Security robot collaborative inspection method and system based on task allocation optimization

Abstract

The invention is suitable for the technical field of security inspection, and provides a security robot collaborative inspection method and system based on task allocation optimization, and the method comprises the steps: obtaining the partition structure information and airflow direction information of a partitioned hazardous chemical substance warehouse with a safety buffer area, determining the relative position relationship of each inspection area of the partitioned hazardous chemical substance warehouse on the gas propagation path, identifying the inspection area located at the upstream of the gas flow and the inspection area located at the downstream of the gas flow, and obtaining the shared resource constraint information of each inspection area and the operation data of the security robot at the same time; the sampling confidence of sampling data in different inspection areas can be evaluated, and the continuous priority value adjustment amount is generated by combining the sampling confidence deviation, so that the inspection task can be preferentially allocated to an airflow upstream area with higher sampling representativeness; meanwhile, on the premise that a sampling optimization result is not damaged, the execution priority of the resource-constrained area is dynamically inhibited, and the performability and safety of the inspection task are ensured.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of security inspection, and particularly relates to a security robot cooperative inspection method and system based on task allocation optimization. BACKGROUND

[0002] The existing security robot inspection technology has been widely applied to scenes with high safety requirements such as hazardous chemical storage, experimental buildings and industrial facilities. By deploying security robots in the inspection area and carrying gas sniffing sensors, real-time monitoring of the environmental gas state can be realized, thereby assisting in discovering dangerous gas leaks and other safety hazards. In the multi-robot cooperative inspection scene, the preset inspection route, fixed inspection cycle or task allocation strategy based on spatial distance is usually used to coordinate multiple security robots to perform sniffing inspection tasks in different inspection areas, so as to improve the inspection coverage efficiency and response speed.

[0003] However, the above-mentioned existing technology focuses on inspection efficiency or path optimization in actual application, and often regards each inspection area as an equivalent target, without fully considering the complex partition structure and gas propagation characteristics in the hazardous chemical warehouse. In the partitioned hazardous chemical warehouse with a safety buffer zone, due to the influence of the ventilation system and structural isolation, different inspection areas are located at different positions in the gas propagation path, especially the safety buffer zone or the downstream area, which is easy to become a gas collection and mixing area. The existing inspection task allocation method directly allocates sniffing tasks without distinguishing the upstream and downstream of the air flow, which may lead to insufficient representativeness of the sampling results, thereby affecting the accuracy of abnormality judgment and increasing the risk of false positives or false negatives.

[0004] In addition, in the case of multiple security robots participating in inspection at the same time, the existing technology does not fully consider the constraints of shared resources in the inspection area, and usually only handles it at the level of path planning or simple obstacle avoidance, lacking a mechanism for linking and adjusting the resource occupation state and task priority. When multiple robots enter the resource-limited area at the same time, scheduling conflicts or execution blockage are easily caused. SUMMARY

[0005] The purpose of the present application is to provide a security robot cooperative inspection method and system based on task allocation optimization, which aims to solve the problems raised in the background art.

[0006] The present application is implemented as follows: a security robot cooperative inspection method based on task allocation optimization, the method comprising:

[0007] Obtain the partition structure information and the airflow direction information of the partitioned hazardous chemical warehouse with a safety buffer zone, determine the relative position relationship of each inspection area of the partitioned hazardous chemical warehouse on the gas propagation path, and identify the inspection area located upstream of the airflow and the inspection area located downstream of the airflow, while obtaining the shared resource constraint information of each inspection area and the operation data of the security robot;

[0008] According to the relative position relationship and the partition structure of each inspection area, evaluate the sampling confidence of obtaining effective sampling data when performing sniffing inspection tasks in each inspection area, and when the sampling confidence corresponding to the inspection area located downstream of the airflow is lower than a preset threshold, generate a corresponding priority adjustment amount based on the deviation amplitude between the sampling confidence and the preset threshold;

[0009] According to the priority adjustment amount, adjust the inspection execution priority corresponding to the inspection area downstream of the airflow and the inspection area upstream of the airflow accordingly to obtain the adjusted downstream inspection execution priority and upstream inspection execution priority;

[0010] Based on the shared resource constraint information of each inspection area, determine the current shared resource constraint level of the corresponding inspection area, and select the corresponding inhibition factor from a preset inhibition factor set based on the shared resource constraint level;

[0011] According to the inhibition factor, correct the adjusted downstream inspection execution priority and upstream inspection execution priority, and perform the corresponding sniffing inspection task according to the final downstream inspection execution priority and the final upstream inspection execution priority obtained after correction.

[0012] As a further limitation of the technical scheme of the embodiment of the present application, according to the relative position relationship and the partition structure of each inspection area, the sampling confidence of obtaining effective sampling data when performing sniffing inspection tasks in each inspection area is evaluated, and when the sampling confidence corresponding to the inspection area located downstream of the airflow is lower than a preset threshold, the corresponding priority adjustment amount is generated based on the deviation amplitude between the sampling confidence and the preset threshold, the steps comprising:

[0013] According to the relative position relationship of the inspection area on the gas propagation path, determine whether the inspection area is located upstream or downstream of the airflow;

[0014] Based on the partition structure attribute corresponding to the inspection area, evaluate the degree to which the sampling data is affected by gas convergence when performing sniffing inspection tasks in the inspection area, and determine the sampling confidence of the inspection area accordingly;

[0015] Compare the sampling confidence corresponding to the inspection area located downstream of the airflow with the preset threshold, and calculate the deviation amplitude when the sampling confidence is lower than the preset threshold;

[0016] The corresponding priority value adjustment amount is generated through a preset mapping relationship based on the deviation amplitude, and the greater the deviation amplitude, the greater the absolute value of the generated priority value adjustment amount.

[0017] As a further limitation of the technical scheme of the embodiment of the application, the step of adjusting the execution priority of the inspection according to the priority value adjustment amount includes:

[0018] obtaining an initial downstream inspection execution priority for the downstream inspection area and an initial upstream inspection execution priority for the upstream inspection area;

[0019] adjusting the initial downstream inspection execution priority downward and the initial upstream inspection execution priority upward based on the priority value adjustment amount to generate an adjusted downstream inspection execution priority and an adjusted upstream inspection execution priority;

[0020] In the process of adjusting the inspection execution priority, the adjusted downstream inspection execution priority and the adjusted upstream inspection execution priority are subjected to preset upper and / or lower priority value constraints to ensure that the adjusted inspection execution priority is within a preset effective range.

