Airway planning method based on improved bidirectional fast random exploration tree algorithm

Abstract

The invention relates to an air route planning method based on an improved bidirectional fast random exploration tree algorithm, and is applied to the technical field of air route planning. The method comprises the following steps: acquiring a current node position, a target node position and terrain information of a target area of route planning; according to the terrain information, a search strategy combination of the target area is determined, the search strategy combination is used for constraining the extension direction of the air route nodes, and the air route nodes are determined based on an improved bidirectional fast random exploration tree algorithm. And determining a route node set according to the current node position, the target node position and the search strategy combination. The route nodes in the route node set are optimized, a target route is generated, and the target route is the route meeting the motion constraint of the fixed-wing aircraft. The expansion direction of the air route nodes is restrained through the search strategy combination, excessive redundant nodes caused during random sampling are avoided, and the convergence speed of air route planning can be increased. Therefore, the air route planning efficiency can be improved.

Description

Technical Field

[0001] This application belongs to the technical field of route planning, and particularly relates to a route planning method based on an improved bidirectional rapidly-exploring random tree algorithm. Background Art

[0002] Route planning refers to the process of determining an effective path from a starting point to an ending point for mobile robots such as unmanned aerial vehicles and airplanes in a given environment. This path should satisfy specific constraints, be able to avoid known obstacles, no-fly zones and other dangerous areas, reduce the collision risk during flight, and thus ensure the safety of the aircraft.

[0003] Generally, the bidirectional rapidly-exploring random tree algorithm can be used to search for a path through random sampling from both the starting point and the ending point to obtain the required route planning result. However, such a route planning method determines new nodes through random search, which will generate more redundant nodes. Therefore, the efficiency of route planning will be reduced. Summary of the Invention

[0004] In view of the above problems, the present disclosure is proposed. The present disclosure provides a route planning method based on an improved bidirectional rapidly-exploring random tree algorithm, which can improve the efficiency of route planning.

[0005] According to one aspect of the present disclosure, there is provided a route planning method based on an improved bidirectional rapidly-exploring random tree algorithm, including:

[0006] Obtaining the current node position, target node position, and terrain information of the target area for route planning;

[0007] Determining a search strategy combination for the target area according to the terrain information, where the search strategy combination is used to constrain the expansion direction of route nodes and determine route nodes based on an improved bidirectional rapidly-exploring random tree algorithm;

[0008] Determining a set of route nodes according to the current node position, the target node position, and the search strategy combination;

[0009] Optimizing the route nodes in the set of route nodes to generate a target route, where the target route is a route that satisfies the motion constraints of a fixed-wing aircraft.

[0010] Optionally, the determining the search strategy combination for the target area according to the terrain information includes:

[0011] Determining the environmental complexity of the target area according to the terrain information and the current node position;

[0012] Determining the search strategy combination according to the environmental complexity and a preset search guidance condition.

[0013] Optionally, determining the environmental complexity of the target area according to the terrain information and the current node position includes:

[0014] Determining a first positional relationship according to the current node position, the geometric center parameter, the equivalent shape parameter, and the geometric envelope parameter of the first obstacle in the terrain information, where the first obstacle is the obstacle closest to the current node position in the target area, and the first positional relationship is the positional relationship between the first obstacle and the current node position;

[0015] Determining a second positional relationship according to the current node position, the geometric center parameter, the equivalent shape parameter, and the geometric envelope parameter of the second obstacle in the terrain information, where the second obstacle is other obstacles in the target area except the first obstacle, and the second positional relationship is the positional relationship between the second obstacle and the current node position;

[0016] Determining the obstacle proximity degree according to the first positional relationship and the second positional relationship;

[0017] Determining the environmental complexity of the target area according to the obstacle proximity degree and a preset environmental weight.

[0018] Optionally, determining the set of route nodes according to the current node position, the target node position, and the search strategy combination includes:

[0019] Determining a distance correction factor according to the current node position and the target node position;

[0020] Determining a node guiding direction according to the distance correction factor, the current node position, and the potential field guiding strategy in the search strategy combination of the current node position and the target node position;

[0021] Determining an alternating frequency according to the environmental complexity and the alternating search strategy in the search strategy combination;

[0022] When it is determined that the search step update condition is satisfied, determining an updated search step according to the current search step and the random search strategy in the search strategy combination;

[0023] Determining the next route node according to the current node position, the alternating frequency, the updated search step, and the node guiding direction;

[0024] Taking the next route node as the current node, repeating the steps of determining the distance correction factor, the node guiding direction, the alternating frequency, the updated search step, and the next route node to determine the set of route nodes.

[0025] Optionally, optimizing the route nodes in the route node set to generate a target route includes:

[0026] Determining two connected random trees according to all the route nodes in the route node set, where the random trees include route nodes with multiple collision-free paths;

[0027] Performing greedy optimization processing on each of the route nodes with collision-free paths to generate a first optimized route;

[0028] Performing path smoothing processing on the first optimized route to determine the target route.

[0029] Optionally, performing path smoothing processing on the first optimized route to determine the target route includes:

[0030] Obtaining the maximum climb angle and the minimum turning radius of the fixed-wing aircraft;

[0031] Performing smoothing processing on the first optimized route according to the maximum climb angle and the minimum turning radius to determine the target route.

