Rescue vehicle dynamic path optimization method and system based on improved rolling time domain

Abstract

The invention provides a rescue vehicle dynamic path optimization method based on an improved rolling time domain. The method comprises the following steps: carrying out real-time statistics on rescue node information in the operation time of a rescue distribution center; determining a target function according to the obtained node number and the coordinate information of the nodes, and constraining and initializing algorithm parameters; wherein the objective function is the minimum value of the sum of the vehicle transportation cost, the total delay of the start service time of the node with the time window exceeding the right time window and the number of the node transportation time exceeding the specified time limit; dividing the operation time of the rescue distribution center into a plurality of time domains, and obtaining an optimal path and optimization cost by real-time rescue node information in each time domain through a simulated annealing algorithm; and calculating the total time length cost, and summarizing the optimal path of the total time domain time length. According to the method, the response speed of the rescue vehicle can be increased, the delay of the rescue vehicle is reduced, meanwhile, prediction errors can be corrected through continuously rolling windows, and the robustness of the path is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicles, and particularly to a method and system for dynamically optimizing the path of a rescue vehicle based on an improved rolling horizon. Background Art

[0003] Traditional static scheduling, which relies on a previously established fixed route, cannot make adjustments to emergencies, thus increasing the detour cost. Compared with traditional static planning, dynamic scheduling has better factuality and flexibility, and can quickly adjust the path plan based on real-time node change information, thereby reducing the delay cost.

[0004] Currently, for the dynamic vehicle routing problem, there are mainly three solution ideas: The first is to predict nodes based on historical data and treat the predicted nodes as known nodes. This method requires a large amount of historical data for prediction, and the processing and storage of data require a large amount of resources and data, which is difficult to operate in actual problem-solving. The second is a global optimization method driven by a single event, that is, a global optimization is performed every time a new node appears, so as to take all nodes into account. However, this method has the disadvantage of high computational resource consumption when nodes appear frequently. The third is the rolling horizon method, that is, the entire optimization period is divided into multiple time horizons, and each time horizon is optimized as a static scenario. For a fixed time horizon length, when nodes are relatively scattered, the number of computational nodes in each time horizon is small, resulting in a low vehicle service rate and increasing the path cost of the rescue vehicle from the distribution center. Summary of the Invention

[0005] Aiming at the deficiencies in the prior art, the present invention provides a method and system for dynamically optimizing the path of a rescue vehicle based on an improved rolling horizon. The leading improvement in the running time of the algorithm speeds up the response speed of the rescue vehicle and reduces the delay of the rescue vehicle. At the same time, the continuously rolling window can correct the prediction error and improve the robustness of the path.

[0006] The present invention achieves the above technical objectives through the following technical means.

[0007] A method for dynamically optimizing the path of a rescue vehicle based on an improved rolling horizon includes the following steps:

[0008] S01: Real-time statistics of rescue node information during the operation time of the rescue distribution center, including node appearance time, node coordinates, node material demand, node service time, node left time window, and node right time window;

[0009] S02: Determine the objective function, constraint function, and initialization algorithm parameters based on the obtained number of nodes and the coordinate information of the nodes; wherein, the objective function is the minimum value of the sum of the vehicle transportation cost, the total delay when the start service time of the nodes with time windows exceeds the right time window, and the number representing the number of nodes whose delivery time exceeds the specified time limit.

[0010] S03: Divide the operation time of the rescue distribution center into several time domains, and obtain the optimal path and optimization cost for the real-time rescue node information in each time domain through the simulated annealing algorithm.

[0011] S04: Calculate the total duration cost TOTF and summarize the optimal paths for the total time domain duration.