[0021] As a further limitation of the technical scheme of the embodiment of the application, the step of determining the current shared resource constraint level of the corresponding inspection area based on the shared resource constraint information of each inspection area and selecting the corresponding suppression factor from a preset suppression factor set based on the shared resource constraint level includes:

[0022] Based on the shared resource constraint information of each inspection area, the shared resource constraint parameter of the corresponding inspection area is obtained, and the shared resource constraint parameter includes at least one of the number limit of security robots allowed to enter the inspection area at the same time, the number of security robots currently entering the inspection area, and the time sequence limit of entering or staying in the inspection area.

[0023] According to the shared resource constraint parameter, the shared resource constraint level of the inspection area at the current time is evaluated, and the current shared resource constraint level of the inspection area is determined accordingly;

[0024] The suppression factor corresponding to the current shared resource constraint level is selected from the preset suppression factor set.

[0025] As a further limitation of the technical scheme of the embodiment of the application, the step of correcting the adjusted downstream inspection execution priority and the upstream inspection execution priority according to the suppression factor and executing the corresponding sniffing inspection task according to the final downstream inspection execution priority and the final upstream inspection execution priority obtained after correction includes:

[0026] The adjusted downstream patrol execution priority value and the adjusted upstream patrol execution priority value are corrected by an inhibition factor to obtain a final downstream patrol execution priority value and a final upstream patrol execution priority value;

[0027] According to the final downstream patrol execution priority value and the final upstream patrol execution priority value, the to-be-executed sniffing patrol tasks are sequenced to form a patrol task execution sequence;

[0028] Under the premise of meeting the shared resource constraint information, the sniffing patrol tasks are sequentially assigned to corresponding security robots according to the patrol task execution sequence;

[0029] The security robots enter corresponding patrol areas and execute the sniffing patrol tasks according to the patrol task execution sequence.

[0030] A security robot cooperative patrol system based on task allocation optimization, the system comprises:

[0031] A structure airflow data module is configured to acquire partition structure information and airflow direction information of a partitioned hazardous chemical warehouse with a safety buffer zone, determine relative position relationships of each patrol area of the partitioned hazardous chemical warehouse on a gas propagation path, and identify a patrol area located upstream of an airflow and a patrol area located downstream of the airflow, while acquiring shared resource constraint information of each patrol area and operation data of a security robot;

[0032] A priority adjustment amount generation module is configured to evaluate a sampling confidence degree of obtaining effective sampling data when a sniffing patrol task is executed in each patrol area according to the relative position relationships and the partition structure of each patrol area, and generate a corresponding priority adjustment amount based on a deviation amplitude between the sampling confidence degree and a preset threshold when the corresponding sampling confidence degree of the patrol area located downstream of the airflow is lower than the preset threshold;

[0033] A patrol execution priority adjustment module is configured to adjust patrol execution priorities of the patrol area located downstream of the airflow and the patrol area located upstream of the airflow according to the priority adjustment amount to obtain an adjusted downstream patrol execution priority value and an adjusted upstream patrol execution priority value;

[0034] An inhibition factor selection module is configured to determine a current shared resource constraint level of a corresponding patrol area based on shared resource constraint information of each patrol area, and select a corresponding inhibition factor from a preset inhibition factor set based on the shared resource constraint level;

[0035] A patrol task correction and execution module is configured to correct the adjusted downstream patrol execution priority value and the adjusted upstream patrol execution priority value according to the inhibition factor, and execute corresponding sniffing patrol tasks according to a final downstream patrol execution priority value and a final upstream patrol execution priority value obtained after the correction.

[0036] As a further limitation of the technical solutions of the embodiments of the present application, the priority value adjustment amount generation module specifically comprises:

[0037] A relative position determination unit is configured to determine whether the inspection region is located upstream or downstream of the gas flow according to the relative position relationship of the inspection region on the gas propagation path.

[0038] A sampling confidence assessment unit is configured to assess the degree of influence of the gas collection on the sampling data when the sniffing inspection task is performed in the inspection region based on the partition structure attribute corresponding to the inspection region, and determine the sampling confidence of the inspection region according to the assessment.

[0039] A deviation amplitude calculation unit is configured to compare the sampling confidence corresponding to the inspection region located downstream of the gas flow with a preset threshold, and calculate the deviation amplitude of the sampling confidence lower than the preset threshold.

[0040] A priority value adjustment amount generation unit is configured to generate a corresponding priority value adjustment amount based on the deviation amplitude through a preset mapping relationship, wherein the greater the deviation amplitude, the greater the absolute value of the generated priority value adjustment amount.

[0041] As a further limitation of the technical solutions of the embodiments of the present application, the inspection execution priority value adjustment module specifically comprises:

[0042] An initial priority value acquisition unit is configured to acquire an initial downstream inspection execution priority value for the inspection region downstream of the gas flow and an initial upstream inspection execution priority value for the inspection region upstream of the gas flow.

[0043] A priority value linkage adjustment unit is configured to lower the initial downstream inspection execution priority value and raise the initial upstream inspection execution priority value based on the priority value adjustment amount, to generate an adjusted downstream inspection execution priority value and an adjusted upstream inspection execution priority value.

[0044] A priority value constraint control unit is configured to apply a preset upper limit and / or lower limit constraint on the adjusted downstream inspection execution priority value and the adjusted upstream inspection execution priority value in the process of adjusting the inspection execution priority value, to ensure that the adjusted inspection execution priority value is within a preset effective range.

[0045] As a further limitation of the technical solutions of the embodiments of the present application, the suppression factor selection module specifically comprises:

[0046] The shared resource constraint parameter acquisition unit is configured to acquire a shared resource constraint parameter of the corresponding inspection area based on shared resource constraint information of each inspection area, wherein the shared resource constraint parameter comprises at least one of a limit on the number of security robots allowed to enter the inspection area simultaneously, the number of security robots currently entering the inspection area, and a time sequence limit on entering or staying in the inspection area.

[0047] The shared resource constraint level determination unit is configured to evaluate the degree of shared resource constraint of the inspection area at the current time according to the shared resource constraint parameter, and determine the current shared resource constraint level of the inspection area according to the evaluation result.

[0048] The suppression factor selection unit is configured to select a suppression factor corresponding to the current shared resource constraint level from a preset set of suppression factors.

[0049] As a further limitation of the technical scheme of the embodiment of the present application, the inspection task modification and execution module specifically comprises:

[0050] The execution priority value modification unit is configured to modify the adjusted downstream inspection execution priority value and the adjusted upstream inspection execution priority value by the suppression factor, respectively, to obtain a final downstream inspection execution priority value and a final upstream inspection execution priority value.

[0051] The inspection task sequencing unit is configured to sequence the sniffing inspection tasks to be executed according to the final downstream inspection execution priority value and the final upstream inspection execution priority value, to form an inspection task execution sequence.

