Path planning method based on position sensitivity and probability driving

Abstract

The invention belongs to the technical field of path planning, and relates to a path planning method based on position sensitivity and probability driving. The method comprises the following steps: reading or constructing an electronic map and setting a starting point, an ending point and a geographic range; setting a corresponding sensitivity level for each area according to an importance rule in a geographical range; setting the sensitivity of each intersection interval according to the starting point, the ending point, the road distribution in the geographical range and the regional sensitivity level; initializing passing indications and detection range exceeding indications of the intersection sections, and setting an upper limit of the detection range; a target starts from a starting point and advances towards a terminal point along a road, a probability interval is obtained according to a sensitivity level probability ratio, a random floating-point number is obtained through calculation, and the step is repeated until the terminal point or reaches the terminal point according to a shortest path rule after an upper limit of a detection geographical range is reached through inverse proportion weighting of Markov chain probability and intersection interval passing times. According to the planning method, the detection efficiency and credibility are remarkably improved, and target anti-cheating is prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular, to a path planning method relying on position sensitivity and probability drive. Background Art

[0002] Satellite navigation systems (such as GPS, Beidou) achieve device positioning through satellite navigation signals. A satellite navigation simulator can generate simulated satellite navigation signals according to set parameters such as time and position, causing the receiving device to misjudge its own time and space. This feature is applied to induced secrecy detection. In induced secrecy detection, by setting simulated position points and using the simulator to send simulated signals, it is possible to detect whether the target under test exhibits abnormal behavior. Further, the simulator can also upgrade single-point simulation to path simulation. By designing a path, dividing frequency bands, and combining paths to form a navigation signal, the target under test can be made to have an illusion of movement. Currently, path design mostly uses specified start and end points and a specific algorithm to generate a fixed path. Although this method can meet the requirements of conventional satellite navigation tests, it has limitations in the secrecy detection scenario. On the one hand, the secrecy sensitivity varies at different positions; on the other hand, repeated use of a fixed path is likely to trigger anti-deception by the target under test, making it difficult to meet the requirements of application scenarios with strict requirements such as secrecy detection and authentication. Summary of the Invention The purpose of the present invention is to address the problems of insufficient dynamic performance in existing path planning, difficulty in preventing the target under test from being activated and anti-deception, and low detection accuracy or even inability to resist in applications such as induced secrecy detection. A path planning method relying on position sensitivity and probability drive is proposed to achieve secrecy detection applications.

[0003] To achieve or reach the above purpose, the present invention adopts the following technical solutions: The present invention provides a path planning method relying on position sensitivity and probability drive, which includes: Read or construct an electronic map and set the start point, end point, and geographical range; Within the geographical range, set the corresponding sensitivity level for each area according to the importance rule; Set the sensitivity of each intersection interval according to the start point, end point, road distribution within the geographical range, and the sensitivity level of each area; Initialize the passing indication and the indication of exceeding the detection range for each intersection interval and set the upper limit of the detection range; The target starts from the starting point and moves forward along the road towards the end point. Path planning is carried out according to the intersection intervals passed with different probabilities. The path planning obtains a probability interval based on the sensitivity level probability ratio and calculates a random floating-point number. After inverse weighting by the Markov chain probability and the number of times the intersection interval is passed, this step is repeated until reaching the end point or reaching the upper limit of the detected geographical range, and then the target reaches the end point according to the shortest path rule.

[0004] As a possible implementation, the path planning is specifically as follows: Calculate the probability ratios of different forward directions according to the sensitivity levels of the intersection intervals; According to the probability ratios, calculate several probability intervals according to the probability proportions; Generate a floating-point random number within the total probability interval, and then multiply it by the probability ratio and the inverse weighting sum indicated by the intersection intervals in different directions to determine in which direction the target moves forward at this intersection; The target moves forward to the next intersection according to the determined forward direction and increments the number of times this section of the intersection interval is passed by 1. Repeat this step to calculate the forward direction and then move forward to the next intersection until the target reaches the end point and this method ends or exceeds the detected geographical range; If the detected geographical range is exceeded, increment the number of times the detected geographical range is exceeded by 1 and determine whether the number of times the detected geographical range is reached the upper limit. If the upper limit of the number of times the detected geographical range is not reached, the target moves back until the next intersection and repeats this step; Otherwise, if the upper limit of the number of times the detected geographical range is reached, the target reaches the end point according to the shortest path rule.

[0005] As a possible implementation, the geographical range is a rectangular area that includes the starting point and the end point.

[0006] As a possible implementation, corresponding sensitivity levels are set for each area according to the importance rule. Specifically, it is divided into no less than 3 importance levels according to the importance of the facilities.

