Path planning methods, electronic devices and storage media

Abstract

This invention relates to the field of path planning technology, specifically to path planning methods, electronic devices, and storage media. The method includes obtaining the next optional sampling point from the current location; when the next optional sampling point is within a preset range of a target obstacle, determining the angle between the current sampling path and the target obstacle based on the current sampling path and the orientation of the target obstacle, wherein the current sampling path is the path formed by the current location and the next optional sampling point; and planning a path through the target obstacle based on the difference between the angle and a preset travel angle to determine the target path. Using the preset travel angle as the ideal travel angle for path planning improves walking safety when traversing target obstacles.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, specifically to path planning methods, electronic devices, and storage media. Background Technology

[0002] In the field of mobile robotics, it's generally necessary to pre-build an obstacle map so that the mobile robot can plan its path during self-movement. Existing path planning methods typically involve bypassing obstacles, but the ground often contains ditches and other obstacles, making this bypass method not always the optimal path. Therefore, the mobile robot needs to be able to traverse the obstacle during path planning. However, if the robot attempts to pass at an angle, it may encounter a probability of being unable to pass. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a path planning method, an electronic device, and a storage medium to solve the path planning problem of target obstacles.

[0004] According to a first aspect, embodiments of the present invention provide a path planning method, comprising:

[0005] Get the next possible sampling point at the current location;

[0006] When the next optional sampling point is within a preset range of the target obstacle, the angle between the current sampling path and the target obstacle is determined based on the current sampling path and the posture of the target obstacle. The current sampling path is the path formed by the current position point and the next optional sampling point.

[0007] The path through the target obstacle is planned based on the difference between the included angle and the preset passage angle, and the target path is determined.

[0008] The path planning method provided in this invention, when walking to a preset range of a target obstacle, determines the angle between the current sampled path and the target obstacle, obtains the difference between the angle and a preset passage angle, and then performs path planning based on the difference. In the path planning process, the angle between the current sampled path and the target obstacle is taken into consideration, and the preset passage angle is used as the ideal passage angle for path planning. Therefore, the angle is compared with the preset passage angle, and path planning is performed on this basis, which improves the walking safety when passing through the target obstacle.

[0009] In some implementations, when the next selectable sampling point is within a preset range of the target obstacle, determining the angle between the current sampling path and the target obstacle based on the current sampling path and the pose of the target obstacle includes:

[0010] Obtain a semantic map, which is marked with the position and attitude angle of the target obstacle;

[0011] Determine the distance between the next optional sampling point and the target obstacle in the semantic map;

[0012] When the next selectable sampling point is within a preset range of the target obstacle, the angle between the current sampling path and the target obstacle is calculated based on the attitude angle of the target obstacle.

[0013] The path planning method provided in this invention marks target obstacles in a semantic map, which allows the semantic annotation results to be combined during the path planning process, thereby improving the accuracy of the angle between the determined current sampling path and the target obstacle.

[0014] In some implementations, calculating the angle between the current sampling path and the target obstacle based on the attitude angle of the target obstacle includes:

[0015] Obtain the attitude angle of the current sampling path;

[0016] Calculate the difference between the attitude angle of the current sampling path and the attitude angle of the target obstacle to determine the included angle.

[0017] In some implementations, the step of planning the path through the target obstacle based on the difference between the included angle and a preset passage angle, and determining the target path, includes:

[0018] The penalty is determined based on the difference between the included angle and the preset passage angle;

[0019] Based on the penalty term, a path is planned to pass through the target obstacle, and the target path is determined.

[0020] The path planning method provided in this embodiment of the invention uses the difference between the angle between the current sampling path and the target obstacle and the preset passage angle to determine the penalty term of the current sampling path, and plans the path through the target obstacle based on the penalty term. Since the penalty term introduces the difference between the angle and the preset passage angle, the penalty term is applied to the next optional sampling point that does not meet the preset passage angle, so that a better target path through the target obstacle can be selected, thereby ensuring that the target obstacle can be passed at the preset passage angle.

[0021] In some implementations, determining the penalty term for the current sampling path based on the difference between the included angle and the preset passage angle includes:

[0022] Obtain the penalty coefficient;

[0023] The penalty term for the current sampling path is determined by multiplying the penalty coefficients based on the absolute value of the difference.

[0024] The path planning method provided in this embodiment of the invention introduces a penalty coefficient, which enables the calculation results of the penalty term to meet the needs of different scenarios, thus expanding the application scope of the path planning method.

[0025] In some implementations, before the step of determining the penalty term for the current sampling path based on the difference between the included angle and the preset passage angle, the method includes:

[0026] When the included angle is less than the angle threshold, the next selectable sampling point is discarded.

[0027] The path planning method provided in this embodiment of the invention indicates that the next selectable sampling point with an included angle less than the angle threshold is obviously unable to pass through the target obstacle, and discarding it can reduce the amount of data processing and improve the efficiency of path planning.

[0028] In some implementations, planning the path through the target obstacle based on the penalty term to determine the target path includes:

[0029] Obtain the cost of the next possible location point, the cost of which is determined based on the distance between the next possible location point and the obstacle;

[0030] The cost value is combined with the penalty term to determine the target cost value of the next selectable location point;

[0031] Based on the target cost value, a path is planned to pass through the target obstacle, and the target path is determined.