[0052] The inspection task allocation unit is configured to allocate the sniffing inspection tasks to the corresponding security robots for execution in sequence according to the inspection task execution sequence, under the premise of meeting the shared resource constraint information.

[0053] The inspection task execution control unit is configured to control the security robots to enter the corresponding inspection areas and execute the sniffing inspection tasks in sequence according to the inspection task execution sequence.

[0054] Compared with the prior art, the present application optimizes the distribution of sniffing and inspection tasks in the partitioned hazardous chemical warehouse with a safety buffer zone by introducing a partition structure and airflow propagation, breaking through the scheduling mode of the existing multi-robot inspection which only relies on spatial distance or fixed priority. By evaluating the sampling confidence of the sampling data in different inspection areas, and combining the sampling confidence bias to generate a continuous priority adjustment amount, the inspection task can be preferentially distributed to the upstream area of the airflow with higher sampling representativeness; at the same time, the shared resource constraint level and the suppression factor mechanism are introduced, which dynamically suppresses the execution priority of the resource-constrained area without destroying the sampling optimization result, ensuring the executability and safety of the inspection task. The present application realizes the collaborative scheduling of sampling effectiveness and resource constraints, can effectively reduce the positioning bias and misjudgment risk of abnormal sources, and is suitable for multi-robot collaborative security inspection in complex environments such as hazardous chemical warehouses, laboratory buildings, and industrial facilities, and has good engineering application prospect. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 The flowchart of the method provided for the embodiments of the present application;

[0056] Figure 2 The flowchart of generating a priority adjustment amount in the method provided for the embodiments of the present application;

[0057] Figure 3 The flowchart of adjusting the inspection execution priority in the method provided for the embodiments of the present application;

[0058] Figure 4 The flowchart of selecting a suppression factor in the method provided for the embodiments of the present application;

[0059] Figure 5 The flowchart of correcting and executing the inspection task in the method provided for the embodiments of the present application;

[0060] Figure 6 The application architecture diagram of the system provided for the embodiments of the present application;

[0061] Figure 7 The structural block diagram of the priority adjustment amount generation module in the system provided for the embodiments of the present application;

[0062] Figure 8 The structural block diagram of the inspection execution priority adjustment module in the system provided for the embodiments of the present application;

[0063] Figure 9 The structural block diagram of the suppression factor selection module in the system provided for the embodiments of the present application;

[0064] Figure 10 The structural block diagram of the inspection task correction and execution module in the system provided for the embodiments of the present application. DETAILED DESCRIPTION

[0065] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0066] Figure 1 A flow chart of the method provided by the embodiment of the present application is shown.

[0067] Specifically, a security robot cooperative inspection method based on task allocation optimization, the method specifically comprises the following steps:

[0068] In step S100, the partition structure information and airflow direction information of the partitioned hazardous chemical warehouse with a safety buffer zone are obtained, the relative position relationship of each inspection area of the partitioned hazardous chemical warehouse on the gas propagation path is determined, and the inspection area located upstream of the airflow and the inspection area located downstream of the airflow are identified, and the shared resource constraint information of each inspection area and the operation data of the security robot are obtained.

[0069] In the embodiment of the present application, the partitioned hazardous chemical warehouse with a safety buffer zone refers to a storage and management facility for storing and managing hazardous chemicals, which is divided into multiple functional partitions in the overall spatial structure, and at least one safety buffer zone is provided between the core storage area and the external passage. The safety buffer zone is usually connected with the adjacent partition through access interlocking, directional ventilation or isolation structure, and is used for temporarily intercepting, collecting or guiding the leaked gas when the gas leakage occurs, so as to reduce the risk of direct diffusion of dangerous gas to the external environment or personnel activity area. Since the safety buffer zone simultaneously assumes the isolation and transition functions in structure and function, the internal gas distribution state is often different from that of the core storage area or the external passage, so that the entire hazardous chemical warehouse presents obvious partitioning and non-uniform gas propagation characteristics.

[0070] The present application takes the sniffing inspection task of the partitioned hazardous chemical warehouse with a safety buffer zone as the research object, the main reason is that in this kind of scene, the gas propagation path is complex, the airflow direction is relatively fixed and is significantly affected by the ventilation system, and the sniffing sampling data obtained by different inspection areas has natural differences in representativeness and reliability. Especially in the multi-robot cooperative inspection scene, if the sniffing task is allocated only according to the spatial distance or the inspection order, the position difference of the safety buffer zone, the core storage area and other different partitions in the gas propagation chain is easily ignored, and then the sampling result deviates from the actual leakage source, affecting the accuracy of abnormal judgment and risk assessment. Especially due to the structure and function of the safety buffer zone, it may become a gas collection and mixing area, if the sniffing inspection task is allocated to the safety buffer zone only according to the spatial distance, the sampling result lacks source representativeness, and then abnormal source positioning error and risk level misjudgment are caused.

[0071] In the embodiment, the partition structure information is used to describe the spatial division and regional attributes of the partitioned dangerous chemical warehouse with a safety buffer zone, which includes the spatial boundary information of each inspection region, the regional type identification, the connection relationship between regions, the connection mode of the safety buffer zone and the adjacent region, and whether there is a closed structure or a collection structure in the region, etc. By obtaining the partition structure information, the functional role and physical position of different inspection regions in the overall warehouse structure can be determined, which provides a basis for subsequent analysis of gas propagation path and sampling conditions.

[0072] The gas flow direction information is used to reflect the main flow direction of the gas in the dangerous chemical warehouse under normal ventilation or leakage state, which can include the air supply direction and exhaust direction of the ventilation system, the dominant gas flow direction between each partition, the gas flow direction in the safety buffer zone, and the time sequence stability information of the gas flow direction. By combining the partition structure information and the gas flow direction information, the relative position relationship of each inspection region on the gas propagation path can be determined, so as to identify the inspection region located upstream of the gas flow and the inspection region located downstream of the gas flow.

[0073] In the embodiment, the shared resource constraint information refers to the constraint conditions imposed by each inspection region on the entry, stay or operation of the security robot in the same time period during the cooperative inspection of multiple security robots. The shared resource constraint information can include the limitation of the number of security robots allowed to enter a certain inspection region at the same time, the number of security robots that have already entered the inspection region, the time sequence limitation of the inspection region on the entry or stay of the robot, and other shared resource limitations caused by safety management strategies or equipment capabilities. Such shared resource constraint information is used to reflect the occupancy degree and carrying capacity of the robot resource of the inspection region in the current state.

[0074] The operation data of the security robot is used to reflect the current operation state of each security robot when performing the cooperative inspection task, which can include the position information, operation state information, power state information, task execution state and historical inspection record of the security robot. By obtaining the operation data of the security robot, a basis condition can be provided for subsequent reasonable allocation and execution of the inspection task, so as to avoid the situation that the robot capacity is insufficient or the operation state is not suitable in the task allocation process.

