Self-adaptive cleaning path planning system and method for environmental sanitation equipment

Abstract

The invention relates to a self-adaptive cleaning path planning system and method for environmental sanitation equipment, and relates to the technical field of path control, and the system comprises an environment calculation module which is used for carrying out the environment dynamic modeling of a to-be-cleaned region, and generating an environment state probability; the cleaning priority module is used for determining the cleaning priority of each area according to the environment state probability; the first planning module is used for determining a planning path for the environmental sanitation equipment according to the cleaning priority of each area; the adjustment amount module is used for determining the path adjustment amount of the new planning path relative to the original planning path in response to the predicted new planning path; the path adjustment module is used for performing path adjustment on the environmental sanitation equipment according to the path adjustment amount, so that the environmental sanitation equipment moves according to a newly planned path; and the second planning module is used for calculating a cleaning effect score of the environmental sanitation equipment and adjusting the new planning path according to the cleaning effect score to obtain a target path. The system can improve the accuracy of path planning of the environmental sanitation equipment.

Description

Technical Field

[0001] The present invention relates to the field of path control technology, and in particular to an adaptive cleaning path planning system, method, electronic device and non-transient computer-readable storage medium for sanitation equipment. Background Art

[0002] In the current cleaning path planning methods of sanitation equipment, methods based on preset rules or traditional path optimization algorithms are usually adopted. Common methods include coverage path planning (CPP) based on grid maps, A* algorithm, Dijkstra algorithm and ant colony algorithm, etc. These methods can plan a more optimized cleaning route in a known environment.

[0003] However, the preset rules are difficult to adapt to the dynamically changing environment, resulting in limited cleaning effects; traditional path optimization algorithms often rely on static maps and respond slowly to sudden obstacles or the randomness of garbage distribution. Summary of the invention

[0004] In response to the technical problems existing in the prior art, the present invention provides an adaptive cleaning path planning system, method, electronic device and non-transitory computer-readable storage medium for sanitation equipment, which can improve the accuracy and efficiency of cleaning path planning of sanitation equipment.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: The present invention provides an adaptive cleaning path planning system for sanitation equipment, the system comprising: The environmental calculation module is used to perform dynamic environmental modeling on the area to be cleaned and generate environmental state probabilities.

[0006] The cleaning priority module is used to determine the cleaning priority of each area according to the environmental state probability.

[0007] The first planning module is used to determine a planned path for the sanitation equipment according to the cleaning priority of each area.

[0008] The adjustment module is used to determine the path adjustment amount of the new planned path relative to the original planned path in response to predicting the new planned path.

[0009] The path adjustment module is used to adjust the path of the sanitation equipment according to the path adjustment amount so that the sanitation equipment moves along the new planned path.

[0010] The second planning module is used to calculate the cleaning effect score of the sanitation equipment and adjust the new planned path according to the cleaning effect score to obtain the target path.

[0011] Optionally, the environment calculation module is specifically used for: A garbage distribution density function is constructed to represent the amount of garbage at a preset location at a preset time.

[0012] An obstacle occurrence probability function is constructed to represent the probability of an obstacle occurring at the preset position at the preset time.

[0013] A congestion degree function is constructed to represent the traffic congestion degree of the preset location at the preset time.

[0014] An environmental state probability is generated according to the garbage distribution density function, the obstacle occurrence probability function and the congestion degree function.

[0015] Optionally, the garbage distribution density function is constructed in the following manner: The garbage distribution image is obtained by using the visual sensor deployed on the sanitation equipment.

[0016] The garbage distribution image is processed using a convolutional neural network to perform garbage density classification and obtain a classification result.

[0017] A spatiotemporal distribution prediction model is established in combination with the classification results and historical cleaning data, and the garbage distribution density function is constructed based on the spatiotemporal distribution prediction model.

[0018] Optionally, the environmental state probability is expressed as:

[0019] in, It's location The probability of the environment state at time t is: is the garbage distribution density function, is the obstacle appearance probability function, is the congestion level function, They are the first weight, the second weight and the third weight respectively.

[0020] Optionally, the cleaning priority module is specifically used for: According to the environmental state probabilities of the respective areas, an average environmental state probability is determined.

[0021] A time decay factor for representing the influence of the uncleaned time period of each area on the cleaning priority is obtained.

[0022] A pedestrian flow score for indicating the size of pedestrian flow in each of the areas is obtained.

[0023] The cleaning priority of each area is determined according to the average value of the environmental state probability, as well as the time decay factor and the human flow score of each area.