[0012] Furthermore, the objective function is expressed as:

[0013] minF = F1 + F2 + F3

[0014] Where: F1 represents the total transportation cost of the vehicle, expressed as:

[0015]

[0016] F2 represents the total delay penalty when the start service time of the nodes with time windows exceeds the right time window, and the formula is expressed as:

[0017]

[0018] F3 represents the number penalty when the delivery time of the nodes exceeds the specified time limit, and the formula is expressed as:

[0019]

[0020] In the formula, N represents the node set, N = {1, 2,..., n}, 0 represents the distribution center; K represents the rescue vehicle set; d ij represents the distance of the section from node i to j; C represents the transportation cost per unit distance of the rescue vehicle; M1 represents the penalty factor for the total delay when the start service time of the nodes with time windows exceeds the right time window; M2 represents the penalty factor for the number of nodes whose delivery time exceeds the specified time limit; LT i represents the right time window of node i; w ij represents a 0-1 variable, reflecting whether the rescue vehicle delays the time window, 1 if yes, 0 if no; n i represents the time point when the rescue vehicle arrives at node i.

[0021] Further, the constraint function is that the total task borne by each vehicle does not exceed the load limit of the vehicle, each demand point is visited at least once, the rescue vehicle must finally return to the distribution center, the rescue vehicle must start from the distribution center, and there is no loop at the same node.

[0022] Further, the real-time rescue node information in each time domain is used to obtain the optimal path and optimization cost through the simulated annealing algorithm, which specifically includes the following steps:

[0023] S3.1: Set the basic rolling duration TT of the current time domain length, set the current time t as the end time of the previous time domain, if it is the first time domain, set the current time t as 0, the minimum time domain length MINTT = 30, the maximum time domain length MAXTT = 180, and judge whether the current time t is less than the total rolling duration AT. If yes, go to S3.2; otherwise, end the process.

[0024] S3.2: Use the basic rolling duration TT to determine the number of nodes FNUM in the current time domain length.

[0025] S3.3: Judge whether the number of nodes FNUM in the current time domain length is greater than the set node number threshold SNUM. If yes, go to S3.4; otherwise, go to S3.5.

[0026] S3.4: Adjust the current time domain length STT to max(TT * (SNUM / FNUM), MINTT), and go to S3.6.

[0027] S3.5: Adjust the current time domain length STT to min(TT * 2, MAXTT), and go to S3.6.

[0028] S3.6: Re-obtain the node information in the current time domain length according to the current time domain length STT.

[0029] S3.7: Judge whether the current time domain is the first time domain. If yes, go to 3.11; otherwise, go to S3.8.

[0030] S3.8: Calculate the distance between each node in the current time domain and the last node of each optimized path in the previous time domain.

[0031] S3.9: Insert each node in the current time domain after the node with the closest distance among the last nodes of each optimized path in the previous time domain.

[0032] S03.10: Judge whether the insertion violates the constraint for each node in the current time domain. If yes, cancel the insertion and keep it as the node in the current time domain.

[0033] S03.11: Confirm the number of nodes in the current time domain and obtain the node information.

[0034] S03.12: The current time-domain node information is processed by the simulated annealing algorithm to obtain the current optimal time-domain path and the optimal cost F;

[0035] S03.13: Update the vehicle state;

[0036] S03.14: The current time t = the current time t + the current time-domain length STT.

[0037] A rescue vehicle path planning system includes a processor and a memory. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the improved rolling time-domain based rescue vehicle dynamic path optimization method as described are run.

[0038] The beneficial effects of the present invention are as follows:

[0039] 1. For the improved rolling time-domain based rescue vehicle dynamic path optimization method of the present invention, from the perspective of emergency rescue, the leading improvement in the running time of the algorithm speeds up the response speed of the rescue vehicle and reduces the delay of the rescue vehicle. At the same time, the continuously rolling window can correct the prediction error and improve the robustness of the path.

[0040] 2. For the improved rolling time-domain based rescue vehicle dynamic path optimization method of the present invention, from the perspective of traffic optimization, the total rescue path becomes shorter, resulting in a lower rescue cost, and improving the economic efficiency during the rescue process without sacrificing the interests of the demand points.

[0041] 3. For the improved rolling time-domain based rescue vehicle dynamic path optimization method of the present invention, from the perspective of social safety, the improved rolling time-domain algorithm makes the domestic rescue vehicle scheduling method more reasonable, enabling the public to obtain rescue faster in case of emergencies, reducing the economic losses of the public, and being more conducive to social harmony and stability. Description of the Drawings

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. The following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained obviously without creative efforts based on these drawings.