[0075] Further, the security robot cooperative inspection method based on task allocation optimization further includes the following steps:

[0076] In step S200, according to the relative position relationship and the partition structure of each inspection area, the sampling confidence of obtaining effective sampling data when performing sniffing inspection task in each inspection area is evaluated, and when the corresponding sampling confidence of the inspection area located downstream of the gas flow is lower than a preset threshold, a corresponding priority adjustment amount is generated based on the deviation amplitude between the sampling confidence and the preset threshold.

[0077] Specifically, Figure 2 A flowchart for generating the priority adjustment amount is shown.

[0078] In step S200, according to the relative position relationship and the partition structure of each inspection area, the sampling confidence of obtaining effective sampling data when performing sniffing inspection task in each inspection area is evaluated, and when the corresponding sampling confidence of the inspection area located downstream of the gas flow is lower than a preset threshold, a corresponding priority adjustment amount is generated based on the deviation amplitude between the sampling confidence and the preset threshold.

[0079] In step S201, according to the relative position relationship of the inspection area on the gas propagation path, it is determined whether the inspection area is located upstream or downstream of the gas flow.

[0080] In step S202, based on the partition structure attribute corresponding to the inspection area, the degree of influence of gas collection on the sampling data when performing sniffing inspection task in the inspection area is evaluated, and the sampling confidence of the inspection area is determined accordingly.

[0081] In step S203, the sampling confidence corresponding to the inspection area located downstream of the gas flow is compared with the preset threshold, and the deviation amplitude of the sampling confidence lower than the preset threshold is calculated.

[0082] In step S204, based on the deviation amplitude, a corresponding priority adjustment amount is generated through a preset mapping relationship, wherein the greater the deviation amplitude, the greater the absolute value of the generated priority adjustment amount.

[0083] In the embodiment of the present application, the core significance of step S201 is to determine the order of different inspection areas in the gas propagation path. By combining the gas flow direction information obtained in step S100 and the spatial position of the inspection area in the partitioned dangerous chemical warehouse, it can be judged whether a certain inspection area is located upstream or downstream of the gas propagation path. The inspection area located upstream of the gas flow is usually closer to the potential gas leakage source, and its sniffing sampling data is more likely to reflect the initial state of the gas; while the inspection area located downstream of the gas flow often receives diffused, mixed or collected gas, and its sampling result may be affected by the superposition of multi-source gas or the buffer structure. By distinguishing the upstream and downstream in step S201, an important semantic premise for the evaluation of sampling confidence in step S202 can be provided, so that the sampling confidence is not only based on the local structure condition, but also can be comprehensively judged in combination with the relative position in the gas propagation chain.

[0084] The partition structure attribute can include whether the inspection area belongs to a safety buffer zone, whether it is located in a closed or semi-closed space, whether it is in communication with multiple partitions, whether it is provided with a flow guide or exhaust structure, and the spatial volume characteristics of the area, etc. When the inspection area is in a safety buffer zone or a multi-partition intersection position, gas is more likely to be trapped, mixed or secondarily collected in the area, so that the gas composition collected by the sniffing sensor deviates from the original characteristics of the actual leakage source. By analyzing the above partition structure attributes, the degree of influence of the sampling data by gas collection can be evaluated, such as determining whether the area is a gas easy collection area, whether the gas can come from multiple upstream areas, or whether there is a significant secondary diffusion phenomenon.

[0085] In the present embodiment, the sampling confidence is used to characterize the degree of confidence of the sampling data obtained when performing sniffing inspection tasks in a certain inspection area to the true gas leakage state. The sampling confidence can be determined according to the degree of influence of gas collection. The lower the degree of influence of gas collection, the closer the sampling data is to the source of gas propagation, and the higher the sampling confidence. On the contrary, when the degree of influence of gas collection is high, the sampling data is more likely to be affected by multi-source mixing or spatial structure interference, and the sampling confidence is correspondingly reduced. By mapping the results of partition structure attribute analysis to sampling confidence, quantitative evaluation of the effectiveness of sampling in different inspection areas can be achieved.

[0086] In step S203, the purpose of setting the preset threshold is to distinguish whether the sampling result has sufficient representativeness. When the sampling confidence is higher than the preset threshold, it means that the sampling data of the inspection area still has a certain effectiveness, and no additional adjustment of the inspection task priority is needed. When the sampling confidence is lower than the preset threshold, it means that the sampling data of the inspection area is not representative enough, and the sniffing result has limited support for anomaly judgment. The preset threshold can be set according to historical inspection data, sensor performance parameters or safety management strategies, and is used as a judgment benchmark for sampling effectiveness.

[0087] The deviation amplitude reflects the gap between the current inspection area sampling confidence and the ideal sampling state. The larger the deviation amplitude, the higher the degree of deviation of the sampling result from the effective state. The preset mapping relationship is used to map the deviation amplitude to the adjustment amplitude of the inspection execution priority value. It can be a linear mapping relationship, a segmented mapping relationship or other pre-set corresponding relationship, so that the deviation amplitude and the adjustment amount of the priority value are monotonically related. Through the preset mapping relationship, when the sampling confidence deviates from the preset threshold more, the absolute value of the priority value adjustment amount generated by the corresponding generation is larger, so that the execution priority of the downstream inspection area is more significantly reduced in the subsequent inspection task allocation, or the execution priority of the upstream inspection area of the gas flow is correspondingly improved.

[0088] Further, the security robot cooperative inspection method based on task allocation optimization further comprises the following steps.

[0089] In step S300, the inspection execution priorities for the airflow downstream inspection area and the airflow upstream inspection area are adjusted according to the priority adjustment amount, to obtain adjusted downstream inspection execution priority and upstream inspection execution priority.

[0090] Specifically, Figure 3 A flowchart of adjusting the inspection execution priority is shown.

[0091] The adjusting the inspection execution priority according to the priority adjustment amount specifically comprises the following steps:

[0092] In step S301, an initial downstream inspection execution priority for the airflow downstream inspection area and an initial upstream inspection execution priority for the airflow upstream inspection area are obtained.

[0093] In step S302, the initial downstream inspection execution priority is adjusted downward and the initial upstream inspection execution priority is adjusted upward based on the priority adjustment amount, to generate an adjusted downstream inspection execution priority and an adjusted upstream inspection execution priority.

[0094] In step S303, during the adjustment of the inspection execution priority, the adjusted downstream inspection execution priority and the adjusted upstream inspection execution priority are subjected to a preset upper limit and / or lower limit constraint of the priority, to ensure that the adjusted inspection execution priority is within a preset effective range.