[0024] Optionally, the cleaning priority is expressed as:

[0025] in, is the cleaning priority of area i at time t, is the area of ​​region i, is the time since area i was last cleaned, is the traffic score of area i, They are the fourth weight, the fifth weight and the sixth weight, is the time decay factor.

[0026] Optionally, the first planning module is specifically used to: The weighted sum of the leave priority of each area and the coverage degree of the path is calculated to obtain the cleaning benefit.

[0027] An energy consumption function is constructed to represent the energy consumed by the sanitation equipment during movement from one area to another area.

[0028] A time consumption function is constructed to represent the time consumed in the process of moving the sanitation equipment from one area to another area.

[0029] A planned path is determined for the sanitation equipment according to the cleaning benefit, the energy consumption function and the time consumption function.

[0030] Optionally, the adjustment amount module is specifically used for: Gets the adjustment factor that represents the magnitude of the control path adjustment.

[0031] A second time attenuation factor for controlling the influence of time on path adjustment is obtained.

[0032] Gets the time interval from the current time to the last path adjustment.

[0033] The difference between the new planned path and the original planned path is processed according to the adjustment coefficient, the second time attenuation factor and the time interval to determine the path adjustment amount.

[0034] Optionally, the second planning module is specifically used to: Obtain the resource consumption of the sanitation equipment at the preset time.

[0035] A resource consumption function is constructed according to the resource consumption of the sanitation equipment at the preset time.

[0036] The cleaning effect score of the sanitation equipment is calculated based on the resource consumption function, the environmental state probability and the cleaning priority of each area.

[0037] The present invention also provides an adaptive cleaning path planning method for sanitation equipment, the method comprising: The environment dynamics modeling is performed on the area to be cleaned to generate the environmental state probability.

[0038] The cleaning priority of each of the areas is determined according to the environmental state probability.

[0039] Determine the planned route for the sanitation equipment based on the cleaning priority of each of the areas described.

[0040] In response to predicting a new planned path, a path adjustment amount of the new planned path relative to the original planned path is determined.

[0041] The path of the sanitation equipment is adjusted according to the path adjustment amount so that the sanitation equipment moves along the new planned path.

[0042] The cleaning effect score of the sanitation equipment is calculated, and the new planned path is adjusted according to the cleaning effect score to obtain the target path.

[0043] In addition, to achieve the above objectives, the present invention also proposes an electronic device, comprising: a memory for storing computer software programs; a processor for reading and executing the computer software programs, thereby implementing the adaptive cleaning path planning method for sanitation equipment as described above.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also proposes a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, the adaptive cleaning path planning method for sanitation equipment as described above is implemented.

[0045] The beneficial effects of the present invention are: (1) The present invention uses dynamic environmental modeling to perceive environmental characteristics such as garbage distribution density, obstacle occurrence probability and congestion level in real time, so that sanitation equipment can respond to environmental changes in a timely manner and avoid wasting time in high-congestion areas or areas with dense obstacles, thereby improving cleaning efficiency.

[0046] (2) The present invention constructs a multi-dimensional task priority evaluation function, which comprehensively considers factors such as the garbage distribution in the area, the time interval between the last cleaning, and the flow of people, and gives priority to cleaning high-priority areas to ensure that limited cleaning resources are used most effectively.

[0047] (3) The present invention comprehensively evaluates factors such as cleaning degree, cleaning requirements and resource consumption, monitors the completion of cleaning tasks in real time, promptly discovers problems such as insufficient cleaning or waste of resources, and adjusts the cleaning strategy based on the evaluation results to ensure that the cleaning quality meets the expected standards.

[0048] In summary, the present invention realizes the adaptive planning and optimization of the cleaning path of sanitation equipment through a series of innovative methods and mechanisms, which has significant beneficial effects in improving cleaning efficiency, optimizing resource utilization, improving cleaning quality, enhancing system flexibility and adaptability, reducing manual intervention costs, and improving the level of urban environmental management. It has important practical significance for promoting the intelligent development of the sanitation industry and improving the quality of the urban environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A scene diagram of the adaptive cleaning path planning method for sanitation equipment provided by the present invention; Figure 2 A schematic diagram of the structure of the adaptive cleaning path planning system for sanitation equipment provided by the present invention; Figure 3 A flow chart of the adaptive cleaning path planning method for sanitation equipment provided by the present invention; Figure 4 A schematic diagram of the hardware structure of an electronic device provided by the present invention; Figure 5 A schematic diagram of the hardware structure of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0050] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0051] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0052] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0053] See also Figure 1 , Figure 1 This is a scene diagram of the adaptive cleaning path planning method for sanitation equipment provided by the present invention. Figure 1 As shown, the terminal and the server are connected via a network, such as a wired or wireless network connection. The terminal may include but is not limited to portable terminals such as mobile phones and tablets installed with various network platform applications, as well as fixed terminals such as computers, query machines, and advertising machines. The server provides users with various business services, including service push servers, user recommendation servers, etc.