[0007] As a possible implementation, the sensitivity level is positively correlated with the path probability level.

[0008] As a possible implementation, the intersection interval is the interval between two intersections, and the interval includes several areas with the same or different sensitivity levels.

[0009] As a possible implementation, setting the sensitivity of each intersection interval means adding or weighted summing the sensitivity levels of multiple areas in this intersection interval.

[0010] As a possible implementation, the total probability interval of several probability intervals is a left-closed and right-closed interval and is decomposed into several probability intervals.

[0011] As a possible implementation, the first interval among several probability intervals is left-closed and right-closed, and the other intervals are left-open and right-closed.

[0012] As a possible implementation, at this intersection, the direction in which the target moves forward is specifically based on the inverse proportional weighting of the probability and the number of times passing through the intersection interval in different directions.

[0013] Beneficial effects A path planning method relying on position sensitivity and probability drive proposed by the present invention has the following beneficial effects compared with the prior art: 1. In the path planning method proposed by the present invention, when performing inductive secrecy detection, different sensitivity levels are assigned to different regions, and then the probabilities of the forward directions of each intersection are set according to the sensitivity levels. The path is planned dynamically according to the probabilities, which can improve the detection efficiency and the credibility of the detection.

[0014] 2. The path planning method proposed by the present invention designs the path based on position sensitivity, and can prevent the target to be detected from entering the anti-deception mode for inductive secrecy detection scenarios, especially for regions with high secrecy sensitivity, so as to achieve high-precision secrecy detection.

[0015] 3. The path planning method proposed by the present invention transforms the overall path planning into multiple route selection processes, and uses probability judgment in each route selection, so that the simulated target action path is more inclined to pass through locations with high sensitivity and different action paths will be adopted in multiple simulations. The planned path is more in line with the action law of the target in reality, making the inductive secrecy detection closer to reality and improving the detection efficiency.

[0016] 4. The path planning method proposed by the present invention is based on the Markov chain, and different paths may be generated in each planning, which can prevent the target to be detected from activating anti-deception means. Description of the drawings

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings: Figure 1 It is a flow chart of the path planning method relying on position sensitivity and probability drive of the present invention; Figure 2 It is a diagram of the possible results of the first path planning and the probability of each forward movement; Figure 3 It is a diagram of the possible results of the second path planning and the probability of each forward movement. Detailed implementation manners

[0018] For the convenience of clearly describing the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and roles. For example, the first threshold and the second threshold are only used to distinguish different thresholds, and do not limit their sequence. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and terms such as "first" and "second" do not necessarily limit them to be different.

[0019] It should be noted that in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific manner.

[0020] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. The following at least one (item) or its similar expression refers to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b or c can represent: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b and c can be single or multiple.

[0021] The embodiment of the present invention aims to provide a path planning method relying on position sensitivity and probability drive. The method includes: reading or constructing an electronic map and setting a starting point, an ending point and a geographical range; within the geographical range, setting a corresponding sensitivity level for each area according to the importance rule; setting the sensitivity of each intersection interval according to the starting point, the ending point, the road distribution within the geographical range, and the area sensitivity level; initializing the passing indication and the indication of exceeding the detection range of each intersection interval and setting the upper limit of the detection range; the target starts from the starting point and moves along the road towards the ending point, obtains a probability interval according to the probability ratio of the sensitivity levels and calculates to obtain a random floating point number, and performs inverse weighting through the Markov chain probability and the inverse of the number of times of passing through the intersection interval, and repeats this step until the ending point or until reaching the upper limit of the detected geographical range and then reaches the ending point according to the shortest path rule. The planning method of the present invention significantly improves the detection efficiency and credibility and prevents the target from anti-deception.

[0022] For the implementation process of the path planning method of the present invention, refer to Figure 1, to achieve high-precision security detection applications. The simulation targets are motor vehicles, non-motor vehicles or pedestrians, and the specific implementation methods are as follows: Read or construct an electronic map and set the starting point, ending point and geographical range; As a possible implementation, the geographical range is a rectangular area that includes the starting point and the ending point.

[0023] Exemplarily, the starting point and the ending point are located on the roads of the electronic map.

[0024] Exemplarily, an electronic map is constructed in real time through SLAM.

[0025] Within the geographical range, set the corresponding sensitivity level for each area according to the importance rule; As a possible implementation, a corresponding sensitivity level is set for each area, and it is divided into no less than 3 importance levels according to the importance degree of the facilities.

[0026] As a possible implementation, the sensitivity level is positively correlated with the path probability level.