[0095] In the embodiment of the present application, the initial downstream inspection execution priority and the initial upstream inspection execution priority can be determined according to factors such as a pre-set inspection strategy, an inspection cycle requirement, a historical inspection frequency, or an importance degree of the inspection area, to reflect a default execution order of each inspection area in the cooperative inspection task when the influence of the sampling confidence is not considered. By obtaining the initial downstream inspection execution priority and the initial upstream inspection execution priority, a benchmark can be provided for subsequent dynamic adjustment based on the sampling confidence.

[0096] In step S302, based on the priority value adjustment amount generated in step S204, the initial downstream patrol execution priority value and the initial upstream patrol execution priority value are adjusted in opposite directions. Specifically, when the priority value adjustment amount is used to reflect the degree of insufficient sampling confidence of the downstream patrol area, the initial downstream patrol execution priority value is lowered, so that the execution order of the downstream patrol area in the subsequent patrol task allocation is relatively moved backward; at the same time, the initial upstream patrol execution priority value is raised, so that the patrol area located upstream of the air flow and having higher sampling representativeness obtains a higher execution priority. Through this upstream and downstream linkage priority value adjustment mode, the security robot can be guided to preferentially execute the patrol task with higher sampling representativeness without changing the overall number of patrol tasks, thereby improving the effectiveness of the cooperative patrol result.

[0097] In the present embodiment, the priority value adjustment amount can directly participate in the numerical operation of the patrol execution priority value, for example, acting on the initial patrol execution priority value in an addition or subtraction manner or a proportional adjustment manner, so that the adjusted patrol execution priority value can continuously change, thereby avoiding the scheduling rigidity problem caused by only discrete level switching. By mapping the sampling confidence deviation degree into a continuous priority value adjustment amount, fine control of the patrol execution order can be realized.

[0098] In step S303, in order to avoid the problem of excessively high or low patrol execution priority value during the priority value adjustment process, a preset upper limit and / or lower limit constraint is applied to the adjusted downstream patrol execution priority value and the adjusted upstream patrol execution priority value. The upper limit and lower limit of the priority value are used to limit the value range of the patrol execution priority value, so that it is always within the effective interval that can be recognized and processed by the system. For example, when the priority value adjustment amount is large, the upper limit constraint is used to prevent a certain patrol area from being advanced indefinitely; when the priority value adjustment amount is negative, the lower limit constraint is used to prevent a certain patrol area from being suppressed for a long time and unable to obtain an execution opportunity.

[0099] Further, the security robot cooperative patrol method based on task allocation optimization further comprises the following steps:

[0100] Step S400, based on the shared resource constraint information of each patrol area, determine the current shared resource constraint level of the corresponding patrol area, and select the corresponding inhibition factor from the preset inhibition factor set based on the shared resource constraint level.

[0101] Specifically, Figure 4 A flowchart for selecting an inhibition factor is shown.

[0102] The current shared resource constraint level of the corresponding inspection area is determined based on the shared resource constraint information of each inspection area, and a corresponding inhibition factor is selected from a preset inhibition factor set based on the shared resource constraint level, specifically including the following steps:

[0103] In step S401, the shared resource constraint parameter of the corresponding inspection area is obtained based on the shared resource constraint information of each inspection area, and the shared resource constraint parameter includes at least one of the number limit of security robots allowed to enter the inspection area at the same time, the number of security robots currently entering the inspection area, and the time sequence limit of entering or staying in the inspection area.

[0104] In step S402, the degree of shared resource constraint of the inspection area at the current time is evaluated according to the shared resource constraint parameter, and the current shared resource constraint level of the inspection area is determined accordingly.

[0105] In step S403, an inhibition factor corresponding to the current shared resource constraint level is selected from a preset inhibition factor set.

[0106] In the embodiment of the application, the shared resource constraint parameter is used to reflect the occupation and carrying capacity of the security robot in the inspection area, which can include the number limit of security robots allowed to enter the inspection area at the same time, the number of security robots currently entering the inspection area, and the time sequence limit required to enter or stay in the inspection area. By obtaining the above shared resource constraint parameter, the availability and tension of the robot resource in the current state of the inspection area can be objectively described.

[0107] Specifically, the number of security robots currently entering the inspection area can be compared with the number limit of security robots allowed to enter the inspection area at the same time. When the current entering number approaches or reaches the number limit, it indicates that the shared resource of the inspection area is in a highly limited state. When the current entering number is much lower than the number limit, it indicates that the inspection area still has a large resource margin. In addition, for the inspection area with time sequence limit for entering or staying, the time sequence of each security robot entering the area, the staying time, and whether there is mutual exclusion or sequential execution requirement can be combined to further evaluate the degree of shared resource constraint. When there is a strict time sequence limit or mutual exclusion requirement in the inspection area, even if the number of security robots currently entering is small, it can be determined that the degree of resource constraint is high.

[0108] In the embodiment, the sharing resource restriction degree can be obtained by comprehensively analyzing the sharing resource constraint parameters, such as forming a comprehensive evaluation result based on the number of occupancy proportion, time sequence conflict situation or resource waiting state and other factors. The sharing resource restriction degree is used to reflect the carrying capacity of the patrol area for the new patrol task at the current time. The higher the restriction degree, the less suitable the patrol area is for assigning new patrol tasks at the current stage.

[0109] After determining the sharing resource restriction degree, the current sharing resource constraint level of the patrol area is determined according to the sharing resource restriction degree in step S402. The sharing resource constraint level can be a discrete level set in advance, which is used to classify the continuous or complex resource restriction state. For example, the sharing resource constraint level can be divided into low constraint level, medium constraint level and high constraint level. When the sharing resource restriction degree is low, the patrol area is classified as low constraint level. When the sharing resource restriction degree is in an intermediate state, the patrol area is classified as medium constraint level. When the sharing resource restriction degree is high or close to the resource upper limit, the patrol area is classified as high constraint level. In this way, the complex resource state can be converted into clear level information that can be used for subsequent decision-making.

[0110] The inhibition factor is used to modify the patrol execution priority in the subsequent step, and the value is matched with the sharing resource constraint level. When the sharing resource constraint level of the patrol area is high, the selected inhibition factor is used to have a stronger inhibitory effect on the patrol execution priority. When the sharing resource constraint level is low, the selected inhibition factor has a weak effect on the patrol execution priority. By mapping the sharing resource restriction degree to the sharing resource constraint level and further mapping it to the inhibition factor, the influence of resource competition on scheduling decision can be explicitly reflected in the patrol task allocation process.