[0054] It should be noted that Figure 1 The scenario diagram of the adaptive cleaning path planning method for sanitation equipment shown is only an example. The terminal, server and application scenario described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not generate limitations on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0055] Among them, the terminal can be used for: The environment dynamics modeling is performed on the area to be cleaned to generate the environmental state probability.

[0056] The cleaning priority of each of the areas is determined according to the environmental state probability.

[0057] Determine the planned route for the sanitation equipment based on the cleaning priority of each of the areas described.

[0058] In response to predicting a new planned path, a path adjustment amount of the new planned path relative to the original planned path is determined.

[0059] The path of the sanitation equipment is adjusted according to the path adjustment amount so that the sanitation equipment moves along the new planned path.

[0060] The cleaning effect score of the sanitation equipment is calculated, and the new planned path is adjusted according to the cleaning effect score to obtain the target path.

[0061] See also Figure 2 , Figure 2 A schematic diagram of the structure of the adaptive cleaning path planning system for sanitation equipment provided by the present invention.

[0062] like Figure 2 As shown, the adaptive cleaning path planning system for sanitation equipment proposed in an embodiment of the present invention includes: The environment calculation module 201 is used to perform dynamic environment modeling on the area to be cleaned and generate an environment state probability.

[0063] The cleaning priority module 202 is used to determine the cleaning priority of each of the areas according to the environmental state probability.

[0064] The first planning module 203 is used to determine a planned path for the sanitation equipment according to the cleaning priority of each area.

[0065] The adjustment module 204 is configured to determine a path adjustment amount of the new planned path relative to the original planned path in response to predicting the new planned path.

[0066] The path adjustment module 205 is used to adjust the path of the sanitation equipment according to the path adjustment amount, so that the sanitation equipment moves along the new planned path.

[0067] The second planning module 206 is used to calculate the cleaning effect score of the sanitation equipment and adjust the new planned path according to the cleaning effect score to obtain the target path.

[0068] In some embodiments, the environment calculation module 201 is specifically used for: A garbage distribution density function is constructed to represent the amount of garbage at a preset location at a preset time.

[0069] An obstacle occurrence probability function is constructed to represent the probability of an obstacle occurring at the preset position at the preset time.

[0070] A congestion degree function is constructed to represent the traffic congestion degree of the preset location at the preset time.

[0071] An environmental state probability is generated according to the garbage distribution density function, the obstacle occurrence probability function and the congestion degree function.

[0072] In some embodiments, the garbage distribution density function is constructed in the following manner: The garbage distribution image is obtained by using the visual sensor deployed on the sanitation equipment.

[0073] The garbage distribution image is processed using a convolutional neural network to perform garbage density classification and obtain a classification result.

[0074] A spatiotemporal distribution prediction model is established in combination with the classification results and historical cleaning data, and the garbage distribution density function is constructed based on the spatiotemporal distribution prediction model.

[0075] In some embodiments, the environmental state probability is expressed as:

[0076] in, It's location The probability of the environment state at time t is: is the garbage distribution density function, is the obstacle appearance probability function, is the congestion level function, They are the first weight, the second weight and the third weight respectively.

[0077] In the specific implementation, the garbage distribution density function Indicates the preset position at the preset time t The garbage distribution density of the area. This function reflects the amount of garbage in a preset spatial location at a specific time. The higher the garbage density, the more urgent it is to clean the area.

[0078] Specifically, the distribution of garbage can be detected in real time through sensors installed on sanitation equipment (such as cameras, lidar, etc.). Combined with historical cleaning records, the current garbage distribution can be predicted. The impact of factors such as weather and human flow on garbage distribution can be considered. For example, strong winds may make garbage distribution more dispersed.

[0079] Obstacle appearance probability function Indicates the preset position at the preset time t The probability of obstacles. This is used to assess the obstacles that sanitation equipment may encounter during the cleaning process (such as pedestrians, vehicles, temporary obstacles, etc.). The higher the probability of obstacles, the more careful you need to be when planning the cleaning path to avoid collisions.

