A path planning method based on road traffic conditions

Abstract

A path planning method based on road traffic conditions, by giving a starting node S and a destination node E, a two-dimensional plane directed graph is drawn, and traffic lights at each intersection in the route are used as nodes, and the corresponding coordinates of each in the two-dimensional coordinate axis are obtained, and the length between each node is calculated and the number of vehicles queued between each node is obtained, and then the path is planned based on the road traffic conditions according to the improved A* algorithm. The planning path of the present invention not only considers the road congestion while considering the distance, but also adds a search angle threshold, and can adjust the proportion of influencing factors and the size of the search angle threshold according to the road congestion.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning in intelligent transportation, and in particular to a path planning method based on road traffic conditions. Background Art

[0002] In the navigation device of the prior art, when exploring a path, the road data stored in the navigation map data is used, and the total weight of the path from the departure point to any location is calculated based on the real-time road traffic information and the road attributes and intersection attributes from the current location to any location. Then, when all the weight calculations to the destination are completed, the path with the smallest total weight is connected as the best path from the current location to the destination.

[0003] When selecting the best path, some existing navigation technologies only consider the distance between the starting point and the destination, the number of traffic lights, and do not comprehensively consider other factors, such as road traffic volume, road conditions, etc., resulting in the selected path being short, but sometimes encountering special time points, there will be traffic jams and delays; it is of little practical significance. Currently, the most widely used path-finding method is the heuristic algorithm A* algorithm, but the traditional A* algorithm also only considers the distance of the journey, without considering other influencing factors.

[0004] Although some existing navigation technologies have taken the impact of traffic flow into consideration, the technology is still not very mature and has not considered adding changes in the search angle to the algorithm. As a result, serious detours often occur in order to avoid traffic flow. Summary of the invention

[0005] In response to the above-mentioned technical problems, the present technical solution provides a path planning method based on road traffic conditions, which not only takes into account the road congestion, but also adds a search angle threshold. It can adjust the proportion of influencing factors and the size of the search angle threshold according to the road congestion; it can effectively solve the above-mentioned problems.

[0006] The present invention is achieved through the following technical solutions:

[0007] A path planning method based on road traffic conditions, by giving the starting node S and the destination node E, calculates the length between each node and obtains the number of vehicles queuing between each node, and then plans the path based on the road traffic conditions according to the improved A* algorithm; the specific operation method is:

[0008] S1: Get the starting node S and the destination node E of the path to be planned, draw a two-dimensional plane directed graph, take the traffic lights at each intersection in the route as the intermediate nodes, and get the corresponding coordinates of the starting node S, the destination node E and each intermediate node in the two-dimensional coordinate axis;

[0009] S2: According to the coordinates of each starting node S, destination node E and each intermediate node, calculate the distance of each corresponding road section, and obtain the vehicles queued at the traffic lights on each road section;

[0010] S3: Based on the known starting node and target node, the improved A* algorithm is used to plan the path.

[0011] Furthermore, the improved A* algorithm is an improvement on the evaluation function. The evaluation function of the original A* algorithm is:

[0012] F(n)=G(n)+H(n);

[0013] G(n) is the distance from the current n nodes to the starting node, and H(n) is the distance from the current n nodes to the target node;

[0014] The improved valuation function is:

[0015] F1(n)=G1(n)+H(n);

[0016] G1(n)=ω1G(n)+ω2P(i);

[0017] ω1+ω2=1;

[0018] P(i) is the number of vehicles queuing at the traffic light with the number i corresponding to the previous parent node to the current child node n. When selecting nodes, the length of the route is considered as well as the traffic flow. The road congestion factor is added to the original valuation function. The value of ω2 is determined by the road traffic flow and is accurate to two decimal places. According to data monitoring, the average number of vehicles queuing in the previous 30 days is obtained, and its average value is μ. av , the average value of road vehicles at the current moment is μ P(k) , the current road congestion level is:

[0019]

[0020] The formula for determining the value of ω2 is:

[0021]

[0022] Among them, the coordinates of the ath node are (Xa, Ya), the coordinates of the bth node are (Xb, Yb), and the length S(i) of the road section numbered i consisting of the ath node and the bth node is:

[0023]