[0032] According to another aspect of the present disclosure, there is provided a route planning device based on an improved bidirectional rapidly-exploring random tree algorithm, including:

[0033] An acquisition module, configured to acquire the current node position, the target node position, and the terrain information of the target area for route planning;

[0034] A first determination module, configured to determine a search strategy combination for the target area according to the terrain information, where the search strategy combination is used to constrain the expansion direction of route nodes and determine route nodes based on an improved bidirectional rapidly-exploring random tree algorithm;

[0035] A second determination module, configured to determine a route node set according to the current node position, the target node position, and the search strategy combination;

[0036] A generation module, configured to optimize the route nodes in the route node set to generate a target route, where the target route is a route that satisfies the motion constraints of a fixed-wing aircraft.

[0037] According to still another aspect of the present disclosure, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor runs the computer program to implement the above-mentioned route planning method based on an improved bidirectional rapidly-exploring random tree algorithm.

[0038] According to another aspect of the present disclosure, there is provided a computer-readable storage medium having a computer program stored thereon, and the program is executed by a processor to implement the above-mentioned route planning method based on the improved bidirectional rapidly-exploring random tree algorithm.

[0039] According to still another aspect of the present disclosure, there is provided a computer program product including computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes to implement the above-mentioned route planning method based on the improved bidirectional rapidly-exploring random tree algorithm.

[0040] In the present disclosure, the current node position, the target node position, and the terrain information of the target area for route planning are obtained. According to the terrain information, a search strategy combination for the target area is determined, where the search strategy combination is used to determine the expansion directions of route nodes and constrained route nodes. According to the current node position, the target node position, and the search strategy combination, a set of route nodes is determined. The route nodes in the set of route nodes are optimized to generate a target route, where the target route is a route that satisfies the motion constraints of a fixed-wing aircraft. By constraining the expansion directions of route nodes through the search strategy combination, excessive redundant nodes can be avoided during random sampling, and the convergence speed of route planning can be improved. Moreover, affected by the characteristics of the fixed-wing aircraft itself, the target route generated through optimization processing can satisfy the kinematic constraints, making the target route more in line with actual requirements. Therefore, the efficiency of route planning can be improved.

[0041] It should be understood that both the foregoing general description and the following detailed description are exemplary and are intended to provide further explanation of the claimed technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] By describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present disclosure will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure, and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation to the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0043] Figure 1 It is a flowchart of a route planning method based on an improved bidirectional rapidly-exploring random tree algorithm provided by the present disclosure.

[0044] Figure 2 It is a schematic structural diagram of alternating search of two random trees provided by the present disclosure.

[0045] Figure 3 It is a schematic structural diagram of updating the search step length provided by the present disclosure.

[0046] Figure 4 Schematic diagram of the route structure composed of the route node set provided by the present disclosure.

[0047] Figure 5 Schematic diagram of the structure of the first optimized route provided by the present disclosure.

[0048] Figure 6 Schematic diagram of the structure of the target route after smoothing processing provided by the present disclosure.

[0049] Figure 7 Another flowchart of a route planning method based on an improved bidirectional rapidly-exploring random tree algorithm provided by the present disclosure.

[0050] Figure 8 Schematic diagram of the structure of a route planning device based on an improved bidirectional rapidly-exploring random tree algorithm provided by the present disclosure.

[0051] Figure 9 Hardware block diagram of an electronic device provided by the present disclosure.

[0052] Figure 10 Schematic diagram of a computer program product provided by the present disclosure. Detailed implementation manners

[0053] To enable those skilled in the art to more clearly understand the technical solution of the present application, the application scenario of the present application solution will be described first below.

[0054] The application scenario of fixed-wing aircraft is very extensive, and it not only shows great potential in daily life, such as urban logistics, fire rescue, urban management, medical distribution, etc. However, the complex three-dimensional dynamic environment will increase the probability of the aircraft colliding with obstacles. Fixed-wing aircraft cannot vertically climb or hover when encountering obstacles like rotary-wing aircraft, and its kinematic constraints make route planning more complex. Therefore, in this case, an efficient path planning method to achieve collision-free flight is crucial.

[0055] Route planning refers to the process of determining an effective path from a starting point to an ending point for mobile robots such as unmanned aerial vehicles and aircraft in a given environment. This path should meet specific constraints, be able to avoid known obstacles, no-fly zones and other dangerous areas, reduce the collision risk during flight, and thus ensure the safety of the aircraft.

[0056] Currently, the rapidly-exploring random tree algorithm is usually adopted to search for paths through random sampling, so that the exploration process does not depend on the global map or complete knowledge of the environment. Therefore, it is efficient to search for paths in an unknown high-dimensional environment and has the property of probabilistic completeness of the state space. However, such a route planning method will generate many redundant nodes. Therefore, the efficiency of route planning will be reduced.

[0057] To solve the above technical problems, the present disclosure provides a route planning method based on an improved bidirectional rapidly-exploring random tree algorithm. In the present disclosure, the current node position, the target node position, and the terrain information of the target area for route planning are obtained. According to the terrain information, a search strategy combination for the target area is determined, where the search strategy combination is used to determine the route nodes and the expansion directions of the constrained route nodes. According to the current node position, the target node position, and the search strategy combination, a set of route nodes is determined. The route nodes in the set of route nodes are optimized to generate a target route, where the target route is a route that satisfies the motion constraints of a fixed-wing aircraft. By constraining the expansion directions of the route nodes through the search strategy combination, excessive redundant nodes can be avoided during random sampling, and the convergence speed of route planning can be improved. Moreover, affected by the characteristics of the fixed-wing aircraft itself, the target route generated by the optimization process can satisfy the kinematic constraints and make the target route more in line with the actual requirements. Therefore, the efficiency of route planning can be improved.