[0043] Figure 1 It is a flowchart of the improved rolling time-domain based rescue vehicle dynamic path optimization method of the present invention.

[0044] Figure 2 It is a node position map of c107 in the Solomon dataset in the embodiment.

[0045] Figure 3It is the optimized path diagram of the first time domain of the embodiment. Detailed implementation manners

[0046] The embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0047] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "axial", "radial", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0048] In the present invention, unless otherwise clearly defined and limited, the terms "mounted", "connected", "connected", "fixed", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0049] As Figure 1 shown, the method for dynamically optimizing the path of a rescue vehicle based on an improved rolling time domain according to the present invention includes the following steps:

[0050] S01: Real-time statistically count the rescue node information during the operation time of the rescue distribution center, including the node appearance time, node coordinates, node material demand, node service time, node left time window, and node right time window;

[0051] S02: Determine the objective function, constraint function, and initialization algorithm parameters based on the obtained number of nodes and the coordinate information of the nodes. Among them, the objective function is the minimum value of the sum of the vehicle transportation cost, the total delay when the start service time of the nodes with time windows exceeds the right time window, and the number representing the number of nodes whose transportation time exceeds the specified time limit. The objective function is expressed as:

[0052] minF = F1 + F2 + F3

[0053] Among them: F1 represents the total transportation cost of the vehicle, expressed as:

[0054]

[0055] F2 represents the total delay penalty when the start service time of the nodes with time windows exceeds the right time window, and the formula is expressed as:

[0056]

[0057] F3 represents the number penalty when the transportation time of the nodes exceeds the specified time limit, and the formula is expressed as:

[0058]

[0059] In the formula, N represents the node set, N = {1, 2,..., n}, 0 represents the distribution center; K represents the rescue vehicle set; d ij represents the distance of the section from node i to j; C represents the transportation cost per unit distance of the rescue vehicle; M1 represents the penalty factor for the total delay when the start service time of the nodes with time windows exceeds the right time window; M2 represents the penalty factor for the number of nodes whose transportation time exceeds the specified time limit; LT i represents the right time window of node i; w ij represents a 0 - 1 variable, reflecting whether the rescue vehicle delays the time window, 1 if yes, 0 if no; n i represents the time point when the rescue vehicle arrives at node i.

[0060] The constraint function is that the total task undertaken by each vehicle does not exceed the load capacity limit of the vehicle, each demand point is visited at least once, the rescue vehicle must finally return to the distribution center, the rescue vehicle must start from the distribution center, and there is no loop at the same node.

[0061] S03: Divide the operation time of the rescue distribution center into several time domains, and the optimal path and optimization cost of the real - time rescue node information in each time domain are obtained through the simulated annealing algorithm. Specifically:

[0062] S3.1: Set the current time domain length base rolling duration TT, set the current time t to the end time of the previous time domain. If it is the first time domain, set the current time t to 0. The minimum time domain length MINTT = 30, the maximum time domain length MAXTT = 180. Determine whether the current time t is less than the total rolling duration AT. If yes, go to S3.2; otherwise, end the process.

[0063] S3.2: Use the base rolling duration TT to determine the number of nodes FNUM in the current time domain length.

[0064] S3.3: Determine whether the number of nodes FNUM in the current time domain length is greater than the set node number threshold SNUM. If yes, go to S3.4; otherwise, go to S3.5.

[0065] S3.4: Adjust the current time domain length STT to max(TT*(SNUM / FNUM), MINTT), and go to S3.6.

[0066] S3.5: Adjust the current time domain length STT to min(TT*2, MAXTT), and go to S3.6.

[0067] S3.6: Re - obtain the node information in the current time domain length according to the current time domain length STT; that is, replace the set current time domain length base rolling duration TT with STT, re - obtain the node information in the current time domain length, and the number of nodes re - obtained may increase or decrease.

[0068] S3.7: Determine whether the current time domain is the first time domain. If yes, go to 3.11; otherwise, go to S3.8.

[0069] S3.8: Calculate the distance between each node in the current time domain and the last node of each optimized path in the previous time domain.