[0024] Since the magnitudes of G(n), H(n), and P(i) are different, they need to be processed to eliminate the influence of their different magnitudes. The planned route has n nodes and k sections, and the length of the i-th section is S(i); then the average length of the k sections is μ S(k) for:

[0025]

[0026] μ H(n) is the average distance from all nodes to the destination node, μ P(k) ' is the average number of vehicles in the queues on all road sections between nodes, then:

[0027]

[0028] The magnitudes of G(n), H(n), and P(i) are different. After processing, the improved G * (n), H * (n), P * (i) is:

[0029]

[0030] Get the final improved evaluation function:

[0031] F1 * (n) = G1 * (n)+H * (n),

[0032] G1 * (n) = ω1G * (n)+ω2P * (i).

[0033] Furthermore, the specific steps of obtaining the path planning based on the road traffic conditions by improving the A* algorithm are:

[0034] Step 1: Determine the coordinates of each node on the two-dimensional coordinate axis and determine the coordinates of the starting node (X st , Y st ), target node coordinates (X end , Y end );

[0035] Step 2: Initialize an OPEN_LIST list and a CLOSE_LIST list, put the starting node into the OPEN_LIST list, and clear the CLOSE_LIST list;

[0036] Step 3: Determine whether the current OPEN_LIST list has a target node. If so, go to step 6;

[0037] If there is no target node, select the cost function F1 in the current OPEN_LIST list * The node with the smallest (n) value is used as the current node n whose neighbor node is to be expanded, and it is deleted from the OPEN_LIST list and placed in the CLOSE_LIST list;

[0038] Step 4: Check the angle K formed by each extended neighbor node, the starting node, and the target node i , determine whether the angle is greater than the angle threshold K d , when the angle is greater than the angle threshold, the neighboring node, the starting node and the target node are put into the OPEN_LIST list; when the angle is less than the angle threshold, the neighboring node, the starting node and the target node are put into the CLOSE_LIST list;

[0039] If there is an adjacent node c in the expanded adjacent nodes that is already in the OPEN_LIST list, calculate the new path from the starting node to the node c G1 * (n); Determine whether an update is needed: mainly determine whether the new G1 * (n) whether it is lower;

[0040] If the new G1 * (n) is lower, then change the parent node to a and recalculate the new F1 * (n) value, H * The value of (n) does not need to change, and the estimated consumption from node c to destination node E is fixed;

[0041] If the new G1 * (n) If it is higher, it means that the new path has higher consumption and no change is needed;

[0042] Step 5: Continue to find the valuation function F1 from the OPEN_LIST list * (n) The node with the smallest value is deleted from the OPEN_LIST list and added to the CLOSE_LIST list, and then returns to step 3;

[0043] Step 6: After adding the nodes in the CLOSE_LIST list, trace back according to the parent-child relationship to obtain the planned path from the starting node S to the destination node E.

[0044] Furthermore, the angle K described in step 4 i , where the coordinates of the neighboring nodes are (X i ,Y i ), the starting node coordinates are (X st ,Y st ), the target node coordinates are (X end ,Y end), then the angle K between the neighboring node, the starting node and the target node i The calculation formula is:

[0045]

[0046] Get the angle K i After the value of i Is it greater than the angle threshold K? d , avoid taking detours in pursuit of smooth roads.

[0047] Furthermore, the angle threshold K d Affected by the road congestion level Ω, when the road is too congested, the angle threshold K is appropriately lowered d When the road is relatively idle, the angle threshold K is appropriately increased. d When Ω<-1, K d =120°, when -1≤Ω≤1, K d =-30Ω+90°When Ω>1, K d =60°.

[0048] Beneficial Effects

[0049] Compared with the prior art, the path planning method based on road traffic conditions proposed in the present invention has the following beneficial effects:

[0050] (1) In the path planning of the present invention, when checking each extended neighboring node, an angle threshold K is added d , according to the road congestion, adjust the angle threshold K d When the road is congested, the angle threshold K is reduced. d , expand the search range, and increase the angle threshold K when the road is not congested d , improve the algorithm search efficiency, increase the timeliness of path planning, and shorten the time users wait for path planning.