[0058] To make the objectives, technical solutions, and advantages of the present disclosure more apparent, exemplary embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure. It should be understood that the present disclosure is not limited by the exemplary embodiments described herein.

[0059] Figure 1 It is a flowchart of a route planning method based on an improved bidirectional rapidly-exploring random tree algorithm provided by the present disclosure. As Figure 1 shown, the method includes:

[0060] S101: Obtain the current node position, the target node position, and the terrain information of the target area for route planning.

[0061] Specifically, when performing route planning, the starting position and the ending position need to be clarified. In this embodiment, the search for route nodes is based on an improved bidirectional rapidly-exploring random tree algorithm, that is, a random tree is generated from the starting position, and another random tree is generated from the ending position. For the random tree starting from the starting point, the target node position is the ending point, and for the random tree starting from the ending point, the target node position is the starting point.

[0062] Based on obstacle perception, the terrain information of the target area of the current node position can be determined to obtain the environmental complexity of the target area of the current node position.

[0063] S102: Determine the search strategy combination for the target area according to the terrain information.

[0064] Specifically, the environmental complexity of the target area can be determined according to the terrain information. Combining with the preset search guidance conditions, the search strategy combination for the target area can be determined. Under the condition that the environmental complexity meets different environmental complexity thresholds, the probability ratio of each strategy may be different. That is to say, the search strategy combination is determined by the environmental complexity. Among them, the search strategy combination is used to determine the waypoint nodes and the expansion directions of the constrained waypoint nodes. In this embodiment, the search strategy combination includes a potential field guidance strategy, an alternating search strategy, and a random search strategy. The potential field guidance strategy and the alternating search strategy are used to constrain the expansion directions of the waypoint nodes, and the random search strategy is used to determine the waypoint nodes. In this embodiment, the random search strategy is an improved bidirectional fast random search tree algorithm.

[0065] S103: Determine the waypoint node set according to the current node position, the target node position, and the search strategy combination.

[0066] Specifically, in this embodiment, the random search strategy in the search strategy combination has an adaptive search strategy allocation mechanism, which can adaptively allocate and adjust the node search step size. The potential field guidance strategy in the search strategy combination can guide the two random trees to expand towards different target node positions respectively, and adjust the potential field through a distance correction factor to avoid the possibility of not reaching the target node. The alternating search strategy can alternately explore between the two random trees, and the alternating frequency is determined by the complexity of the environment to avoid blind sampling of the random trees. The current node position combines with the search strategy combination to generate the next waypoint node towards the target node position, that is, the node in the random tree, until the two random trees are connected to determine the complete waypoint node set.

[0067] S104: Optimize the waypoint nodes in the waypoint node set to generate the target route.

[0068] Specifically, delete the redundant nodes in the waypoint node set and smooth the route to obtain the target route. The waypoint nodes in the target route are the minimum viable waypoint points. Among them, the target route is a route that meets the motion constraints of a fixed-wing aircraft.

[0069] In the present disclosure, the current node position, the target node position of the route planning, and the terrain information of the target area are obtained. According to the terrain information, a search strategy combination for the target area is determined, where the search strategy combination is used to determine the route nodes and the expansion directions of the constrained route nodes. According to the current node position, the target node position, and the search strategy combination, a set of route nodes is determined. The route nodes in the set of route nodes are optimized to generate a target route, where the target route is a route that satisfies the motion constraints of a fixed-wing aircraft. By constraining the expansion directions of the route nodes through the search strategy combination, excessive redundant nodes can be avoided during random sampling, which can improve the convergence speed of the route planning. Moreover, affected by the characteristics of the fixed-wing aircraft itself, the target route generated through the optimization process can satisfy the kinematic constraints, making the target route more in line with the actual requirements. Therefore, the efficiency of the route planning can be improved.

[0070] In one possible implementation manner, an exemplary method for determining the search strategy combination of the target area according to the terrain information includes:

[0071] According to the terrain information and the current node position, the environmental complexity of the target area is determined.

[0072] Specifically, there may be multiple obstacles in the target area. By performing obstacle perception on the target area, the terrain information of the target area can be obtained. The terrain information includes parameters such as the geometric center parameters of the obstacles in the target area, the equivalent shape parameters of the obstacles, and the geometric envelope range parameters of the obstacles. According to the current node position and the obstacle-related parameters in the nearby area, the environmental complexity of the target area where the current node position is located can be determined.

[0073] According to the environmental complexity and the preset search guidance conditions, the search strategy combination is determined.

[0074] Specifically, in this embodiment, the search strategy combination is composed of a potential field guidance strategy, an alternating search strategy, and a random search strategy. The potential field guidance strategy guides two random trees to expand towards the target starting point and the target ending point respectively. In the present disclosure, a distance correction factor is added to adjust the potential field function to avoid the possibility of not being able to reach the target point. The alternating search strategy realizes alternating exploration between two independent trees. The alternating frequency is determined by the environmental complexity. The latest node on random tree 1 will be used as the target node by random tree 2 to guide the growth of the next node, and vice versa, which helps to accelerate the connection of the random trees and avoid blind sampling of the random trees. The random search strategy has an adaptive search strategy allocation mechanism. When a route node cannot be searched for multiple times, it avoids collisions with obstacles by adjusting the search step size to determine the route node.