[0027] Exemplarily, list the critical infrastructure as level 5; list the sub-critical infrastructure as level 4; list the third critical infrastructure as level 3; list the general infrastructure as level 2; list the non-critical infrastructure as level 1; list the non-infrastructure as level 0; the levels set here range from 0 to 5, where 0 means there is no sensitivity level at all, increasing in sequence, 5 is the highest sensitivity level, corresponding to the most important area; this number also corresponds to the probability level when calculating the path later.

[0028] Set the sensitivity of each intersection interval according to the starting point, ending point, road distribution within the geographical range, and the sensitivity levels of each area; As a possible implementation, the intersection interval is the interval between two intersections, and the interval includes several areas with the same or different sensitivity levels.

[0029] As a possible implementation, setting the sensitivity of each intersection interval means adding or weighted summing the sensitivity levels of multiple areas in this intersection interval.

[0030] Exemplarily, at a crossroads, turning left will pass through two areas with sensitivity levels of 1 and 3 respectively, with a total of 4; going straight will pass through two areas with sensitivity levels of 2 and 4 respectively, with a total of 6; turning right will pass through three areas with sensitivity levels of 0, 1 and 1 respectively, with a total of 2.

[0031] Initialize the passing indication and the indication of exceeding the detection range of each intersection interval and set the upper limit of the detection range; The target starts from the starting point and moves along the road towards the end point. Path planning is carried out according to the intersection intervals passed with different probabilities. The path planning obtains a probability interval based on the sensitivity level probability ratio and calculates a random floating-point number. After inverse weighting by the Markov chain probability and the number of times passing through the intersection interval, this step is repeated until reaching the end point or reaching the upper limit of the detected geographical range, and then reaching the end point according to the shortest path rule.

[0032] As a possible implementation, the path planning is specifically as follows: calculate the probability ratios of different forward directions according to the sensitivity levels of the intersection intervals. Exemplarily, at a certain intersection, the current probability ratios of turning left, going straight, and turning right are 4:6:2. Turning left at this intersection will pass through two areas with sensitivity levels of 1 and 3 respectively, with a total of 4; going straight will pass through two areas with sensitivity levels of 2 and 4 respectively, with a total of 6; turning right will pass through three areas with sensitivity levels of 0, 1, and 1 respectively, with a total of 2.

[0033] Exemplarily, when the target moves forward to an intersection, different probabilities are given according to the sensitivity levels of different passed areas as the basis for which direction the target moves forward.

[0034] If reaching the end point according to the above method, the path planning for this time ends. If exceeding the geographical range, the target turns around at the location where the range is exceeded and walks back to reach the next intersection and makes a choice of the forward direction. For this choice, if the number of available directions ≥ 2, then in specific implementation, add 1 to the indication of the exceeded detection range of the passed route and use it as the denominator to weight the probabilities of different forward directions and generate corresponding probability intervals, and generate a floating-point random number to determine in which direction the target moves forward at this intersection.

[0035] According to the probability ratios, calculate several probability intervals according to the probability proportion; generate a floating-point random number within the total probability interval, and then multiply it by the probability ratios and the inverse weighting sum of the indication of the intersection intervals in different directions to determine in which direction the target moves forward at this intersection; the target moves forward to the next intersection according to the determined forward direction and adds 1 to the number of times passing through this section of the intersection interval. Repeat this step to calculate the forward direction and then move forward to the next intersection until the target reaches the end point to end this method or exceeds the detected geographical range; if exceeding the detected geographical range, add 1 to the number of times exceeding the detected geographical range and judge whether the number of times of the detected geographical range reaches the upper limit. If the upper limit of the number of times of the detected geographical range is not reached, the target walks back until the next intersection and repeats this step; otherwise, if the upper limit of the number of times of the detected geographical range is reached, the target reaches the end point according to the shortest path rule.

[0036] As a possible implementation, the total probability interval of several probability intervals is a left-closed and right-closed interval and the decomposed several probability intervals.

[0037] As a possible implementation, the first interval among several probability intervals is closed on the left and closed on the right, and the other intervals are open on the left and closed on the right.

[0038] Exemplarily, within the range of [0, 10], a floating-point random number is generated. Combining with the probability ratios of moving forward in different directions, within [0, 10], according to the probability ratios obtained in the previous step, the left-open and right-closed probability intervals of floating-point numbers are calculated proportionally (except for the first interval, which is closed on the left and closed on the right), accurate to three decimal places. For example, for a probability ratio of 4:6:2, the obtained probability intervals are [0, 3.33], (3.33, 8.33], (8.33, 10].