[0051] (2) This solution starts with improving the evaluation function of the A* algorithm and adding the factor of traffic flow. Through the variable linear weights ω1 and ω2, the appropriate weights can be adjusted according to the traffic conditions at the time, the path length and the proportion of road congestion can be adjusted, and a better route can be selected. A variable angle threshold judgment is added to improve the overall performance of the algorithm and make it more suitable for application in actual scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a specific flow chart of the overall method in the present invention.

[0053] Figure 2 It is a schematic diagram of the two-dimensional plane coordinate axes of the road section in the implementation case of the present invention.

[0054] Figure 3 It is a schematic diagram of a path planning route in an implementation case of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. The described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Under the premise of not departing from the design concept of the present invention, various modifications and improvements made by ordinary persons in the art to the technical solutions of the present invention should all fall within the protection scope of the present invention.

[0056] Embodiment 1:

[0057] like Figure 1 As shown in the figure, a path planning method based on road traffic conditions is used. By giving the starting node S and the destination node E, the length between each node is calculated and the number of vehicles queuing between each node is obtained. Then, the path is planned based on the road traffic conditions according to the improved A* algorithm. The specific operation method is as follows:

[0058] S1: Get the starting node S and the destination node E of the path to be planned, draw a two-dimensional plane directed graph, take the traffic lights at each intersection in the route as the intermediate nodes, and get the corresponding coordinates of the starting node S, the destination node E and each intermediate node in the two-dimensional coordinate axis;

[0059] S2: According to the coordinates of each starting node S, destination node E and each intermediate node, calculate the distance of each corresponding road section, and obtain the vehicles queued at the traffic lights on each road section;

[0060] S3: Based on the known starting node and target node, the improved A* algorithm is used to plan the path. The improved A* algorithm is an improvement on the evaluation function. The evaluation function of the original A* algorithm is:

[0061] F(n)=G(n)+H(n);

[0062] G(n) is the distance from the current n nodes to the starting node, and H(n) is the distance from the current n nodes to the target node;

[0063] The improved valuation function is:

[0064] F1(n)=G1(n)+H(n);

[0065] G1(n)=ω1G(n)+ω2P(i);

[0066] ω1+ω2=1;

[0067] P(i) is the number of vehicles queued at the traffic light on the road section numbered i from the previous parent node to the current child node n. When selecting the node, the road traffic conditions are taken into consideration not only the length of the route, but also the road congestion level as an influencing factor on the basis of the original valuation function.

[0068] The value of ω2 is determined by the road traffic volume, accurate to two decimal places; according to data monitoring, the average number of queued vehicles in the previous 30 days is obtained, and its average value is μ av , the average value of road vehicles at the current moment is μ P(k) , the current road congestion level is:

[0069]

[0070] The formula for determining the value of ω2 is:

[0071]

[0072] Among them, the coordinates of the ath node are (Xa, Ya), the coordinates of the bth node are (Xb, Yb), and the length S(i) of the road section numbered i consisting of the ath node and the bth node is:

[0073]

[0074] Since the magnitudes of G(n), H(n), and P(i) are different, they need to be processed to eliminate the influence of their different magnitudes. The planned route has n nodes and k sections, and the length of the i-th section is S(i); then the average length of the k sections is μ S(k) for:

[0075]

[0076] μ H(n) is the average distance from all nodes to the destination node, μ P(k) ' is the average number of vehicles in the queues on all road sections between nodes, then:

[0077]

[0078] The magnitudes of G(n), H(n), and P(i) are different. After processing, the improved G * (n), H * (n), P * (i) is:

[0079]

[0080] Get the final improved evaluation function:

[0081] F1 *(n) = G1 * (n)+H * (n),

[0082] G1 * (n) = ω1G * (n)+ω2P * (i).

[0083] The specific steps of obtaining path planning based on road traffic conditions by improving the A* algorithm are as follows:

[0084] Step 1: Determine the coordinates of each node on the two-dimensional coordinate axis and determine the coordinates of the starting node (X st , Y st ), target node coordinates (X end , Y end ).

[0085] Step 2: Initialize an OPEN_LIST list and a CLOSE_LIST list, put the starting node into the OPEN_LIST list, and clear the CLOSE_LIST list.

[0086] Step 3: Determine whether there is a target node in the current OPEN_LIST list. If there is a target node, go to step 6.

[0087] If there is no target node, select the cost function F1 in the current OPEN_LIST list * The node with the smallest (n) value is used as the current node n whose neighboring node is to be expanded, and it is deleted from the OPEN_LIST list and placed in the CLOSE_LIST list.