[0075] Under the condition that the environmental complexity meets different environmental complexity thresholds, the probability ratios of each strategy may be different. That is to say, the search strategy combination is determined by the environmental complexity. Among them, the environmental complexity threshold is determined through multiple training and planning.

[0076] According to the following formula, the search strategy combination corresponding to different environmental complexities can be determined:

[0077]

[0078] Among them, G is the search strategy combination, f a is the potential field guidance probability, f p is the alternating search probability, f r is the random search probability, is the first environmental complexity threshold, is the environmental complexity, is the second environmental complexity threshold.

[0079] In a possible implementation manner, an exemplary method for determining the environmental complexity of the target area according to the terrain information and the current node position includes:

[0080] According to the current node position, the geometric center parameter, the equivalent shape parameter, and the geometric envelope parameter of the first obstacle in the terrain information, determine the first position relationship.

[0081] Specifically, the first obstacle is the obstacle closest to the current node position in the target area, and the first position relationship is the position relationship between the first obstacle and the current node position.

[0082] The first position relationship can be determined according to the following formula:

[0083]

[0084] Among them, S i (P) is the first position relationship between the equivalent geometric envelope of the i-th obstacle and the current node p, a 0 , b 0 , c 0 , R u , p, q, r are parameters for determining the equivalent shape and envelope range of the i-th obstacle, [x 0 , y 0 , z 0 is the equivalent geometric center of the i-th obstacle.

[0085] According to the current node position, the geometric center parameter, the equivalent shape parameter, and the geometric envelope parameter of the second obstacle in the terrain information, determine the second position relationship.

[0086] Specifically, the second obstacle is other obstacles in the target area except the first obstacle, and the second positional relationship is the positional relationship between the second obstacle and the current node position.

[0087] The second positional relationship can be determined according to the following formula:

[0088]

[0089] where S k (P) is the second positional relationship between the equivalent geometric envelope of the k-th obstacle and the current node p, a 0 , b 0 , c 0 , R u , p, q, r are parameters for determining the equivalent shape and envelope range of the k-th obstacle, [x 0 , y 0 , z 0 is the equivalent geometric center of the k-th obstacle.

[0090] Based on the first positional relationship and the second positional relationship, determine the degree of obstacle proximity.

[0091] Specifically, the degree of obstacle proximity can be determined according to the following formula:

[0092]

[0093] where is the degree of obstacle proximity, S i (P) is the first positional relationship, S k (P) is the second positional relationship, i is the first obstacle, k is the second obstacle, and N is the number of obstacles in the target area.

[0094] Based on the degree of obstacle proximity and the preset environmental weight, determine the environmental complexity of the target area.

[0095] Specifically, the environmental complexity can be determined according to the following formula:

[0096]

[0097] where is the environmental complexity, is the degree of obstacle proximity, λ p is the preset environmental weight, k is the second obstacle, and N is the number of obstacles in the target area.

[0098] In a possible implementation manner, an exemplary method for determining a set of route nodes according to the current node position, the target node position, and the search strategy combination includes:

[0099] Determine the distance correction factor according to the current node position and the target node position.

[0100] Specifically, adjust the repulsive potential field in the potential field guiding strategy through the distance correction factor. When approaching the target node position, the distance correction factor rapidly decreases, making the repulsive force tend to zero to avoid the situation where the repulsive force is too large to reach the target node position.

[0101] The expression of the distance correction factor is as follows:

[0102] κd n (p, p target )

[0103] where p is the current node position and p target is the target node position.

[0104] Determine the node guiding direction according to the distance correction factor, the current node position, the target node position, and the potential field guiding strategy in the search strategy combination.

[0105] Specifically, the distance correction factor, the current node position, the target node position, and the repulsive potential field strategy in the potential field guiding strategy can determine the repulsive potential field.

[0106] The repulsive potential field can be determined according to the following formula:

[0107]

[0108] where U rep is the repulsive potential field, p is the current node position, p target is the target node position, kd n (p, p target ) is the correction factor, λ r is the repulsive potential field action factor, r min is the shortest distance from the current node to the obstacle, and R safe is the repulsive potential field action range threshold.

[0109] The node guiding direction is determined according to the vector resultant force of the repulsive force and the attractive force. To prevent the attractive force from being too large and colliding with the obstacle when approaching the target node, the attractive potential field decays when approaching the target node.

[0110] The attractive potential field can be determined according to the following formula:

[0111]

[0112] where U att is the attractive potential field, λ a is the attractive potential field action factor, d(p, p target) is the Euclidean distance function between the current node position and the target node position, and λ 1 is the critical distance between the current node position and the target node position.

[0113] According to the negative gradient method, the forces of the repulsive potential field and the attractive potential field can be calculated respectively.

[0114] The repulsive force and the attractive force can be calculated according to the following formula:

[0115]

[0116] where is the vector repulsive force, is the vector attractive force, and U rep is the repulsive potential field, and U att is the attractive potential field, and p is the current node position.

[0117] Through the vector repulsive force and the vector attractive force, the vector resultant force of the two can be calculated, and by calculating the vector resultant force, the node guiding direction can be determined. The potential field guiding strategy can avoid blind sampling, reduce the generation of redundant nodes, and improve the sampling efficiency to a certain extent. In order to further improve the convergence speed.