[0080] Specifically, the presence of obstacles can be detected in real time through sensors such as laser radar and cameras. Combined with high-precision maps, possible obstacle areas (such as construction areas, fixed obstacles, etc.) can be marked in advance. Real-time traffic information can be obtained through the traffic monitoring system to predict the probability of occurrence of dynamic obstacles (such as vehicles and pedestrians).

[0081] Congestion function Indicates the preset position at the preset time t The congestion level reflects the traffic congestion that sanitation equipment may encounter during the cleaning process. The higher the congestion level, the more detours need to be considered when planning the cleaning path to reduce cleaning time.

[0082] Specifically, the traffic monitoring system can be used to obtain real-time traffic flow data and assess the degree of congestion. Combined with historical traffic data, the current congestion situation can be predicted. The vehicle's own sensors (such as radar and cameras) can be used to perceive the surrounding traffic conditions in real time.

[0083] Weight coefficient They are the weight coefficients of garbage distribution density, obstacle occurrence probability and congestion degree, and their sum is equal to 1. They are used to adjust the three factors to the probability of environmental status. The contribution size of the path planning can be optimized by adjusting the weights for different application scenarios and requirements.

[0084] If the primary goal of the cleaning task is to remove the garbage as quickly as possible, then you can increase If there are many pedestrians and vehicles in the cleaning area and special attention needs to be paid to safety, you can increase If the cleaning task needs to be completed within a limited time and traffic congestion has a greater impact on cleaning efficiency, then you can increase The weight of .

[0085] Through this formula, the probability of the environmental state of each position at each moment can be dynamically calculated This probability value can be used for subsequent cleaning task priority evaluation and path planning, combined with And other factors (such as area size, last cleaning time, etc.), assess the cleaning priority of each area. The optimal cleaning path is planned based on the distribution of garbage, avoiding high congestion areas and areas with high probability of obstacles, and giving priority to cleaning areas with high garbage distribution density.

[0086] The present invention is updated in real time , and , which can adapt to the dynamic changes of the environment. By adjusting the weight coefficient, the path planning can be optimized according to different application scenarios and needs. The three important factors of garbage distribution, obstacles and congestion are comprehensively considered to make the path planning more comprehensive and reasonable.

[0087] In some embodiments, the cleaning priority module is specifically used to: According to the environmental state probabilities of the respective areas, an average environmental state probability is determined.

[0088] A time decay factor for representing the influence of the uncleaned time period of each area on the cleaning priority is obtained.

[0089] A pedestrian flow score for indicating the size of pedestrian flow in each of the areas is obtained.

[0090] The cleaning priority of each area is determined according to the average value of the environmental state probability, as well as the time decay factor and the human flow score of each area.

[0091] In some embodiments, the cleaning priorities are expressed as:

[0092] in, is the cleaning priority of area i at time t, is the area of ​​region i, is the time since area i was last cleaned, is the traffic score of area i, They are the fourth weight, the fifth weight and the sixth weight, is the time decay factor.

[0093] In the specific implementation, this formula is used to evaluate the cleaning priority of area i at time t , taking into account multiple factors to determine which areas need to be cleaned first.

[0094] Average probability of environmental state , this part calculates the probability of the environmental state of all locations in area i The average value of is the area of ​​region i. By calculating the average environmental state probability in a region, the overall cleaning demand of the region can be quantified. If the average environmental state probability of a region is high, it means that the garbage distribution density, obstacle probability or congestion level in the region is high and needs to be cleaned first. First traverse all locations in region i , calculate the probability of the environmental state at each location Then add up the probabilities of the environmental states at all locations and divide by the area .

[0095] Time decay factor , which represents the time since the last cleaning of area i The impact on the cleaning priority, that is, the impact of the length of time that area i is not cleaned on the cleaning priority, where is the first time decay factor. As time goes by, the cleaning demand of the area will gradually increase. First time decay factor Used to control how much time affects cleaning priority. Smaller, time has a greater impact on cleaning priority; if The larger, the less impact time has on cleaning priority. is the time since area i was last cleaned (in hours, days, etc.). is an exponential decay function that decays over time. With the increase of , its value decreases gradually.

[0096] Traffic score Indicates the traffic score of area i, which reflects the traffic volume of the area. Areas with high traffic volume usually generate more garbage and therefore require higher cleaning priority. The traffic score can be determined based on real-time data (such as camera monitoring) or historical data (such as statistical traffic volume). The traffic volume can be monitored in real time by sensors installed in the area (such as cameras, infrared sensors, etc.). It is also possible to count the traffic volume of the area based on historical data and give a score value.