[0039] As a possible implementation, at this intersection, the direction in which the target moves forward is specifically: based on the inverse proportional weighting of the probability and the number of times the intersection interval has been passed in different directions.

[0040] Exemplarily, if reaching the end point according to the above method, then this path planning ends. If it exceeds the geographical range, the target reverses at the location where it exceeds the range and walks back to reach the next intersection for choosing the forward direction. For this selection, if the number of available directions ≥ 2, then exclude the routes that have already been passed, continue to calculate the probabilities of different forward directions according to the above method, generate the corresponding probability intervals, and generate a floating-point random number to determine the direction in which the target moves forward at this intersection.

[0041] Exemplarily, the inverse proportional weighting of the number of times the intersection interval has been passed. For example, the inverse proportional weighting of the number of times the intersection interval has been passed is 3, and the coefficient is 1 / (the number of times the intersection interval has been passed + A) * B; the value range of A is [0.2 - 10] and the value range of B is [0.1 - 5].

[0042] As a specific implementation, there are several intersections within the detected geographical range. Each time the path is planned, several intersections will be passed through, that is, it needs to be planned several times. Denote the probability of choosing the nth route as the forward direction for the mth time as , since the probability of choosing a route each time is related to the previous choices, it can be denoted as a conditional probability. For example, the probability of choosing route n1 for the first time is denoted as , the probability of choosing route for the second time is denoted as , the probability of choosing route for the third time is denoted as , and so on. Then the probability of choosing route for the yth time is denoted as . Thus, a Markov chain based on probability planning path is formed.

[0043] Assume that in a path planning, it takes 6 times of planning to go from the starting point to the end point, and each time there is , …… There are several routes to choose from. Since different probabilities are used to select routes each time, under the same conditions, the possible results of path planning twice and the probability of moving forward each time are as Figure 2 、 Figure 3 shown. It should be further explained that since at each intersection, the next section of the route is selected based on probability, even if the same starting point, ending point, and confidentiality sensitivity levels within each area are set, the route selected each time may be different. Since the result of each route selection is not only related to the current probability but also to each previous selection, the results of path planning twice may vary greatly. At the same time, when selecting a route each time, the probability of selecting a high-sensitivity area is greater than that of a low-sensitivity area, so the path is more likely to pass through high-sensitivity areas.

[0044] At different locations, there are often objects with different sensitivity levels. For example, the confidentiality sensitivity of an ordinary residential community is very low, while that of a space unit is very high. If a residential community is located next to a space unit, the confidentiality sensitivity level will also increase accordingly; In the induced confidentiality detection and authentication, if there are areas with different confidentiality sensitivity levels within the simulated geographical range, the following operations will be carried out to achieve excellent detection effects: S11. Set boundary conditions; the boundary conditions refer to the geographical range to be detected; S12. Generate path restrictions according to the constraint principle; the constraint principle means that the generated path cannot exceed the above-mentioned boundary conditions, as well as the starting point and the ending point; S13. Calculate the probability of the current node choosing different forward directions according to the path restrictions; S14. Select a jump point according to the first preset principle to form a new section of the path; the first preset principle means that different jump probabilities are assigned from large to small according to the sensitivity level from high to low; S15. Judge whether the jump is reasonable according to the second preset principle; the second preset principle means judging whether this section of the road has been passed. If so, give higher weight to the sections that have not been passed; that is, different weights are assigned to the passed and unpassed routes, and the passed routes are avoided with high probability; if it exceeds the boundary, directly return within the boundary; if it exceeds the boundary three times or more, directly go to the end point without considering the jump probability.

[0045] S16. Record the generated path and generate a model based on the results of multiple path planning.

[0046] Before planning the running path of the target of the present invention, it is necessary to set areas with different confidentiality sensitivity levels and assign different weights to areas with different confidentiality sensitivity levels, so that the probability of passing through locations with high confidentiality sensitivity levels is higher than that of locations with low confidentiality sensitivity levels.

[0047] Typical path planning is global planning, that is, the path planned each time is fixed. The method proposed by the present invention dynamically generates a path based on a Markov chain. When passing through each intersection, the forward direction is determined with a probability; when the detection area is large, the paths planned multiple times may be different; Since confidentiality detection often needs to repeatedly detect the same target, and with the progress of technology, the anti-deception ability of the target to be detected is constantly increasing. If the same path is used for induction each time, the target to be detected may recognize that the current environment is not real, and then activate anti-deception means, making the confidentiality detection ineffective; the transition probability of each step at the intersection; Confidentiality detection often needs to perform multiple satellite navigation detections on the same target, simulate its action path, and conduct induction detection on it. The goal of satellite navigation induction detection is to make the target to be detected think that it is on this simulated path. The usual method is to use the same path for induction each time. However, with the progress of technology, the anti-deception ability of the target to be detected is constantly increasing. If the same path is used for each induction detection, the target to be detected may recognize that the current environment is not real, and then activate anti-deception means, making the confidentiality detection ineffective.