[0118] The vector resultant force can be determined according to the following formula:

[0119]

[0120] where is the vector repulsive force, is the vector attractive force, is the vector resultant force.

[0121] The node guiding direction can be determined according to the following formula:

[0122]

[0123] where is the vector resultant force.

[0124] According to the environmental complexity and the alternating search strategy in the search strategy combination, the alternating frequency is determined.

[0125] Specifically, based on the random search strategy, the alternating search strategy is designed, which can accelerate the connection between two random trees. Figure 2 is the structural schematic diagram of the alternating search of two random trees provided by the present disclosure, as Figure 2As shown. The latest node on the random tree 1 is used as the target node when the random tree 2 is expanded, guiding the expansion of the new nodes on the random tree 2, and vice versa, thus accelerating the connection between the random tree 1 and the random tree 2. During the alternating expansion process, the alternating frequency is determined by the environmental complexity and is reflected by the number of consecutive expansions of the nodes on each random tree.

[0126] When the environment is relatively simple, reduce the alternating frequency, increase the number of consecutive expansions of the random tree, and improve the growth rate. When the environment is relatively complex, increase the alternating frequency, reduce the number of consecutive expansions of the random tree, and reduce the possibility of invalid sampling. Among them, when the distance between the nodes on the two random trees is less than the set threshold and the connection line between the nodes does not collide with the obstacle, the two random trees are connected at this time.

[0127] The alternating frequency can be calculated and determined according to the following formula:

[0128]

[0129] Among them, n c is the alternating frequency, a c is the number of consecutive expansions, a x is the environmental complexity gain coefficient, is the environmental complexity.

[0130] When it is determined that the search step size update condition is met, the updated search step size is determined according to the current search step size and the random search strategy in the search strategy combination.

[0131] Specifically, the sampling randomness of the existing bidirectional fast random exploration tree algorithm also makes it difficult to pass when facing narrow spaces. Therefore, in this embodiment, the bidirectional fast random exploration tree algorithm is improved, and the search step size can be adaptively adjusted during the search process, constituting the random search strategy in the present disclosure. Figure 3 This is the structural schematic diagram of the updated search step size provided by the present disclosure, as Figure 3 shown. When approaching a narrow path, after consecutive exploration failures, the search step size will be adjusted to be smaller, so that the random tree can quickly pass through the narrow area. On the contrary, when dealing with a relatively open area with sparse obstacles, after consecutive successful explorations, the search step size will be adjusted to be larger for rapid exploration.

[0132] The updated search step size can be determined according to the following formula:

[0133]

[0134] Among them, Δ stepu is the updated search step size, Δ step is the current search step size, λ col is the step size shortening coefficient, nTcol is the threshold of the number of node growth collisions, n col is the number of node growth collisions, λ ncol is the step expansion coefficient, n Tncol is the threshold of the number of collision - free node growth, n ncol is the number of collision - free node growth.

[0135] Determine the next route node according to the current node position, alternating frequency, updated search step, and node guiding direction.

[0136] Specifically, the alternating frequency is used to constrain the continuous expansion times of each node on the random tree.

[0137] The next route node can be calculated according to the following formula:

[0138]

[0139] where P next is the next route node, P now is the current node position, Δ stepu is the updated search step, is the node guiding direction.

[0140] Take the next route node as the current node, and repeat the steps of determining the distance correction factor, node guiding direction, alternating frequency, updated search step, and next route node to determine the set of route nodes.

[0141] Specifically, repeat the above steps until the random tree generated from the starting position is connected to the random tree generated from the ending position. At this time, integrate all the route nodes into the set of route nodes.

[0142] In a possible implementation manner, an exemplary method for optimizing the route nodes in the set of route nodes to generate the target route includes:

[0143] Determine two connected random trees according to all the route nodes in the set of route nodes.

[0144] Specifically, the random tree includes route nodes with multiple collision - free paths. Connect the route nodes in the set of route nodes, and two connected random trees can be obtained, which can form a route with more redundant nodes. As Figure 4 shown, Figure 4 is the structural schematic diagram of the route formed by the set of route nodes provided by the present disclosure. It can be seen that there are routes formed by some redundant nodes in this route structural schematic diagram.

[0145] Perform greedy optimization processing on each route node with a collision - free path to generate the first optimized route.

[0146] Specifically, for some redundant nodes, all the nodes on the path are marked in the order from the starting position to the ending position, and then all the nodes are traversed in sequence to determine two nodes. For example, whether node A and node B can be directly connected. If they can be directly connected without colliding with obstacles, it can be known that the other nodes between node A and node B will be considered redundant nodes and need to be deleted. As Figure 5 shown Figure 5 is the structural schematic diagram of the first optimized route provided by the present disclosure. It can be seen that in this route structural schematic diagram, the first optimized route is more intuitive and concise compared to the route formed by some redundant nodes.

[0147] Perform path smoothing on the first optimized route to determine the target route.

[0148] For example:

[0149] Obtain the maximum climb angle and minimum turning radius of the fixed-wing aircraft.

[0150] Specifically, the maximum climb angle is usually limited by the maximum thrust and the gravity of the aircraft. Therefore, the maximum climb angle can be determined according to the following formula:

[0151]

[0152] where is the maximum climb angle, P max is the maximum thrust, m is the mass of the fixed-wing aircraft, and g is the acceleration due to gravity.