[0097] They are the weight coefficients of the average probability of environmental status, the first time attenuation factor and the flow score, and the sum of the three is equal to 1. Used to adjust the cleaning priority of the three factors The contribution size of the cleaning priority can be optimized by adjusting the weights for different application scenarios and requirements.

[0098] Understandably, if the primary goal of the cleaning task is to remove the garbage as quickly as possible, then If the cleaning task needs to consider the time interval between the last cleaning, you can increase If cleaning tasks need to prioritize high traffic areas, you can increase The weight of .

[0099] Through this formula, the cleaning priority of each area at each moment can be dynamically calculated. . According to cleaning priority , prioritize the areas with high cleaning priority to ensure that limited cleaning resources are used most effectively. Areas with high cleaning priority can be allocated more cleaning equipment or manpower to improve cleaning efficiency.

[0100] The present invention comprehensively considers three important factors: environmental status, time interval and human flow, making the evaluation of cleaning priority more comprehensive and reasonable. and traffic score , can adapt to the dynamic changes of the environment. By adjusting the weight coefficient and the first time attenuation factor , the evaluation of cleaning priorities can be optimized according to different application scenarios and needs.

[0101] In some embodiments, the first planning module is specifically used to: Calculate the weighted sum of the leave priority of each area and the coverage degree of the path to obtain the cleaning benefit; An energy consumption function is constructed to represent the energy consumed by the sanitation equipment during movement from one area to another area.

[0102] A time consumption function is constructed to represent the time consumed in the process of moving the sanitation equipment from one area to another area.

[0103] A planned path is determined for the sanitation equipment according to the cleaning benefit, the energy consumption function and the time consumption function.

[0104] In some embodiments, the planned path can be expressed as:

[0105] in, is the planned path, is the coverage length of the path in region i, is the energy consumption function from region i to region j, is the time consumption function from region i to j, They are the seventh weight, the eighth weight and the ninth weight respectively.

[0106] In specific implementation, this formula is used to evaluate and optimize the cleaning path of sanitation equipment , by comprehensively considering factors such as cleaning priority, energy consumption and time consumption, the optimal cleaning path is designed.

[0107] The product of cleaning priority and coverage length , this part calculates the cleaning priority of the path in each area i With coverage length The weighted sum of . Cleaning priority reflects the cleaning requirements of area i, while the coverage length It represents the actual cleaning range of the path in the area. By multiplying the two, the cleaning benefit of the path in each area can be quantified. It is used to adjust the importance of cleaning benefits in the entire path optimization. When calculating, first traverse all the areas i that the path passes through, and then calculate the cleaning priority of each area i With coverage length The products of all regions are added together to get the total cleaning benefit.

[0108] Energy consumption function , this part calculates the energy consumption function of the path from area i to area j The weighted sum of . Energy consumption function It reflects the energy consumed by sanitation equipment in the process of moving from area i to area j. By minimizing energy consumption, the energy efficiency of cleaning tasks can be improved and operating costs can be reduced. It is used to adjust the importance of energy consumption in the entire path optimization. When calculating, first traverse all adjacent area pairs in the path For each pair of regions , calculate its energy consumption function The energy consumption of all area pairs is accumulated to obtain the total energy consumption.

[0109] Time consumption function This part calculates the time consumption function of the path from area i to area j The weighted sum of . Time consumption function It reflects the time consumed by sanitation equipment in the process of moving from area i to area j. By minimizing the time consumption, the efficiency of the cleaning task can be improved, ensuring that more cleaning work can be completed in a limited time. It is used to adjust the importance of time consumption in the entire path optimization. When calculating, first traverse all adjacent area pairs in the path For each pair of regions , and then calculate its time consumption function Finally, the time consumption of all area pairs is accumulated to get the total time consumption.

[0110] They are the weight coefficients of cleaning efficiency, energy consumption and time consumption, and they all satisfy the sum of the three factors and are 1. They are used to adjust the three factors to the path optimization objective function The contribution size of the path planning can be optimized by adjusting the weights for different application scenarios and requirements.

[0111] If the primary goal of the cleaning task is to maximize cleaning efficiency, then you can increase If the cleaning task needs to consider energy efficiency, then you can increase If the cleaning task needs to be completed within a limited time, then you can increase The weight of .

[0112] Through this formula, the cleaning path of sanitation equipment can be dynamically evaluated and optimized. The goal of path optimization is to maximize , that is, to minimize energy and time consumption while meeting cleaning benefits. The specific steps are as follows: Generate multiple possible cleaning paths. Use formulas to evaluate the pros and cons of each path. Select The path with the largest value is taken as the optimal path.