[0088] Step 4: Check the angle K formed by each extended neighbor node, the starting node, and the target node i , determine whether the angle is greater than the angle threshold K d When the angle is greater than the angle threshold, the neighboring node, the starting node and the target node are placed in the OPEN_LIST list; when the angle is less than the angle threshold, the neighboring node, the starting node and the target node are placed in the CLOSE_LIST list.

[0089] Angle K i , where the coordinates of the neighboring nodes are (X i ,Y i ), the starting node coordinates are (X st ,Y st ), the target node coordinates are (X end ,Y end ), then the angle K between the neighboring node, the starting node and the target node i The calculation formula is:

[0090]

[0091] Get the angle K i After the value of i Is it greater than the angle threshold K? d , avoid taking detours in pursuit of smooth roads.

[0092] Among them, the angle threshold K d Affected by the road congestion level Ω, when the road is too congested, the angle threshold K is appropriately lowered d When the road is relatively idle, the angle threshold K is appropriately increased. d When Ω<-1, K d =120°, when -1≤Ω≤1, K d =-30Ω+90°When Ω>1, K d =60°.

[0093] If there is an adjacent node c in the expanded adjacent nodes that is already in the OPEN_LIST list, calculate the new path from the starting node to the node c G1 * (n); Determine whether an update is needed: mainly determine whether the new G1 * (n) Is it lower?

[0094] If the new G1 * (n) is lower, then change the parent node to a and recalculate the new F1 * (n) value, H * The value of (n) does not need to change, and the estimated cost from node c to destination node E is fixed.

[0095] If the new G1 * If (n) is higher, it means that the new path has higher consumption and no change is needed.

[0096] Step 5: Continue to find the valuation function F1 from the OPEN_LIST list * The node with the smallest (n) value is deleted from the OPEN_LIST list and added to the CLOSE_LIST list, and then returns to step 3.

[0097] Step 6: After adding the nodes in the CLOSE_LIST list, trace back according to the parent-child relationship to obtain the planned path from the starting node S to the destination node E.

[0098] In order to verify the feasibility and superiority of the embodiment, the inventors set up a case for verification of the above embodiment, and the verified case is as follows:

[0099] In this case, some sections of a city are selected for path planning, such as Figure 2As shown, the starting node is A, the destination node is L, and the path is planned based on the road traffic flow. According to data detection, the average number of queuing vehicles in the previous 30 days is 5.07.

[0100] The relevant data are shown in Table 1 and Table 2 as follows:

[0101]

[0102] Table 1 shows the coordinates of the starting node A, the destination node L, and each intermediate node

[0103]

[0104] Table 2 shows the data related to the route

[0105] Through calculation, it can be known that μ S(k) = 0.52, μ H(n) = 1.06, μ P(k) = 3.35, μ av = 4.47, Ω = -0.25. Since -1 ≤ -0.25 ≤ 1, so K d = 97.5°, and the angle threshold K of this case d is 97.5°.

[0106] H(A) = 1.83km, H(B) = 1.13km, H(C) = 0.81km, H(D) = 1.69km, H(E) = 0.97km, H(F) = 0.55km, H(G) = 1.68km, H(H) = 1.00km, H(I) = 0.32km, H(J) = 1.73km, H(K) = 0.95km, H(L) = 0km.

[0107] According to the evaluation function F(n) = G(n) + H(n) of the A* algorithm, using the above data, obtain the path from the starting node A to the destination node L. The calculation process is as follows:

[0108] Taking A as the starting node, calculate the F(n) values of B and D respectively. F(B) = G(B) + H(B) = 1.93, F(D) = G(D) + H(D) = 1.94. Since F(B) < F(D), so choose B as the next node.

[0109] Taking B as the current node, search for the next adjacent node, and calculate the F(n) values of C and E. F(C) = G(C) + H(C) = 2.31, F(E) = G(E) + H(E) = 1.98. Since F(D) < F(E) < F(C), so choose D as the next node.

[0110] Taking D as the current node, search for the next adjacent node, calculate the F(n) values of G and E, F(G) = G(G) + H(G) = 2.18, F(E) = G(E) + H(E) = 2.07, F BE (E) < F DE (E), select the parent node as D, F(E) < F(G) < F(C), so select E as the next node.