[0153] The minimum turning radius reflects the maneuverability of the fixed-wing aircraft, and the maneuverability is usually limited by the flight speed and the maximum allowable roll angle of the fixed-wing aircraft. Therefore, the minimum turning radius can be determined according to the following formula:

[0154]

[0155] where r is the minimum turning radius, V is the flight speed, g is the acceleration due to gravity, and φ max is the maximum roll angle.

[0156] Perform smoothing on the first optimized route according to the maximum climb angle and the minimum turning radius to determine the target route.

[0157] Specifically, in this embodiment, the 3D Dubins path smoothing algorithm is used to perform smoothing on the first optimized route, and the target route can be obtained. As Figure 6 shown Figure 6 is the structural schematic diagram of the target route after smoothing provided by the present disclosure. It can be seen that the route after smoothing is smoother and more accurate.

[0158] Figure 7 Another flowchart of a route planning method based on an improved bidirectional fast random search tree algorithm provided by the present disclosure. As Figure 7 shown, the method includes:

[0159] S701: Initialize the random tree, terrain information, and the allocation probability of the search strategy combination.

[0160] Specifically, when initializing the random tree, it is necessary to set the initial starting point, ending point of the route planning, and the initial value of the current search step size. Initializing the terrain information requires setting the obstacle positions and the equivalent geometric envelopes of the obstacles.

[0161] S702: Calculate the environmental complexity of the current node position.

[0162] Specifically, there may be multiple obstacles in the target area. By perceiving the obstacles in the target area, the terrain information of the target area can be obtained. According to the current node position and the obstacle-related parameters in the nearby area, the environmental complexity of the target area where the current node position is located can be determined.

[0163] S703: Determine the allocation probability of the search strategy combination based on the environmental complexity.

[0164] Under the condition that the environmental complexity meets different environmental complexity thresholds, the probability ratio of each strategy may be different. That is to say, the search strategy combination is determined by the environmental complexity allocation.

[0165] S704: Determine whether the environmental complexity is greater than the environmental complexity threshold.

[0166] Specifically, if so, go to S705; if not, it means that the probability of the current potential field guidance strategy cannot meet the route planning requirements, go to S706, and update the probability of the potential field guidance strategy.

[0167] S705: Determine whether the environmental complexity is greater than the alternation probability threshold.

[0168] Specifically, if so, go to S708; if not, it means that the probability of the current alternation search strategy cannot meet the route planning requirements, go to S707, and update the probability of the alternation search strategy.

[0169] S706: Update the probability of the potential field guidance strategy.

[0170] Specifically, based on the constraints of the preset search guidance conditions, the probability of the potential field guidance strategy is updated.

[0171] S707: Update the probability of the alternation search strategy.

[0172] Specifically, based on the constraints of preset search guidance conditions, the probability of the alternating search strategy is updated.

[0173] S708: Grow route nodes based on the random search strategy.

[0174] Specifically, after determining the probabilities of the potential field guidance strategy, the alternating search strategy, and the random search strategy, route nodes can be generated based on the random search strategy.

[0175] S709: Expand two random trees.

[0176] Specifically, based on the constraints of the alternating search strategy, the two random trees expand nodes alternately.

[0177] S710: Determine whether a collision with an obstacle occurs.

[0178] Specifically, if not, enter S712 to continue generating the random tree; if so, enter S711 to adjust the search step size to adapt to the current environmental conditions.

[0179] S711: Adaptively adjust the search step size.

[0180] Specifically, if there are multiple collisions with obstacles or multiple non-collisions occur, it indicates that the current search step size cannot meet the environmental conditions of the target area, and the search step size needs to be adjusted, and the probability distribution of the search strategy combination is re-allocated according to the updated search step size.

[0181] S712: Re-select the parent node and reconnect the child node according to the cost between the route nodes on the random tree.

[0182] Specifically, if the generated child node can be connected to its corresponding parent node, it means that the child node is selected correctly. If it cannot be connected, it means that the selection of the parent node may be incorrect, and the parent node needs to be re-selected and connected to the child node to form a random tree.

[0183] S713: Determine whether the two random trees are connected.

[0184] Specifically, if so, enter S714 to optimize the route obtained by connecting the random trees; if not, it means that there may be a calculation deviation in the environmental complexity, and enter S702 to re-estimate the current environmental complexity.

[0185] S714: Optimize the route obtained by connecting the random trees based on the greedy algorithm to obtain an optimized route.

[0186] Specifically, for partially redundant nodes, all nodes on the path are marked in the order from the starting point to the ending point, and then we will traverse all nodes in sequence to determine whether two nodes can be directly connected, and delete the redundant nodes to obtain an optimized route.

[0187] S715: Smooth the optimized route to obtain the target route.

[0188] Specifically, in this embodiment, the 3D Dubins path smoothing algorithm is used to smooth the optimized route, and the target route can be obtained. The route after smoothing is smoother and more accurate.

[0189] Figure 8 It is a schematic structural diagram of a route planning device based on an improved bidirectional rapidly-exploring random tree algorithm provided by the present disclosure. As Figure 8 shown, the route planning device 800 based on the improved bidirectional rapidly-exploring random tree algorithm includes: an acquisition module 810, a first determination module 820, a second determination module 830, and a generation module 840.