[0113] Through the above methods, the present invention can comprehensively consider the three important factors of cleaning efficiency, energy consumption and time consumption, making the path planning more comprehensive and reasonable. By updating the cleaning priority, energy consumption function and time consumption function in real time, it can adapt to the dynamic changes of the environment. By adjusting each weight, the path planning can be optimized according to different application scenarios and requirements.

[0114] In some embodiments, the adjustment amount module is specifically used to: Gets the adjustment factor that represents the magnitude of the control path adjustment.

[0115] A second time attenuation factor for controlling the influence of time on path adjustment is obtained.

[0116] Gets the time interval from the current time to the last path adjustment.

[0117] The difference between the new planned path and the original planned path is processed according to the adjustment coefficient, the second time attenuation factor and the time interval to determine the path adjustment amount.

[0118] In some embodiments, the path adjustment amount may be expressed as:

[0119] in, is the path adjustment at time t, It is a new planning path. is the original planned path. is the adjustment factor, is the second time decay factor, It is the time interval from the current time to the last time the path was adjusted.

[0120] In specific implementation, this formula is used to describe the path adjustment mechanism of sanitation equipment in a dynamic environment, and the path adjustment amount is determined according to the difference in the optimization objective function values ​​between the new and old paths and the time interval.

[0121] Path Adjustment Represents the amount of adjustment to the cleaning path at time t. This adjustment determines the degree of change of the path in a dynamic environment. If the adjustment is large, it means that the path needs to be changed significantly; if the adjustment is small, it means that the path is relatively stable.

[0122] The difference in optimization objective function value between the new planned path and the original planned path , this part calculates the new planning path and the original planned path The optimization objective function value difference.

[0123] Optimizing the objective function Used to evaluate the quality of the path. If the optimization objective function value of the new planned path Greater than the optimization objective function value of the original planned path , indicating that the new path is better and needs to be adjusted.

[0124] When calculating, you can use the path optimization objective function mentioned above to calculate the values ​​of the new path and the original path respectively. Then calculate the difference between the two .

[0125] Adjustment factor Used to control the amplitude of path adjustment and determine the sensitivity of path adjustment. If the value is larger, the path adjustment will be more sensitive, that is, it will react more strongly to the difference between the new and old paths; The smaller the value, the smoother the path adjustment, that is, the weaker the reaction to the difference between the new and old paths. It is a positive number, and the value range can be adjusted according to actual needs.

[0126] This part is an exponential decay function, which represents the time interval Impact on path adjustment. Used to control the timeliness of path adjustment. If the time interval If the time interval is large, it means that a long time has passed since the last adjustment, and the path adjustment amplitude will decrease. A smaller value indicates that the time since the last adjustment is shorter and the path adjustment will be larger. It is the time interval between the current time t and the last adjustment time. It is the second time attenuation factor, which is used to control the influence of time on path adjustment.

[0127] Through this formula, the cleaning path of sanitation equipment can be dynamically adjusted to adapt to environmental changes. The specific steps are as follows: Use the optimization objective function to evaluate the new planned path and the original planned path . Calculate the path adjustment amount according to the formula Finally, according to the adjustment amount Update cleaning path.

[0128] The present invention can dynamically adjust the cleaning path to adapt to environmental changes by evaluating the difference in the optimization objective function values ​​of the new and old paths in real time. , can control the timeliness of path adjustment and avoid instability caused by frequent adjustments. and the second time decay factor , the path adjustment mechanism can be optimized according to different application scenarios and requirements.

[0129] In some embodiments, the second planning module is specifically used to: Obtain the resource consumption of the sanitation equipment at the preset time.

[0130] A resource consumption function is constructed according to the resource consumption of the sanitation equipment at the preset time.

[0131] The cleaning effect score of the sanitation equipment is calculated based on the resource consumption function, the environmental state probability and the cleaning priority of each area.

[0132] In some embodiments, the cleaning effectiveness score may be expressed as:

[0133] in, is the cleaning effect rating, is the resource consumption function, They are the tenth weight, eleventh weight and twelfth weight respectively.

[0134] In specific implementation, this formula is used to evaluate the cleaning effect of sanitation equipment at time t. It comprehensively considers factors such as environmental state probability, cleaning priority, and resource consumption to quantify the completion of the cleaning task.

[0135] The complement of the environmental state probabilities , this part calculates the probability of the environmental state at all locations The complement of ). The probability of the environmental state Reflects the location The cleaning demand at time t. Its complement It reflects the location Adding up the cleanliness levels of all locations gives you the overall cleaning effect.