[0111] Taking E as the current node, search for the next adjacent node, calculate the F(n) values of F and H, F(F) = G(F) + H(F) = 2.31, F(H) = G(H) + H(H) = 2.3, F(G) < F(H) < F(F) = F(C), so select G as the next node.

[0112] Taking G as the current node, search for the next adjacent node, calculate the F(n) values of H and J, F(H) = G(H) + H(H) = 2.2, F(J) = G(J) + H(J) = 2.52, F GH (H) < F EH (H), so select G as the previous hop node, F(H) < F(F) = F(C) < F(J), so select H as the next node.

[0113] Taking H as the current node, search for the next adjacent node, calculate the F(n) values of I and K, F(I) = G(I) + H(I) = 2.37, F(K) = G(K) + H(K) = 2.5, F(C) = F(F) < F(I) < F(K) < F(J), so select C as the next node.

[0114] Taking C as the current node, search for the next adjacent node, calculate the F(n) value of F, F(F) = G(F) + H(F) = 2.32, F EF (F) < F CF (F), so select E as the previous hop node, F(F) < F(I) < F(K) < F(J), so select F as the next node.

[0115] Taking F as the current node, search for the next adjacent node, calculate the F(n) value of I, F(I) = G(I) + H(I) = 2.42, F HI (I) < F FI (I), so select H as the previous hop node F(F) < F(I) < F(K) < F(J), so select F as the next node.

[0116] Taking I as the current node, search for the next adjacent node, the next adjacent node is the destination node L, and the algorithm ends.

[0117] The path planned by the A* algorithm is A - D - G - H - I - L, and the distance is 2.37 km.

[0118] The speed V of the vehicle on the ith route i and the road congestion degree of the i-th route Ω i The relationship is: Without considering the waiting time of the vehicle at the traffic light, the time taken for this path is 3.62 minutes.

[0119] According to the improved A* algorithm, using the above data, the path planning based on the road traffic conditions from the starting point A to the destination node L is obtained. The calculation process is briefly described as follows:

[0120] Take A as the starting node and calculate F1 of B and D respectively * (n) value, F1 * (n) = G1 * (n)+H * (n), K B =142.1°, K D =120.3°, the angle ABL formed by node B, the starting node and the target node, and the angle ADL formed by node D, the starting node and the target node are both greater than the angle threshold K d , F1 * (B) = G1 * (B)+H * (B)=2.83,F1 * (D) = G1 * (D)+H * (D)=2.40,F1 * (D) <F1 * (B), so choose D as the next node.

[0121] Take D as the current node and calculate F1 of E and G * (n) value, K E =161.9°, K G =100.3°, the angle AEL formed by node E and the starting node and the target node, and the angle AGL formed by node G and the starting node and the target node are both greater than the angle threshold K d , F1 * (E) = G1 * (E)+H * (E)=2.69,F1 * (G) = G1 * (G)+H * (G)=2.52,F1 * (G) <F1 * (E) <F1 * (B), so choose G as the next node.

[0122] Take G as the current node and calculate F1 of H and J * (n) value, K H =161.9°, K J =84.8°, the angle AHL formed by node H, the starting node and the target node is greater than the angle threshold K d , F1 * (H) = G1 * (H)+H * (H) = 3.01, the angle AJL formed by node J and the start node and target node is less than the angle threshold of 97.5°, so it is not considered. F1 * (E) <F1 * (B) <F1 * (H), so choose E as the next node.

[0123] Take E as the current node and calculate F1 of F and H * (n) value, K F =104.1°, K H =161.9°, the angle AFL formed by node F and the starting node and the target node, and the angle AHL formed by node H and the starting node and the target node are both greater than the angle threshold K d , F1 * (F) = G1 * (F)+H * (F)=2.94,F1 * (H) = G1 * (H)+H * (H)=2.75,F1 * EH (H) <F1 * GH (H), so choose E as the previous hop node, F1 * (H) <F1 * (B) <F1 * (F), so choose H as the next node;

[0124] Take H as the current node and calculate F1 of I and K * (n) value, K I =126.3°, K K =126.5°, the angle AIL formed by node I and the starting node and the target node, and the angle AKL formed by node K and the starting node and the target node are both greater than the angle threshold K d , F1 * (I) = G1 * (I)+H * (I)=3.26,F1 * (K) = G1 * (K)+H* (K)=2.93,F1 * (B) <F1 * (K) <F1 * (F) <F1 * (H) <F1 * (I), so choose B as the next node.