[0070] S3.9: Insert each node in the current time domain after the node with the closest distance among the last nodes of each optimized path in the previous time domain.

[0071] S03.10: Determine whether the insertion violates the constraints for each node in the current time domain. If yes, cancel the insertion and keep it as a node in the current time domain.

[0072] S03.11: Confirm the number of nodes in the current time domain and obtain the node information.

[0073] S03.12: Import the current time domain node information into the simulated annealing algorithm to obtain the optimal path and optimal cost F in the current time domain.

[0074] S03.13: Update the vehicle state.

[0075] S03.14: Current time t = Current time t + Current time domain length STT;

[0076] S04: Calculate the total duration cost TOTF and summarize the optimal path of the total time domain duration.

[0077] Embodiment

[0078] The following takes c107 in the Solomon dataset as an example for further illustration:

[0079] Since the Solomon dataset is a static dataset, the node appearance time is added on this basis, and the right time window of the demand point is appropriately modified. There are 100 nodes in c107 excluding the distribution center. The specific node plane distribution is as Figure 2 shown, and part of the node information is shown in Table 1. Among them, the time window of the distribution center is [0, 1236]. Let the rolling total duration be 1300, the time domain length (basic time domain length) TT be 100, the vehicle unit distance transportation cost C be 100, the vehicle running speed be 1, the maximum load be 200, the penalty factor M1 for the total delay when the start service time of the node with a time window exceeds the right time window be 1000, the penalty factor M2 for the number of nodes whose transportation time exceeds the specified time limit be 1000, and the node quantity threshold SNUM be 15.

[0080] Since c107 after modification already includes parameters such as node appearance time, node coordinates, node material demand, node service time, node left time window, and node right time window, the specific steps of S03 are described below.

[0081] Next, a specific description is made for the second time domain. It is known that the first time domain interval is (0, 52), as Figure 3 shown, and the simulated annealing optimization path of the first time domain is as follows:

[0082] 0 → 32 → 33 → 24 → 20 → 0

[0083] 0 → 67 → 65 → 81 → 78 → 0

[0084] 0 → 90 → 87 → 96 → 98 → 0

[0085] 0 → 55 → 57 → 42 → 43 → 0

[0086] 0 → 5 → 3 → 13 → 17 → 0

[0087] S3.1: Set the basic rolling duration TT of the current time domain length to 100, set the current time as t = 52, the minimum time domain length MINTT = 30, the maximum time domain length MAXTT = 180, and the current time t = 52 is less than the rolling total duration AT = 1300 (round up to the nearest 100 integer for the right time window of the distribution center);

[0088] S3.2: Determine the number of nodes FNUM in the current time domain length using the basic rolling duration TT; when the basic time domain length TT is 100, the prediction interval is (53, 153), and the number of predicted nodes FNUM entering it is 11.

[0089] S3.3: If the number of nodes FNUM in the current time domain length is less than the set node number threshold SNUM, then go to S3.5;

[0090] S3.5: Adjust the current time domain length STT to min(TT * 2, MAXTT), that is, the second time domain length STT = min(TT * 2, MAXTT) = min(100 * 2, 180) = 180, so adjust the second time domain length STT to 180;

[0091] S3.6: Re - obtain the number of nodes in the current time domain length according to the current time domain length STT, which is 20;

[0092] S3.7: If the current time domain is not the first time domain, go to 3.8;

[0093] S3.8: Calculate the distance between each node in the current time domain and the last node of each optimized path in the previous time domain;

[0094] S3.9: Insert each node in the current time domain after the node with the closest distance among the last nodes of each optimized path in the previous time domain;

[0095] S03.10: For each node in the current time domain, judge whether it violates the constraint after insertion. If so, cancel the insertion and keep it as a node in the current time domain;