[0190] The acquisition module 810 is configured to acquire the current node position, the target node position, and the terrain information of the target area for route planning;

[0191] The first determination module 820 is configured to determine a search strategy combination for the target area according to the terrain information, where the search strategy combination is used to constrain the expansion direction of route nodes, and determine route nodes based on the improved bidirectional rapidly-exploring random tree algorithm;

[0192] The second determination module 830 is configured to determine a set of route nodes according to the current node position, the target node position, and the search strategy combination;

[0193] The generation module 840 is configured to optimize the route nodes in the set of route nodes to generate a target route, where the target route is a route that satisfies the motion constraints of a fixed-wing aircraft.

[0194] Optionally, the first determination module is configured to:

[0195] Determine the environmental complexity of the target area according to the terrain information and the current node position;

[0196] Determine the search strategy combination according to the environmental complexity and a preset search guiding condition.

[0197] Optionally, the first determination module is configured to:

[0198] Determine a first positional relationship based on the current node position, the geometric center parameters, equivalent shape parameters, and geometric envelope parameters of the first obstacle in the terrain information, where the first obstacle is the obstacle closest to the current node position in the target area, and the first positional relationship is the positional relationship between the first obstacle and the current node position;

[0199] Determine a second positional relationship based on the current node position, the geometric center parameters, equivalent shape parameters, and geometric envelope parameters of the second obstacle in the terrain information, where the second obstacle is the other obstacles in the target area except the first obstacle, and the second positional relationship is the positional relationship between the second obstacle and the current node position;

[0200] Determine the obstacle proximity based on the first positional relationship and the second positional relationship;

[0201] Determine the environmental complexity of the target area based on the obstacle proximity and a preset environmental weight.

[0202] Optionally, the second determination module is configured to:

[0203] Determine a distance correction factor based on the current node position and the target node position;

[0204] Determine a node guidance direction based on the distance correction factor, the current node position, and the potential field guidance strategy in the search strategy combination for the current node position and the target node position;

[0205] Determine an alternation frequency based on the environmental complexity and the alternating search strategy in the search strategy combination;

[0206] When it is determined that the search step size update condition is met, determine an updated search step size based on the current search step size and the random search strategy in the search strategy combination;

[0207] Determine the next route node based on the current node position, the alternation frequency, the updated search step size, and the node guidance direction;

[0208] Use the next route node as the current node, and repeat the steps of determining the distance correction factor, the node guidance direction, the alternation frequency, the updated search step size, and the next route node to determine the set of route nodes.

[0209] Optionally, the generation module is configured to:

[0210] Determine two connected random trees based on all the route nodes in the set of route nodes, where the random trees include multiple route nodes with collision-free paths;

[0211] Perform greedy optimization processing on the waypoint nodes of each of the collision-free paths to generate a first optimized route;

[0212] Perform path smoothing processing on the first optimized route to determine the target route.

[0213] Optionally, the generating module is configured to:

[0214] Obtain the maximum climb angle and the minimum turning radius of the fixed-wing aircraft;

[0215] Perform smoothing processing on the first optimized route according to the maximum climb angle and the minimum turning radius to determine the target route.

[0216] An embodiment of the present application also provides an electronic device to execute the above route planning method based on the improved bidirectional rapidly-exploring random tree algorithm. Please refer to Figure 9 It shows a schematic diagram of an electronic device provided by some embodiments of the present application. As Figure 9 shown, the electronic device 90 includes: a processor 900, a memory 901, a bus 902, and a communication interface 903. The processor 900, the communication interface 903, and the memory 901 are connected through the bus 902; a computer program that can run on the processor 900 is stored in the memory 901, and when the processor 900 runs the computer program, it executes the route planning method based on the improved bidirectional rapidly-exploring random tree algorithm provided by any of the foregoing embodiments of the present application.

[0217] Among them, the memory 901 may include a high-speed random access memory (RAM: Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 903 (which may be wired or wireless), a communication connection is realized between the device network element and at least one other network element, and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used.

[0218] The bus 902 may be an ISA bus, a PCI bus, an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 901 is used to store a program, and after receiving an execution instruction, the processor 900 executes the program. The route planning method based on the improved bidirectional rapidly-exploring random tree algorithm disclosed in any of the foregoing embodiments of the present application may be applied to the processor 900 or implemented by the processor 900.

[0219] The processor 900 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 900 or instructions in the form of software. The above-mentioned processor 900 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 901, and the processor 900 reads the information in the memory 901 and combines its hardware to complete the steps of the above method.

[0220] The electronic device provided in the embodiments of the present application and the route planning method based on the improved bidirectional rapidly-exploring random tree algorithm provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by them.

[0221] The embodiments of the present application also provide a computer-readable storage medium corresponding to the route planning method based on the improved bidirectional rapidly-exploring random tree algorithm provided in the foregoing embodiments. The shown computer-readable storage medium may be an optical disc, on which a computer program is stored. When the computer program is run by a processor, it will execute the route planning method based on the improved bidirectional rapidly-exploring random tree algorithm provided in any of the foregoing embodiments.

[0222] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here one by one.

[0223] The computer-readable storage medium provided by the above embodiments of the present application and the route planning method based on the improved bidirectional rapidly-exploring random tree algorithm provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0224] The embodiments of the present application also provide a computer program product 1000, as Figure 10 shown. The computer program product carries a computer program 1001, and the instructions included in the program code can be used to execute the steps of the route planning method based on the improved bidirectional rapidly-exploring random tree algorithm described in the above method embodiments. For details, reference can be made to the above method embodiments and will not be elaborated here.