[0048] Based on the method proposed by the present invention, the operation path can be designed according to the confidentiality sensitivity levels at different positions. Multiple detections will plan different paths based on the Markov chain, and at the same time, it is more inclined to pass through high-sensitivity areas, so as to make the target to be detected think that it is in a real environment, while inducing the target to be detected and preventing it from activating anti-deception means.

[0049] Although the present invention has been described in conjunction with various embodiments herein, however, in the process of implementing the claimed invention, those skilled in the art can understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure content, and the drawings' description. In the specification, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude a plurality of situations. A single processor or other unit can implement several functions listed in the specification. Certain measures are described in different embodiments, but this does not mean that these measures cannot be combined to produce good results.

[0050] Although the present invention has been described in connection with specific features and their embodiments, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the invention. Accordingly, the present specification and the drawings are merely illustrative of the invention and are considered to cover any and all modifications, variations, combinations or equivalents within the scope of the invention. Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A path planning method relying on location sensitivity and probability drive, characterized in that, Including: Read or construct an electronic map and set the starting point, ending point, and geographical range; Within the geographical range, set the corresponding sensitivity level for each area according to the importance rule; Based on the starting point, ending point, road distribution within the geographical range, and sensitivity levels of each area, set the sensitivity of each intersection section; Initialize the passing indication and out-of-detection-range indication for each intersection section and set the upper limit of the detection range; The target starts from the starting point, moves along the road towards the ending point, and conducts path planning according to the intersection sections passed with different probabilities; the path planning obtains a probability interval based on the sensitivity level probability ratio and calculates a random floating-point number, which is weighted inversely by the Markov chain probability and the number of times the intersection section is passed. Repeat this step until reaching the ending point or the upper limit of the detected geographical range, and then reach the ending point according to the shortest path rule.

2. A path planning method based on location sensitivity and probability drive according to claim 1, characterized in that, The path planning is specifically as follows: Calculate the probability ratio of different forward directions according to the sensitivity level of the intersection section; calculate several probability intervals according to the probability ratio; Generate a floating-point random number within the total probability interval, then multiply it by the probability ratio and the inverse proportional weighted sum of the intersection section indications in different directions to determine the forward direction of the target at this intersection; The target moves forward to the next intersection according to the determined forward direction and adds 1 to the number of times this intersection section is passed. Repeat this step to calculate the forward direction and then move forward to the next intersection until the target reaches the ending point or exceeds the detected geographical range and ends; If the detected geographical range is exceeded, add 1 to the number of times the detected geographical range is exceeded and determine whether the number of times the detected geographical range is reached the upper limit. If the upper limit of the number of times the detected geographical range is not reached, the target moves back until the next intersection and repeats this step; otherwise, if the upper limit of the number of times the detected geographical range is reached, the target reaches the ending point according to the shortest path rule.

3. A path planning method based on location sensitivity and probability drive according to claim 1, characterized in that The geographical range is a rectangular area including the starting point and the ending point.

4. A path planning method based on location sensitivity and probability drive according to claim 1, characterized in that The step of setting the corresponding sensitivity level for each area according to the importance rule is specifically that, according to the importance degree of the facilities, it is divided into no less than 3 importance levels.

5. A path planning method based on location sensitivity and probability drive according to claim 1, characterized in that The sensitivity level is positively correlated with the path probability level.

6. A path planning method based on location sensitivity and probability drive according to claim 1, characterized in that The intersection section is the section between two intersections, and the section includes several areas with the same or different sensitivity levels.

7. A path planning method based on location sensitivity and probability drive according to claim 6, characterized in that The step of setting the sensitivity of each intersection section refers to adding or weighted summing the sensitivity levels of multiple areas in this intersection section.

8. A path planning method based on location sensitivity and probability drive according to claim 2, characterized in that, The total probability interval of the several probability intervals is a left-closed and right-closed and decomposed several probability intervals.

9. A path planning method based on location sensitivity and probability drive according to claim 8, characterized in that, The first interval among the several probability intervals is left-closed and right-closed, and the other intervals are left-open and right-closed.

10. The path planning method based on location sensitivity and probability drive according to claim 2, wherein The step of determining the forward direction of the target at this intersection is specifically: based on the inverse proportional weighting of the probability in different directions and the number of times the intersection section is passed.

Images