness as the target path, and the intelligent robot moves according to the target path.

2. The intelligent robot path planning system based on the Internet of Things according to claim 1 is characterized in that: The step of evaluating the convenience of the initial path according to the mobile weather information to obtain the path convenience of the initial path is specifically as follows: Extracting road surface information of the initial path, wherein the road surface information includes road surface flatness, road surface slope, and road surface anti-skid degree; Evaluate the convenience of moving on the initial path based on the road surface information, and record it as the basic convenience of the initial path; According to the mobile weather information, the impact of weather on the initial path is evaluated to obtain the impact convenience; Subtract the influencing convenience from the basic convenience to obtain the path convenience of the initial path.

3. The intelligent robot path planning system based on the Internet of Things according to claim 2 is characterized in that: The step of evaluating the degree of influence of weather on the initial path according to the mobile weather information to obtain the influence on convenience is specifically as follows: Determine whether the physical properties of the road surface are affected by the weather based on the road surface information. If the physical properties of the road surface are affected by the weather, extract the weather influencing factors that affect the physical properties of the road surface. Collect the required standard values ​​of weather influencing factors for roads, and extract the real-time values ​​of weather influencing factors based on mobile weather information; The difference between the calculated demand standard value and the real-time value is recorded as the factor difference, and the factor difference of all weather influencing factors is superimposed as the influencing convenience; If the physical properties of the road surface are not affected by weather, historical accident information of the initial path is obtained; The historical accident probability of different weather conditions is counted to form a weather-accident probability table, and the corresponding accident probability is obtained according to the mobile weather information and recorded as the real-time probability; The minimum value of the historical accident probability of the collected initial path is recorded as the minimum probability, and the difference between the real-time probability and the minimum probability is calculated as the impact convenience.

4. The intelligent robot path planning system based on the Internet of Things according to claim 1 is characterized in that: The step of collecting the information of the obstructions in the initial path, analyzing the convenience of the robot's movement in combination with the mobile weather information and recording it as the convenience of movement is specifically as follows: Determine whether the intelligent robot is disturbed by weather based on mobile weather information. If so, determine whether to reduce the interference by shielding. If interference is reduced by blocking, the information of the blocking objects in the initial path is collected and combined with the mobile weather information to evaluate the mobility convenience; If interference is not reduced by blocking, the number of pedestrians and vehicles on the initial path is estimated based on the mobile weather information, and the convenience of movement is obtained based on the number of pedestrians and vehicles; If the intelligent robot is not affected by the weather, the number of obstacles in the initial path is counted, and the ease of movement is obtained based on the number of obstacles.

5. The intelligent robot path planning system based on the Internet of Things according to claim 4 is characterized in that: If interference is reduced by blocking, the steps of collecting information about blocking objects in the initial path and evaluating the convenience of movement in combination with the mobile weather information are specifically as follows: Collect the information of the occluders in the initial path, and extract the occlusion distance and occlusion area according to the occluder information; The basic occlusion degree of the initial path is calculated based on the occlusion distance and occlusion area; According to the occlusion information, the occlusions are divided into plant occlusions and non-plant occlusions, the plant information is extracted, and the plant influence is obtained according to the plant information; Extract non-plant information, obtain non-plant influence according to the non-plant information, and superimpose plant influence to obtain occlusion influence; The ease of movement of the intelligent robot on the initial path is calculated by subtracting the occlusion impact from the basic occlusion.

6. The intelligent robot path planning system based on the Internet of Things according to claim 5 is characterized in that: The step of extracting plant information and obtaining the plant influence according to the plant information is specifically as follows: According to the plant information, the average shedding rate of the plants during the moving time was calculated as the basic shedding rate; The average value of the shedding rate increase of plants under different weather conditions is calculated to form a weather-shedding increase rate table, and the corresponding shedding increase rate is obtained by searching according to the mobile weather information; The basal shedding rate and the shedding increase rate were superimposed to obtain the plant shedding rate of the plant; Extract the shedding substances of the plants according to the plant information, obtain the material information of the shedding substances, and analyze the interference degree of the shedding substances on the intelligent robot according to the material information, which is recorded as the material interference degree; The plant blocking distance is counted, and the degree of influence of plants on the intelligent robot is comprehensively obtained by combining the plant shedding rate and material interference, which is recorded as the plant influence degree.

7. The intelligent robot path planning system based on the Internet of Things according to claim 6 is characterized in that: The step of obtaining material information of the detached material and analyzing the material information to obtain the interference degree of the detached material on the intelligent robot as the material interference degree is specifically as follows: The average height, average weight and average falling speed of the falling material are collected, and the average impact force of the falling material is calculated based on the average height, average weight and average falling speed; The edge shape of the detached material is collected, and the average sharpness of the detached material is obtained based on the edge shape evaluation; The average viscosity of the shed material is collected, combined with the average impact force and average sharpness, to confirm the material interference of the shed material on the intelligent robot.

8. The intelligent robot path planning system based on the Internet of Things according to claim 5 is characterized in that: The step of extracting non-plant information and obtaining the non-plant influence according to the non-plant information is specifically as follows: Collect non-plant-blocked obstructing materials, and extract the service life of the obstructing materials based on the non-plant information; Collect the average drop probability of the shielding material corresponding to the service life, and obtain the average drop loss of the shielding material; The non-plant occlusion distance is collected, and the weight ratios of the non-plant occlusion distance, average drop probability, and average drop loss are set respectively. The non-plant influence is calculated according to the weight ratio.

9. The intelligent robot path planning system based on the Internet of Things according to claim 5, characterized in that: The step of estimating the number of pedestrians and vehicles on the initial path according to the mobile weather information and obtaining the mobility convenience according to the number of pedestrians and vehicles is specifically as follows: Obtain the historical data of pedestrians and vehicles on the initial path, and extract the average number of pedestrians and the average number of vehicles under different weather conditions based on the historical data of pedestrians and vehicles; The corresponding average number of pedestrians and average number of vehicles are found according to the mobile weather information and recorded as the estimated number of pedestrians and the estimated number of vehicles; The estimated number of pedestrians and vehicles are superimposed to obtain the estimated number of obstacles. The average number of pedestrians and the average number of vehicles on the initial path are extracted based on the historical data of pedestrians and vehicles, and the average number of pedestrians and the average number of vehicles on the initial path are superimposed to obtain the number of standard obstacles; The difference between the standard number of obstacles and the estimated number of obstacles is calculated, and the convenience of movement is obtained by combining the occlusion impact.

10. The intelligent robot path planning system based on the Internet of Things according to claim 5, characterized in that: The step of counting the number of obstacles in the initial path and obtaining the moving convenience according to the number of obstacles is specifically as follows: Count the total path distance of the initial path and the number of fixed obstacles in the initial path; The number of times the intelligent robot moves and adjusts its state in the initial path is recorded as the number of adjustments; The ease of movement is obtained by combining the total path distance, the number of fixed obstacles, the number of adjustments and the impact of occlusion.

Images