[0125] Take B as the current node and calculate F1 of C and E * (n) value, K C =100.6°, K E =161.9°, the angle ACL formed by node C and the starting node and the target node, and the angle AEL formed by node E and the starting node and the target node are both greater than the angle threshold K d , F1 * (C) = G1 * (C)+H * (C)=2.73,F1 * (E) = G1 * (E)+H * (E)=2.65,F1 * (E) <F1 * (C) <F1 * (K) <F1 * (F) <F1 * (I), so choose E as the next node.

[0126] Take E as the current node and calculate F1 of F and H * (n) value, K F =104.1°, K H =161.9°, the angle AFL formed by node F and the starting node and the target node, and the angle AHL formed by node H and the starting node and the target node are both greater than the angle threshold K d , F1 * (F) = G1 * (F)+H * (F)=2.90,F1 * (H) = G1 * (H)+H * (H)=2.71,F1 * (H) <F1 * (C) <F1 * (F) <F1 * (K) <F1 * (I), so choose H as the next node.

[0127] Take H as the current node and calculate F1 of I and K * (n) value, K I=126.3°, K K =126.5°, the angle AIL formed by node I and the starting node and the target node, and the angle AKL formed by node K and the starting node and the target node are both greater than the angle threshold K d , F1 * (I) = G1 * (I)+H * (I)=3.22,F1 * (K) = G1 * (K)+H * (K)=2.88,F1 * (C) <F1 * (K) <F1 * (F) <F1 * (H) <F1 * (I), so choose C as the next node.

[0128] Take C as the current node and calculate F1 of F * (n) value, K F =104.1°, the angle AFL formed by node F, the start node and the target node is greater than the angle threshold K d , F1 * (F) = G1 * (F)+H * (F)=2.88,F1 * CF (F) <F1 * EF (F), so choose C as the previous hop node, F1 * (K)=F1 * (F) <F1 * (F) <F1 * (H) <F1 * (I), so choose K as the next node.

[0129] With K as the current node and the next-hop neighbor node as the target node L, the algorithm ends.

[0130] The path planned by the improved A* algorithm is ABEHIL, with a distance of 2.6 km. The time taken to plan the path by the improved A* algorithm is 3.2 minutes.

[0131] Analysis of experimental results: From the above examples, we can see that Figure 3As shown in the figure, the path planned by the original A* algorithm is ADGHIL, which is the green path in the figure; after considering the traffic conditions on the road, the path planned by the improved A* algorithm is ABEHKL, which is the red path in the figure. The improved A* algorithm not only takes into account the road length, but also the traffic conditions on the road, effectively avoiding a lot of time wasted due to road congestion, and is more in line with actual scene applications.

[0132] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes, substitutions and improvements within the technical scope disclosed by the present invention are within the protection scope of the present invention.