[0096] Taking the first node in the second time domain as an example, the number of the first node is 7, and the coordinates are (40, 66). The numbers of the last nodes of each optimized path in the previous time domain are 20, 78, 98, 43, and 17 respectively; calculate the distances between the 7th node and the 20th, 78th, 98th, 43rd, and 17th nodes. After calculation, the distances are 19, 57, 20, 31, and 24 respectively; it can be seen that the 7th node is the closest to the 20th node, so insert the 7th node after the 20th node, and then judge whether it violates the constraint. The time point when the vehicle leaves the 20th node is the 480th minute, calculate the time point when the vehicle arrives at the 7th node is 480 + 19 = 499 minutes, and the time window of the 7th node is (108, 288). Since the time point of arriving at the 7th node is not within its time window, the insertion is cancelled. Similarly, calculate the load constraint. After the vehicle serves the 20th node, the cumulative node demand is 90, and after adding the demand of the 7th node, which is 20, it is 110, less than the maximum load of the vehicle, which is 200, and does not violate the load constraint.

[0097] Taking all constraints into consideration, one time window constraint is violated, so the insertion operation of node 7 is cancelled and node 7 is retained in the second time domain.

[0098] S03.11: Confirm the number of nodes in the current time domain and obtain node information;

[0099] S03.12: After all insertion nodes in the second time domain are judged, import the remaining node information in the second time domain into the simulated annealing algorithm to obtain the optimal path and optimal cost F in the second time domain;

[0100] S03.13: Update the vehicle state;

[0101] S03.14: Current time t = current time t + current time domain length STT = 52 + 180 = 232.

[0102] Enter the next time domain. After all time domain optimizations are completed, calculate the total duration cost TOTF and summarize the optimal path of the total time domain duration.

[0103] Table 1 Partial c107 node information

[0104] Number X Coordinate Y Coordinate Demand Left Time Window Right Time Window Service Time Occurrence Time 0 40 50 0 0 1236 0 0 3 42 66 10 16 486 90 0 5 42 65 10 15 339 90 0 7 40 66 20 108 288 90 67 13 22 75 30 30 598 90 0 17 18 75 20 34 414 90 0 20 30 50 10 10 789 90 0 24 25 50 10 15 592 90 0 32 10 40 30 31 766 90 0 33 8 40 40 33 473 90 0 42 33 32 20 19 659 90 0 43 33 35 10 16 676 90 0 55 42 15 10 37 217 90 5 57 40 15 40 35 677 90 0 65 48 40 10 13 513 90 0 67 47 40 10 12 499 90 0 78 88 35 20 50 398 90 0 81 85 35 30 47 888 90 0 87 65 55 20 25 405 90 0 90 60 55 10 20 479 90 0 96 60 80 10 36 702 90 0 98 58 75 20 30 470 90 0

[0105] When the basic time domain length is 100, the experimental results are shown in Table 2. It can be seen that under the same number of vehicle uses, the improved rolling time domain algorithm is 15% less in optimal cost and 30% less in running time than the standard rolling time domain algorithm, which has a certain optimization significance.

[0106] Table 2 c107 experimental results 100

[0107] Algorithm Number of Vehicles Used Optimal Cost Running Time (s) Standard Rolling Horizon 39 329399.9135 362.584281 Improved Rolling Horizon 39 279947.6331 253.489274

[0108] To sum up, the improved rolling time domain algorithm of the present invention is superior to the standard rolling time domain algorithm in terms of total cost and running time. After an actual emergency occurs, it can reduce the cost of rescue vehicles, reduce the delay of rescue vehicles, and at the same time, the continuously rolling window can correct prediction errors, improve the stability of the path, and make the distribution resources of rescue supplies be utilized more efficiently.

[0109] A rescue vehicle path planning system includes a processor and a memory. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the above-mentioned rescue vehicle dynamic path optimization method based on the improved rolling time domain are run.

[0110] It should be understood that although this specification is described according to various embodiments, not every embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0111] The series of detailed descriptions listed above are only specific descriptions of the feasible embodiments of the present invention, and they are not intended to limit the protection scope of the present invention. Any equivalent embodiments or changes made without departing from the technical spirit of the present invention should be included within the protection scope of the present invention.