[0136] When calculating, first traverse all positions , calculate the probability of the environmental state at each location . Then calculate the cleanliness level of each location ( ). Then add up the cleanliness levels of all locations.

[0137] Sum of cleaning priorities The calculation is for the cleaning priority of all areas The sum of . Cleaning priority It reflects the cleaning demand of area i at time t. By adding up the cleaning priorities of all areas, the overall cleaning demand can be obtained. When calculating, first traverse all areas i and calculate the cleaning priority of each area . Add the cleaning priorities of all areas together.

[0138] Resource consumption function , which represents the resource consumption at time t, such as energy consumption, time consumption, etc. Resource consumption function It reflects the resource consumption required to complete the cleaning task. By minimizing resource consumption, the efficiency of the cleaning task can be improved. When calculating, design the resource consumption function according to the actual resource consumption. .

[0139] They are the weight coefficients of cleanliness, cleaning requirements and resource consumption, and the sum of the three is 1. Used to adjust the three factors to score the cleaning effect The contribution of . Different application scenarios and requirements can optimize the evaluation of cleaning effect by adjusting the weight. If the primary goal of the cleaning task is to improve the degree of cleanliness, then If the cleaning task needs to consider the cleaning requirements, then you can increase If the cleaning task needs to be completed with limited resources, then you can increase The weight of .

[0140] In some embodiments, the cleaning effect score may be calculated first, then the path optimization requirements may be evaluated, then the new planned path may be adjusted, the path adjustment amount may be calculated, then the target path may be updated, and finally the target path may be executed.

[0141] Through the above methods, the present invention can dynamically evaluate the cleaning effect of sanitation equipment. The cleaning effect score can be used to monitor the completion of cleaning tasks and optimize cleaning strategies. The present invention comprehensively considers three important factors: cleaning degree, cleaning requirements and resource consumption, making the evaluation of cleaning effect more comprehensive and reasonable. By updating the environmental state probability, cleaning priority and resource consumption function in real time, it can adapt to the dynamic changes of the environment.

[0142] See also Figure 3 , a flow chart of the adaptive cleaning path planning method of sanitation equipment of the present invention is provided, comprising the following steps: Step 301: Perform environmental dynamic modeling on the area to be cleaned and generate environmental state probability; Step 302: Determine the cleaning priority of each area according to the environmental state probability; Step 303: Determine a planned path for the sanitation equipment according to the cleaning priority of each area; Step 304: in response to predicting the new planned path, determining a path adjustment amount of the new planned path relative to the original planned path; Step 305: adjusting the path of the sanitation equipment according to the path adjustment amount, so that the sanitation equipment moves along the new planned path; Step 306: Calculate the cleaning effect score of the sanitation equipment, and adjust the new planned path according to the cleaning effect score to obtain the target path.

[0143] See also Figure 4 , Figure 4 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented: Perform environmental dynamic modeling on the area to be cleaned and generate environmental state probabilities; Determining the cleaning priority of each of the areas according to the environmental state probability; Determine the planned routes for sanitation equipment according to the cleaning priorities of each of the areas; In response to predicting a new planned path, a path adjustment amount of the new planned path relative to the original planned path is determined.

[0144] The path of the sanitation equipment is adjusted according to the path adjustment amount so that the sanitation equipment moves along the new planned path.

[0145] The cleaning effect score of the sanitation equipment is calculated, and the new planned path is adjusted according to the cleaning effect score to obtain the target path.

[0146] See also Figure 5 , Figure 5 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 5 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented: The environment dynamics modeling is performed on the area to be cleaned to generate the environmental state probability.

[0147] The cleaning priority of each of the areas is determined according to the environmental state probability.

[0148] Determine the planned route for the sanitation equipment based on the cleaning priority of each of the areas described.

[0149] In response to predicting a new planned path, a path adjustment amount of the new planned path relative to the original planned path is determined.

[0150] The path of the sanitation equipment is adjusted according to the path adjustment amount so that the sanitation equipment moves along the new planned path.

[0151] The cleaning effect score of the sanitation equipment is calculated, and the new planned path is adjusted according to the cleaning effect score to obtain the target path.

[0152] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0153] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as systems, methods, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0154] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0155] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0157] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0158] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An adaptive cleaning path planning system for sanitation equipment, characterized in that: The system comprises: The environmental calculation module is used to perform environmental dynamic modeling on the area to be cleaned and generate environmental state probabilities; A cleaning priority module, used to determine the cleaning priority of each of the areas according to the environmental state probability; A first planning module is used to determine a planning path for the sanitation equipment according to the cleaning priority of each of the areas; An adjustment module, configured to determine, in response to predicting a new planned path, a path adjustment amount of the new planned path relative to the original planned path; A path adjustment module, used for adjusting the path of the sanitation equipment according to the path adjustment amount, so that the sanitation equipment moves along the new planned path; The second planning module is used to calculate the cleaning effect score of the sanitation equipment and adjust the new planned path according to the cleaning effect score to obtain the target path.