[0111] Further, the security robot cooperative patrol method based on task allocation optimization further comprises the following steps:

[0112] Step S500, modifying the adjusted downstream patrol execution priority and upstream patrol execution priority according to the inhibition factor, and executing the corresponding sniffing patrol task according to the final downstream patrol execution priority and the final upstream patrol execution priority obtained after modification.

[0113] Specifically, Figure 5 The flowchart of modifying and executing the patrol task is shown.

[0114] The flowchart of modifying and executing the patrol task is shown. The method comprises the following steps:

[0115] Step S501, the adjusted downstream patrol execution priority value and the adjusted upstream patrol execution priority value are modified by the inhibition factor respectively to obtain a final downstream patrol execution priority value and a final upstream patrol execution priority value;

[0116] Step S502, according to the final downstream patrol execution priority value and the final upstream patrol execution priority value, the to-be-executed sniffing patrol task is sequenced to form a patrol task execution sequence;

[0117] Step S503, under the premise of meeting the shared resource constraint information, the sniffing patrol task is sequentially assigned to the corresponding security robot for execution according to the patrol task execution sequence;

[0118] Step S504, the security robot is controlled to sequentially enter the corresponding patrol area and execute the sniffing patrol task according to the patrol task execution sequence.

[0119] In the embodiment of the application, the inhibition factor is used to reflect the carrying capacity of the patrol area to the shared resource of the security robot. When the shared resource constraint level of the patrol area is high, the corresponding inhibition factor is used to exert a stronger inhibitory effect on the patrol execution priority value, so that the execution order of the patrol area in the final scheduling is relatively moved backward. When the shared resource constraint level is low, the corresponding inhibition factor has less effect on the patrol execution priority value, thereby avoiding unnecessary suppression of the patrol task of the resource sufficient area. By introducing the inhibition factor in this stage, the resource availability factor can be integrated into the final priority value without destroying the above-mentioned adjustment result based on sampling representativeness.

[0120] The patrol task execution sequence is used to determine the execution order of the corresponding sniffing patrol task of different patrol areas in the time dimension, and the sequencing result comprehensively reflects the influence of the sampling confidence, the airflow propagation position relationship and the shared resource constraint and other factors. By taking the final patrol execution priority value as the sequencing basis, it can be ensured that the patrol task with higher priority is preferentially scheduled and executed in the overall cooperative patrol process.

[0121] Specifically, in the task allocation process, the running data of the security robot obtained in step S100 is combined to judge the current available state of each security robot, and only when the shared resource constraint of the patrol area is not violated, the corresponding sniffing patrol task is allocated to the security robot for execution. When a patrol area does not meet the shared resource constraint condition at the current time, the allocation of the patrol task can be delayed, and the scheduling is performed after the resource condition is met, so as to ensure the executability and safety of the patrol task allocation.

[0122] When the security robot performs the sniffing inspection task, the security robot can enter the inspection area according to the predetermined path, sniff and sample the environmental gas, and use the sampling result for subsequent abnormality judgment or risk analysis. By strictly controlling according to the inspection task execution sequence, conflict or resource contention of multiple security robots in the same inspection area can be avoided, and the inspection sequence is ensured to be consistent with the scheduling result optimized based on the priority value.

[0123] Further, Figure 6 An application architecture diagram of the system provided by the embodiment of the application is shown.

[0124] In another preferred embodiment provided by the application, a security robot cooperative inspection system based on task allocation optimization comprises:

[0125] The structure airflow data module 100 is configured to acquire the partition structure information and airflow direction information of the partitioned hazardous chemical warehouse with a safety buffer zone, determine the relative position relationship of each inspection area of the partitioned hazardous chemical warehouse on the gas propagation path, and identify the inspection area located upstream of the airflow and the inspection area located downstream of the airflow, and acquire the shared resource constraint information of each inspection area and the operation data of the security robot.

[0126] Further, the security robot cooperative inspection system based on task allocation optimization further comprises:

[0127] The priority value adjustment amount generation module 200 is configured to evaluate the sampling confidence of obtaining effective sampling data when each inspection area performs the sniffing inspection task according to the relative position relationship and the partition structure of each inspection area, and generate a corresponding priority value adjustment amount based on the deviation amplitude between the sampling confidence and a preset threshold when the corresponding sampling confidence of the inspection area located downstream of the airflow is lower than the preset threshold.

[0128] Specifically, Figure 7 A structural block diagram of the priority value adjustment amount generation module 200 in the system provided by the embodiment of the application is shown.

[0129] In the preferred embodiment provided by the application, the priority value adjustment amount generation module 200 specifically comprises:

[0130] The relative position determination unit 201 is configured to determine whether the inspection area is located upstream of the airflow or downstream of the airflow according to the relative position relationship of the inspection area on the gas propagation path.

[0131] The sampling confidence evaluation unit 202 is configured to evaluate the degree to which the sampling data is affected by the gas convergence when the inspection area performs the sniffing inspection task based on the partition structure attribute corresponding to the inspection area, and determine the sampling confidence of the inspection area according to the evaluation result.

[0132] The deviation amplitude calculation unit 203 is configured to compare the sampling confidence corresponding to the inspection area downstream of the air flow with a preset threshold, and calculate a deviation amplitude of the sampling confidence lower than the preset threshold.

[0133] The priority adjustment amount generation unit 204 is configured to generate a corresponding priority adjustment amount based on the deviation amplitude through a preset mapping relationship, wherein the greater the deviation amplitude, the greater the absolute value of the generated priority adjustment amount.

[0134] Further, the security robot cooperative inspection system based on task allocation optimization further comprises:

[0135] The inspection execution priority adjustment module 300 is configured to adjust the inspection execution priorities for the downstream inspection area and the upstream inspection area according to the priority adjustment amount, to obtain an adjusted downstream inspection execution priority and an adjusted upstream inspection execution priority.

[0136] Specifically, Figure 8 The structure block diagram of the inspection execution priority adjustment module 300 in the system provided by the embodiment of the application is shown.

[0137] In the preferred embodiment provided by the application, the inspection execution priority adjustment module 300 specifically comprises:

[0138] The initial priority acquisition unit 301 is configured to acquire an initial downstream inspection execution priority for the downstream inspection area and an initial upstream inspection execution priority for the upstream inspection area.

[0139] The priority linkage adjustment unit 302 is configured to lower the initial downstream inspection execution priority and raise the initial upstream inspection execution priority based on the priority adjustment amount, to generate an adjusted downstream inspection execution priority and an adjusted upstream inspection execution priority.

[0140] The priority constraint control unit 303 is configured to apply a preset upper limit and / or lower limit constraint to the adjusted downstream inspection execution priority and the adjusted upstream inspection execution priority in the process of adjusting the inspection execution priority, to ensure that the adjusted inspection execution priority is within a preset effective range.