Claims

1. A dynamic path optimization method for rescue vehicles based on improved rolling horizon, characterized in that It includes the following steps: S01: Real-time statistics of rescue node information during the operation time of the rescue distribution center, including node appearance time, node coordinates, node material demand, node service time, node left time window, and node right time window; S02: Determine the objective function, constraints, and initialize algorithm parameters based on the obtained number of nodes and node coordinate information; among them, the objective function is the minimum value of the sum of vehicle transportation costs, the total delay when the start service time of time-windowed nodes exceeds the right time window, and the number representing the number of nodes whose delivery time exceeds the specified time limit; S03: Divide the operation time of the rescue distribution center into several time domains, and obtain the optimal path and optimized cost for the real-time rescue node information in each time domain through the simulated annealing algorithm; S04: Calculate the total duration cost TOTF and summarize the optimal path of the total time domain duration.

2. The dynamic path optimization method for rescue vehicles based on improved rolling horizon according to claim 1, characterized in that The objective function is expressed as: minF = F1 + F2 + F3 Where: F1 represents the total transportation cost of the vehicle, expressed as: F2 represents the total delay penalty when the start service time of time-windowed nodes exceeds the right time window, and the formula is expressed as: F3 represents the number penalty when the node delivery time exceeds the specified time limit, and the formula is expressed as: In the formula, N represents the set of nodes, N = {1, 2, ..., n}, and 0 represents the distribution center; K represents the set of rescue vehicles; d ij represents the distance between node i and section j; C represents the transportation cost per unit distance of the rescue vehicle; M1 represents the penalty factor for the total delay when the start service time of the node with a time window exceeds the right time window; M2 represents the penalty factor for the number of nodes whose transportation time exceeds the specified time limit; LT i represents the right time window of node i; w ij represents a 0-1 variable, reflecting whether the rescue vehicle delays the time window, being 1 if yes and 0 if no; n i represents the time point when the rescue vehicle arrives at node i.

3. The dynamic path optimization method for rescue vehicles based on improved rolling horizon according to claim 1, wherein The constraint function is that the total task undertaken by each vehicle does not exceed the load limit of the vehicle, each demand point is visited at least once, the rescue vehicle must finally return to the distribution center, the rescue vehicle must depart from the distribution center, and there is no loop for the same node.

4. The dynamic path optimization method for rescue vehicles based on improved rolling horizon according to claim 1, characterized in that The optimal path and optimized cost for the real-time rescue node information in each time domain are obtained through the simulated annealing algorithm, which specifically includes the following steps: S3.1: Set the current time domain length base rolling duration TT, set the current time t as the end time of the previous time domain. If it is the first time domain, set the current time t as 0. The minimum time domain length MINTT = 30, the maximum time domain length MAXTT = 180. Determine whether the current time t is less than the rolling total duration AT. If yes, go to S3.2; otherwise, end the process; S3.2: Use the base rolling duration TT to determine the number of nodes FNUM in the current time domain length; S3.3: Determine whether the number of nodes FNUM in the current time domain length is greater than the set node number threshold SNUM. If yes, go to S3.4; otherwise, go to S3.5; S3.4: Adjust the current time domain length STT to max(TT * (SNUM / FNUM), MINTT), and go to S3.6; S3.5: Adjust the current time domain length STT to min(TT * 2, MAXTT), and go to S3.6; S3.6: Re-obtain the node information in the current time domain length according to the current time domain length STT; S3.7: Determine whether the current time domain is the first time domain. If yes, go to 3.11; otherwise, go to S3.8; S3.8: Calculate the distance between each node in the current time domain and the last node of each optimized path in the previous time domain; S3.9: Insert each node in the current time domain after the node with the closest distance among the last nodes of each optimized path in the previous time domain; S03.10: Determine whether the insertion violates the constraints for each node in the current time domain. If so, cancel the insertion and retain it as the node in the current time domain; S03.11: Confirm the number of nodes in the current time domain and obtain the node information; S03.12: Through the simulated annealing algorithm for the node information in the current time domain, obtain the optimal path and the optimal cost F in the current time domain; S03.13: Update the vehicle state; S03.14: Current time t = current time t + current time domain length STT.

5. A rescue vehicle path planning system, characterized in that, It includes a processor and a memory. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the dynamic path optimization method for rescue vehicles based on the improved rolling time domain as described in any one of claims 1-4 are run.

Images