2. The adaptive cleaning path planning system for sanitation equipment according to claim 1, characterized in that: The environment calculation module is specifically used for: Constructing a garbage distribution density function for representing the amount of garbage at a preset location at a preset time; Constructing an obstacle occurrence probability function for representing the probability of an obstacle appearing at the preset position at the preset time; Constructing a congestion degree function for representing the traffic congestion degree of the preset location at the preset time; An environmental state probability is generated according to the garbage distribution density function, the obstacle occurrence probability function and the congestion degree function.

3. The adaptive cleaning path planning system for sanitation equipment according to claim 2, characterized in that: The garbage distribution density function is constructed in the following way: Acquire garbage distribution images through visual sensors deployed on the sanitation equipment; Using a convolutional neural network to process the garbage distribution image to perform garbage density classification and obtain a classification result; A spatiotemporal distribution prediction model is established in combination with the classification results and historical cleaning data, and the garbage distribution density function is constructed based on the spatiotemporal distribution prediction model.

4. The adaptive cleaning path planning system for sanitation equipment according to claim 3, characterized in that: The environmental state probability is expressed as: ； in, It's location The probability of the environment state at time t is: is the garbage distribution density function, is the obstacle appearance probability function, is a function of congestion level, They are the first weight, the second weight and the third weight respectively.

5. The adaptive cleaning path planning system for sanitation equipment according to claim 4, characterized in that: The cleaning priority module is specifically used for: Determining an average value of the environmental state probability according to the environmental state probability of each of the areas; Obtaining a time decay factor for indicating the effect of the duration of uncleanness of each area on the cleaning priority; Obtaining a human flow score for indicating the magnitude of human flow in each of the areas; The cleaning priority of each area is determined according to the average value of the environmental state probability, as well as the time decay factor and the human flow score of each area.

6. The adaptive cleaning path planning system for sanitation equipment according to claim 5, characterized in that: The cleaning priorities are expressed as: ； in, is the cleaning priority of area i at time t, is the area of ​​region i, is the time since area i was last cleaned, is the traffic score of area i, They are the fourth weight, the fifth weight and the sixth weight, is the time decay factor.

7. The adaptive cleaning path planning system for sanitation equipment according to claim 6, characterized in that: The first planning module is specifically used for: Calculate the weighted sum of the leave priority of each area and the coverage degree of the path to obtain the cleaning benefit; Constructing an energy consumption function representing the energy consumed by the sanitation equipment during movement from one area to another area; Constructing a time consumption function representing the time consumed in the process of moving the sanitation equipment from one area to another area; A planned path is determined for the sanitation equipment according to the cleaning benefit, the energy consumption function and the time consumption function.

8. The adaptive cleaning path planning system for sanitation equipment according to claim 7, characterized in that: The adjustment amount module is specifically used for: Obtaining an adjustment coefficient for indicating an adjustment range of a control path; Obtaining a second time attenuation factor for controlling the degree of influence of time on path adjustment; Get the time interval between the current and last path adjustment; The difference between the new planned path and the original planned path is processed according to the adjustment coefficient, the second time attenuation factor and the time interval to determine the path adjustment amount.

9. The adaptive cleaning path planning system for sanitation equipment according to claim 8, characterized in that: The second planning module is specifically used for: Obtaining resource consumption of the sanitation equipment at the preset time; Constructing a resource consumption function according to the resource consumption of the sanitation equipment at the preset time; The cleaning effect score of the sanitation equipment is calculated based on the resource consumption function, the environmental state probability and the cleaning priority of each area.

10. An adaptive cleaning path planning method for sanitation equipment, characterized in that: The method comprises: Perform environmental dynamic modeling on the area to be cleaned and generate environmental state probabilities; Determining the cleaning priority of each of the areas according to the environmental state probability; Determine the planned routes for sanitation equipment according to the cleaning priorities of each of the areas; In response to predicting a new planned path, determining a path adjustment amount of the new planned path relative to the original planned path; Adjusting the path of the sanitation equipment according to the path adjustment amount so that the sanitation equipment moves along the new planned path; The cleaning effect score of the sanitation equipment is calculated, and the new planned path is adjusted according to the cleaning effect score to obtain the target path.

Images