[0141] Further, the security robot cooperative inspection system based on task allocation optimization further comprises:

[0142] The suppression factor selection module 400 is configured to determine a current shared resource constraint level of the corresponding inspection area based on the shared resource constraint information of each inspection area, and select a corresponding suppression factor from a preset suppression factor set based on the shared resource constraint level.

[0143] Specifically, Figure 9 A structural block diagram of the inhibition factor selection module 400 in the system provided by the embodiment of the present application is shown.

[0144] In the preferred embodiment provided by the present application, the inhibition factor selection module 400 specifically comprises:

[0145] A shared resource constraint parameter acquisition unit 401 is configured to acquire a shared resource constraint parameter of the corresponding inspection area based on the shared resource constraint information of each inspection area, wherein the shared resource constraint parameter comprises at least one of the following: a limit on the number of security robots allowed to enter the inspection area at the same time, the number of security robots currently entering the inspection area, and a time sequence limit for entering or staying in the inspection area.

[0146] A shared resource constraint level determination unit 402 is configured to evaluate the degree of limitation of the shared resource of the inspection area at the current time according to the shared resource constraint parameter, and determine the current shared resource constraint level of the inspection area according to the evaluation result.

[0147] An inhibition factor selection unit 403 is configured to select an inhibition factor corresponding to the current shared resource constraint level from a preset inhibition factor set.

[0148] Further, the security robot cooperative inspection system based on task allocation optimization further comprises:

[0149] An inspection task correction and execution module 500 is configured to correct the adjusted downstream inspection execution priority value and the adjusted upstream inspection execution priority value according to the inhibition factor, and execute the corresponding sniffing inspection task according to the final downstream inspection execution priority value and the final upstream inspection execution priority value obtained after correction.

[0150] Specifically, Figure 10 A structural block diagram of the inspection task correction and execution module 500 in the system provided by the embodiment of the present application is shown.

[0151] In the preferred embodiment provided by the present application, the inspection task correction and execution module 500 specifically comprises:

[0152] An execution priority correction unit 501 is configured to correct the adjusted downstream inspection execution priority value and the adjusted upstream inspection execution priority value respectively by using the inhibition factor, and obtain a final downstream inspection execution priority value and a final upstream inspection execution priority value.

[0153] An inspection task sorting unit 502 is configured to sort the sniffing inspection tasks to be executed according to the final downstream inspection execution priority value and the final upstream inspection execution priority value, and form an inspection task execution sequence.

[0154] The patrol task assignment unit 503 is configured to assign the sniffing patrol task to the corresponding security robot in sequence according to the patrol task execution sequence under the premise that the shared resource constraint information is met.

[0155] The patrol task execution control unit is configured to control the security robot to enter the corresponding patrol area in sequence and execute the sniffing patrol task according to the patrol task execution sequence.

[0156] It should be understood that, although each step in the flowchart of each embodiment of the present application is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0157] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments of each method. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0158] Any technical features in the above-described embodiments can be combined in any manner, and for the sake of brevity, not all possible combinations are described, but it is understood that the scope of the present specification includes all possible combinations.

[0159] The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application patent should be subject to the appended claims.

[0160] The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application patent should be subject to the appended claims. The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application patent should be subject to the appended claims.

Claims

1. A collaborative inspection method for security robots based on task allocation optimization, characterized in that, The method includes: Acquire the partition structure information and airflow direction information of the partitioned hazardous chemical warehouse with safety buffer zone, determine the relative positional relationship of each inspection area of ​​the partitioned hazardous chemical warehouse on the gas propagation path, and identify the inspection area located upstream of the airflow and the inspection area located downstream of the airflow. At the same time, acquire the shared resource constraint information of each inspection area and the operation data of the security robot. Based on the relative positional relationship and the zoning structure of each inspection area, the sampling confidence of the effective sampling data obtained when performing sniffing inspection tasks in each inspection area is evaluated. When the sampling confidence of the inspection area located downstream of the airflow is lower than the preset threshold, the corresponding priority value adjustment amount is generated based on the deviation between the sampling confidence and the preset threshold. Based on the priority value adjustment amount, the inspection execution priority values ​​for the downstream inspection area and the upstream inspection area of ​​the airflow are adjusted accordingly to obtain the adjusted downstream inspection execution priority values ​​and upstream inspection execution priority values. Based on the shared resource constraint information of each inspection area, the current shared resource constraint level of the corresponding inspection area is determined, and the corresponding inhibition factor is selected from the preset inhibition factor set based on the shared resource constraint level. The downstream and upstream inspection execution priorities are adjusted based on the suppression factor, and the corresponding sniffing and inspection tasks are executed based on the final downstream and upstream inspection execution priorities obtained after the adjustment.

2. The collaborative inspection method for security robots based on task allocation optimization according to claim 1, characterized in that, Based on the relative positional relationships and the zoning structure of each inspection area, the sampling confidence of valid sampling data obtained when performing sniffing inspection tasks in each inspection area is evaluated. When the sampling confidence of the inspection area located downstream of the airflow is lower than a preset threshold, the steps for generating a corresponding priority adjustment amount based on the deviation between the sampling confidence and the preset threshold include: Based on the relative position of the inspection area on the gas propagation path, it can be determined whether the inspection area is located upstream or downstream of the airflow. Based on the partition structure attributes corresponding to the inspection area, the degree to which the sampling data is affected by gas accumulation when performing sniffing inspection tasks in the inspection area is evaluated, and the sampling confidence of the inspection area is determined accordingly. The sampling confidence level of the inspection area located downstream of the airflow is compared with a preset threshold, and the deviation magnitude of the sampling confidence level being lower than the preset threshold is calculated. Based on the deviation magnitude, a corresponding priority adjustment amount is generated through a preset mapping relationship. The larger the deviation magnitude, the larger the absolute value of the generated priority adjustment amount.

3. The collaborative inspection method for security robots based on task allocation optimization according to claim 1, characterized in that, The steps for adjusting the inspection execution priority values ​​for the downstream and upstream inspection areas based on the priority value adjustment amount include: Obtain the initial downstream inspection execution priority value for the downstream inspection area of ​​the airflow and the initial upstream inspection execution priority value for the upstream inspection area of ​​the airflow; Based on the priority value adjustment, the initial downstream inspection execution priority value is lowered and the initial upstream inspection execution priority value is raised, generating the adjusted downstream inspection execution priority value and the adjusted upstream inspection execution priority value. During the process of adjusting the priority value of inspection execution, preset upper and / or lower limit constraints are applied to the adjusted downstream inspection execution priority value and the adjusted upstream inspection execution priority value.