Claims

1. A path planning method based on road traffic conditions, characterized in that: By giving the starting node S and the destination node E, the length between each node is calculated and the number of vehicles queuing between each node is obtained. Then, according to the improved A* algorithm, the path is planned based on the road traffic conditions. The specific operation method is as follows: S1: Get the starting node S and the destination node E of the path to be planned, draw a two-dimensional plane directed graph, take the traffic lights at each intersection in the route as the intermediate nodes, and get the corresponding coordinates of the starting node S, the destination node E and each intermediate node in the two-dimensional coordinate axis; S2: According to the coordinates of each starting node S, destination node E and each intermediate node, calculate the distance of each corresponding road section, and obtain the vehicles queued at the traffic lights on each road section; S3: Based on the known starting node and target node, the improved A* algorithm is used to plan the path; The improved A* algorithm is to improve the evaluation function. The evaluation function of the original A* algorithm is: F(n)=G(n)+H(n); G(n) is the distance from the current n nodes to the starting node, and H(n) is the distance from the current n nodes to the target node; The improved valuation function is: F1(n)=G1(n)+H(n); G1(n)=ω1G(n)+ω2P(i); ω1+ω2=1; P(i) is the number of vehicles queuing at the traffic light with the number i corresponding to the road section from the previous parent node to the current child node n. When selecting nodes, the length of the route is considered as well as the traffic flow on the road. This is to add the influencing factor of road congestion to the original valuation function. The value of ω2 is determined by the road traffic flow and is accurate to two decimal places. According to data monitoring, the average number of vehicles queuing in the previous 30 days is obtained, and its average value is μ. av , the average value of road vehicles at the current moment is μ P(k) , the current road congestion level is: The formula for determining the value of ω2 is: Among them, the coordinates of the ath node are (Xa, Ya), the coordinates of the bth node are (Xb, Yb), and the length S(i) of the road section numbered i consisting of the ath node and the bth node is: Since the magnitudes of G(n), H(n), and P(i) are different, they need to be processed to eliminate the influence of their different magnitudes. The planned route has n nodes and k sections, and the length of the i-th section is S(i); then the average length of the k sections is μ S(k) for: μ H(n) is the average distance from all nodes to the destination node, μ P(k) ' is the average number of vehicles in the queues on all road sections between nodes, then: The magnitudes of G(n), H(n), and P(i) are different. After processing, the improved G * (n), H * (n), P * (i) is: Get the final improved evaluation function: F1 * (n)=G1 * (n)+H * (n), G1 * (n)=ω1G * (n)+ω2P * (i)。 2. The path planning method based on road traffic conditions according to claim 1, characterized in that: The specific steps of obtaining the path planning based on the road traffic conditions by improving the A* algorithm are: Step 1: Determine the coordinates of each node on the two-dimensional coordinate axis and determine the coordinates of the starting node (X st , Y st ), target node coordinates (X end , Y end ); Step 2: Initialize an OPEN_LIST list and a CLOSE_LIST list, put the starting node into the OPEN_LIST list, and clear the CLOSE_LIST list; Step 3: Determine whether the current OPEN_LIST list has a target node. If so, go to step 6; If there is no target node, select the cost function F1 in the current OPEN_LIST list * The node with the smallest (n) value is used as the current node n whose neighbor node is to be expanded, and it is deleted from the OPEN_LIST list and placed in the CLOSE_LIST list; Step 4: Check the angle K formed by each extended neighbor node, the starting node, and the target node i , determine whether the angle is greater than the angle threshold K d , when the angle is greater than the angle threshold, the neighboring node, the starting node and the target node are put into the OPEN_LIST list; when the angle is less than the angle threshold, the neighboring node, the starting node and the target node are put into the CLOSE_LIST list; If there is an adjacent node c in the expanded adjacent nodes that is already in the OPEN_LIST list, calculate the new path from the starting node to the node c G1 * (n); Determine whether an update is needed: mainly determine whether the new G1 * (n) whether it is lower; If the new G1 * (n) is lower, then change the parent node to a and recalculate the new F1 * (n) value, H * The value of (n) does not need to change, and the estimated consumption from node c to destination node E is fixed; If the new G1 * (n) If it is higher, it means that the new path has higher consumption and no change is needed; Step 5: Continue to find the valuation function F1 from the OPEN_LIST list * (n) The node with the smallest value is deleted from the OPEN_LIST list and added to the CLOSE_LIST list, and then returns to step 3; Step 6: After adding the nodes in the CLOSE_LIST list, trace back according to the parent-child relationship to obtain the planned path from the starting node S to the destination node E.

3. A path planning method based on road traffic conditions according to claim 2, characterized in that: The angle K mentioned in step 4 i , where the coordinates of the neighboring nodes are (X i ,Y i ), the starting node coordinates are (X st ,Y st ), the target node coordinates are (X end ,Y end ), then the angle K between the neighboring node, the starting node and the target node i The calculation formula is: Get the angle K i After the value of i Is it greater than the angle threshold K? d , avoid taking detours in pursuit of smooth roads.

4. The path planning method based on road traffic conditions according to claim 2, characterized in that: The angle threshold K d Affected by the road congestion level Ω, when the road is too crowded, the angle threshold K is appropriately lowered d When the road is relatively idle, the angle threshold K is appropriately increased. d When Ω<-1, K d =120°, when -1≤Ω≤1, K d =-30Ω+90°, when Ω>1, K d =60°.

Images