[0225] Among them, the above computer program product can be specifically implemented in the form of hardware, software, or a combination thereof. In an alternative embodiment, the computer program product is specifically embodied as a computer storage medium. In another alternative embodiment, the computer program product is specifically embodied as a software product, such as a Software Development Kit (SDK), etc.

[0226] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are only examples and not limitations. It cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present disclosure. In addition, the above disclosed specific details are only for illustrative purposes and for easy understanding, rather than limitations. The above details do not limit the present disclosure to necessarily adopt the above specific details for implementation.

[0227] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present disclosure are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms, meaning "including but not limited to", and can be used interchangeably with each other. The words "or" and "and" used herein refer to the word "and / or" and can be used interchangeably with each other, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with each other.

[0228] In addition, as used herein, the "or" used in the listing of items starting with "at least one" indicates a separate listing, so that for example, the listing of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). In addition, the term "exemplary" does not mean that the described examples are preferred or better than other examples.

[0229] It should also be noted that in the systems and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present disclosure.

[0230] Various changes, substitutions, and alterations to the technologies described herein can be made without departing from the teachings defined by the appended claims. In addition, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and acts described above. Processes, machines, manufactures, compositions of events, means, methods, or acts that currently exist or will later be developed and that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Accordingly, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or acts within their scope.

[0231] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0232] The above description has been presented for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although several example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims

1. A route planning method based on an improved bidirectional fast random exploration tree algorithm, characterized in that: include: Obtain the current node position, target node position and terrain information of the target area of ​​route planning; Determine a search strategy combination for the target area according to the terrain information, wherein the search strategy combination is used to constrain the expansion direction of the route nodes, and determine the route nodes based on an improved bidirectional fast random exploration tree algorithm; Determine a route node set according to the current node position, the target node position and the search strategy combination; The path nodes in the path node set are optimized to generate a target path, where the target path is a path that satisfies the motion constraints of the fixed-wing aircraft.

2. The method according to claim 1, characterized in that Determining the search strategy combination of the target area according to the terrain information includes: Determining the environmental complexity of the target area according to the terrain information and the current node position; The search strategy combination is determined according to the environmental complexity and preset search guidance conditions.

3. The method according to claim 2, characterized in that The determining the environmental complexity of the target area according to the terrain information and the current node position includes: Determine a first position relationship according to the current node position, a geometric center parameter, an equivalent shape parameter, and a geometric envelope parameter of a first obstacle in the terrain information, wherein the first obstacle is an obstacle in the target area that is closest to the current node position, and the first position relationship is a position relationship between the first obstacle and the current node position; determining a second positional relationship according to the current node position, a geometric center parameter, an equivalent shape parameter, and a geometric envelope parameter of a second obstacle in the terrain information, wherein the second obstacle is an obstacle other than the first obstacle in the target area, and the second positional relationship is a positional relationship between the second obstacle and the current node position; Determining the degree of proximity of an obstacle according to the first position relationship and the second position relationship; The environmental complexity of the target area is determined according to the obstacle proximity and a preset environmental weight.

4. The method according to claim 2, characterized in that: The determining of the route node set according to the current node position, the target node position and the search strategy combination includes: Determining a distance correction factor according to the current node position and the target node position; Determine a node guidance direction according to the potential field guidance strategy in the search strategy combination of the distance correction factor, the current node position and the target node position; Determining an alternating frequency according to the environmental complexity and an alternating search strategy in the search strategy combination; When it is determined that the search step length update condition is met, determining an updated search step length according to the current search step length and a random search strategy in the search strategy combination; Determine the next route node according to the current node position, the alternating frequency, the update search step length and the node guidance direction; The next route node is taken as the current node, and the steps of determining the distance correction factor, the node guidance direction, the alternation frequency, the update search step length and the next route node are repeated to determine the route node set.

5. The method according to claim 1, characterized in that The step of optimizing the route nodes in the route node set to generate a target route includes: Determine two connected random trees according to all the route nodes in the route node set, wherein the random trees include a plurality of route nodes with no collision paths; Performing greedy optimization processing on each route node of the collision-free path to generate a first optimized route; Perform path smoothing processing on the first optimized route to determine the target route.

6. The method according to claim 5, characterized in that The performing path smoothing processing on the first optimized route to determine the target route includes: Obtaining the maximum climb angle and minimum turning radius of the fixed-wing aircraft; The first optimized route is smoothed according to the maximum climb angle and the minimum turning radius to determine the target route.

7. A route planning device based on an improved bidirectional fast random exploration tree algorithm, characterized in that: include: The acquisition module is used to obtain the current node position, target node position and terrain information of the target area of ​​route planning; A first determination module is used to determine a search strategy combination for the target area according to the terrain information, wherein the search strategy combination is used to constrain the expansion direction of the route nodes and determine the route nodes based on an improved bidirectional fast random exploration tree algorithm; A second determination module, configured to determine a route node set according to the current node position, the target node position and the search strategy combination; The generation module is used to optimize the route nodes in the route node set to generate a target route, where the target route is a route that satisfies the motion constraints of the fixed-wing aircraft.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor runs the computer program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code, and when the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes any one of claims 1 to 6.

Images