4. The collaborative inspection method for security robots based on task allocation optimization according to claim 1, characterized in that, The steps of determining the current shared resource constraint level of the corresponding inspection area based on the shared resource constraint information of each inspection area, and selecting the corresponding inhibition factor from the preset inhibition factor set based on the shared resource constraint level, include: Based on the shared resource constraint information of each inspection area, the shared resource constraint parameters of the corresponding inspection area are obtained. The shared resource constraint parameters include at least one of the following: the limit on the number of security robots allowed to enter the inspection area at the same time, the number of security robots currently entering the inspection area, and the time limit for entering or staying in the inspection area. Based on the shared resource constraint parameters, assess the degree of shared resource limitation in the inspection area at the current moment, and determine the current shared resource constraint level of the inspection area accordingly; Select the suppression factor corresponding to the current shared resource constraint level from the preset set of suppression factors.

5. The collaborative inspection method for security robots based on task allocation optimization according to claim 1, characterized in that, The steps for adjusting the downstream and upstream inspection execution priorities based on the suppression factor, and then executing the corresponding sniffing and inspection tasks based on the final adjusted downstream and upstream inspection execution priorities, include: The downstream inspection execution priority value and the upstream inspection execution priority value are corrected by the inhibition factor to obtain the final downstream inspection execution priority value and the final upstream inspection execution priority value. Based on the final downstream inspection execution priority value and the final upstream inspection execution priority value, the sniffing inspection tasks to be executed are sorted to form an inspection task execution sequence. Under the premise of satisfying the shared resource constraints, the sniffing inspection tasks are assigned to the corresponding security robots in sequence according to the inspection task execution sequence; The security robot is controlled to enter the corresponding inspection area in sequence and perform sniffing inspection tasks according to the inspection task execution sequence.

6. A collaborative inspection system for security robots based on task allocation optimization, characterized in that, The system includes: The structural airflow data module is used to acquire the partition structure information and airflow direction information of the partitioned hazardous chemical warehouse with safety buffer zone, determine the relative positional relationship of each inspection area of ​​the partitioned hazardous chemical warehouse on the gas propagation path, identify the inspection area located upstream of the airflow and the inspection area located downstream of the airflow, and acquire the shared resource constraint information of each inspection area and the operation data of the security robot. The priority value adjustment generation module is used to evaluate the sampling confidence of effective sampling data obtained when performing sniffing inspection tasks in each inspection area based on the relative position relationship and the partition structure of each inspection area. When the sampling confidence of the inspection area located downstream of the airflow is lower than the preset threshold, the corresponding priority value adjustment is generated based on the deviation between the sampling confidence and the preset threshold. The inspection execution priority value adjustment module is used to adjust the inspection execution priority value for the downstream inspection area and the upstream inspection area of ​​the airflow according to the priority value adjustment amount, so as to obtain the adjusted downstream inspection execution priority value and upstream inspection execution priority value. The inhibition factor selection module is used to determine the current shared resource constraint level of the corresponding inspection area based on the shared resource constraint information of each inspection area, and select the corresponding inhibition factor from the preset inhibition factor set based on the shared resource constraint level. The inspection task correction and execution module is used to correct the adjusted downstream inspection execution priority value and upstream inspection execution priority value according to the suppression factor, and execute the corresponding sniffing inspection task according to the final downstream inspection execution priority value and the final upstream inspection execution priority value obtained after correction.

7. A security robot collaborative inspection system based on task allocation optimization according to claim 6, characterized in that, The priority value adjustment generation module specifically includes: The relative position determination unit is used to determine whether the inspection area is located upstream or downstream of the airflow based on the relative position of the inspection area on the gas propagation path. The sampling confidence assessment unit is used to assess the degree to which the sampling data is affected by gas accumulation when performing sniffing and inspection tasks in the inspection area based on the partition structure attributes corresponding to the inspection area, and to determine the sampling confidence of the inspection area accordingly. The deviation amplitude calculation unit is used to compare the sampling confidence level of the inspection area located downstream of the airflow with a preset threshold and calculate the deviation amplitude when the sampling confidence level is lower than the preset threshold. The priority adjustment amount generation unit is used to generate a corresponding priority adjustment amount based on the deviation amplitude through a preset mapping relationship. The larger the deviation amplitude, the larger the absolute value of the generated priority adjustment amount.

8. A security robot collaborative inspection system based on task allocation optimization according to claim 6, characterized in that, The inspection execution priority adjustment module specifically includes: The initial priority value acquisition unit is used to acquire the initial downstream inspection execution priority value for the downstream inspection area of ​​the airflow and the initial upstream inspection execution priority value for the upstream inspection area of ​​the airflow. The priority value linkage adjustment unit is used to lower the initial downstream inspection execution priority value and raise the initial upstream inspection execution priority value based on the priority value adjustment amount, thereby generating the adjusted downstream inspection execution priority value and the adjusted upstream inspection execution priority value. The priority value constraint control unit is used to apply preset upper and / or lower limit constraints to the adjusted downstream and upstream inspection execution priority values ​​during the process of adjusting the inspection execution priority values.

9. A security robot collaborative inspection system based on task allocation optimization according to claim 6, characterized in that, The inhibitor selection module specifically includes: The shared resource constraint parameter acquisition unit is used to acquire the shared resource constraint parameters of the corresponding inspection area based on the shared resource constraint information of each inspection area. The shared resource constraint parameters include at least one of the following: the limit on the number of security robots allowed to enter the inspection area at the same time, the number of security robots currently entering the inspection area, and the time limit for entering or staying in the inspection area. The shared resource constraint level determination unit is used to assess the degree of shared resource limitation in the inspection area at the current moment based on the shared resource constraint parameters, and determine the current shared resource constraint level of the inspection area accordingly. The suppression factor selection unit is used to select a suppression factor from a preset set of suppression factors that corresponds to the current shared resource constraint level.

10. A security robot collaborative inspection system based on task allocation optimization according to claim 6, characterized in that, The inspection task correction and execution module specifically includes: The execution priority value correction unit is used to correct the adjusted downstream inspection execution priority value and upstream inspection execution priority value respectively through the suppression factor to obtain the final downstream inspection execution priority value and the final upstream inspection execution priority value. The inspection task sorting unit is used to sort the sniffing inspection tasks to be executed according to the final downstream inspection execution priority value and the final upstream inspection execution priority value, forming an inspection task execution sequence; The inspection task allocation unit is used to allocate sniffing inspection tasks to the corresponding security robots in sequence according to the inspection task execution sequence, provided that the shared resource constraint information is satisfied. The inspection task execution control unit is used to control the security robot to enter the corresponding inspection area in sequence and perform sniffing inspection tasks according to the inspection task execution sequence.

Images