[0032] The path planning method provided in this invention uses the value to represent the distance to obstacles. When planning a path, it not only considers surrounding obstacles but also incorporates a penalty term for the target obstacle, which can further improve the accuracy of the determined target path.

[0033] In some implementations, planning the path through the target obstacle based on the target cost value to determine the target path includes:

[0034] Calculate the heuristic value in the hybrid A-Star algorithm based on the target cost value;

[0035] The candidate sampling point corresponding to the smallest heuristic value is selected from the heuristic values;

[0036] The candidate sampling point is determined as the next target sampling point of the current location point to determine the target path.

[0037] The path planning method provided in this invention applies a penalty term to the sampled path of the hybrid A* algorithm, so that the target path planned by the hybrid A* algorithm satisfies both the kinematic constraints of the mobile robot and the requirement to pass through the target obstacle.

[0038] According to a second aspect, embodiments of the present invention also provide a path planning apparatus, comprising:

[0039] The acquisition module is used to obtain the next optional sampling point at the current location.

[0040] The first determining module is used to determine the angle between the current sampling path and the target obstacle based on the current sampling path and the posture of the target obstacle when the next optional sampling point is located within a preset range of the target obstacle. The current sampling path is the path formed by the current position point and the next optional sampling point.

[0041] The second determining module is used to plan the path through the target obstacle based on the difference between the included angle and the preset passage angle, and to determine the target path.

[0042] According to a third aspect, embodiments of the present invention provide an electronic device, including: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the path planning method described in the first aspect or any embodiment of the first aspect.

[0043] According to a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing computer instructions for causing the computer to perform the path planning method described in the first aspect or any embodiment of the first aspect.

[0044] It should be noted that the corresponding beneficial effects of the path planning device, electronic device and computer-readable storage medium provided in the embodiments of the present invention can be found in the description of the corresponding beneficial effects of the path planning method above, and will not be repeated here. Attached Figure Description

[0045] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0046] Figure 1 This is an optional path through the target obstacle according to an embodiment of the present invention;

[0047] Figure 2 This is a flowchart of a path planning method according to an embodiment of the present invention;

[0048] Figure 3 This is a flowchart of a path planning method according to an embodiment of the present invention;

[0049] Figure 4 This is a flowchart of a path planning method according to an embodiment of the present invention;

[0050] Figure 5 This is a structural block diagram of a path planning device according to an embodiment of the present invention;

[0051] Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] The path planning method provided in this invention optimizes the path through a target obstacle, enabling a mobile robot to pass through the obstacle at a preset passage angle. The preset passage angle is determined based on the dimensions of the mobile robot and the target obstacle; that is, when the mobile robot passes the target obstacle at an angle, the preset passage angle ensures that the front and rear wheels of the mobile robot are positioned on opposite sides of the target obstacle. In some optional embodiments, the preset passage angle is 90 degrees, meaning the mobile robot passes the target obstacle perpendicularly. It should be noted that the specific value of the preset passage angle is not limited in this invention; its value is determined based on the dimensions of the mobile robot and the target obstacle.

[0054] Figure 1 The diagram shows several possible paths for the mobile robot to traverse the target obstacle. The straight line with an arrow in the middle represents the optimal path, meaning the mobile robot travels at an angle perpendicular to the target obstacle.

[0055] The electronic device used to execute the path planning method described in this embodiment of the invention can be a mobile robot or a host computer, such as a server, that is communicatively connected to the mobile robot. If the electronic device is a host computer, the mobile robot communicates with the host computer during its movement, and the host computer determines the target path for the mobile robot to pass through the target obstacle and sends the target path to the mobile robot. Accordingly, the mobile robot passes through the target obstacle based on the target path. The types of mobile robots include, but are not limited to, commercial cleaning robots, self-propelled robots, guided robots, etc., and there are no specific limitations on the specific type.

[0056] It should be noted that the target obstacle in this embodiment of the invention does not refer to a specific target obstacle, but rather to all target obstacles within the path planning area. Target obstacles include, but are not limited to, obstacles such as ditches and embankments.

[0057] According to an embodiment of the present invention, a path planning method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0058] This embodiment provides a path planning method that can be used in the aforementioned electronic devices, such as mobile robots, servers, cleaning robots, etc. Figure 2 This is a flowchart of a path planning method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0059] S11, obtain the next optional sampling point for the current position.

[0060] The next optional sampling point is the sampling point calculated by the electronic device through a path planning algorithm, which is used as the optional sampling point for the current position. The path planning algorithm includes, but is not limited to, hybrid A* algorithm, A* algorithm, etc., and is specifically set according to actual needs.

[0061] S12, when the next selectable sampling point is within the preset range of the target obstacle, determine the angle between the current sampling path and the target obstacle based on the current sampling path and the posture of the target obstacle.

[0062] Wherein, the current sampling path is the path formed by the current location point and the next optional sampling point;

[0063] The target obstacle is pre-marked on the map, including its position and orientation. The orientation of the target obstacle includes its length, width, and orientation angle on the map. Since the next optional sampling point is calculated using a path planning algorithm, its position on the map is known. By comparing the next optional sampling point with the position of the target obstacle, it can be determined whether the next optional sampling point is within the target obstacle's preset range. For example, the distance between the next optional sampling point and the target obstacle can be calculated, and the distance can be used to determine if it is within the target obstacle's preset range; or, the preset range of the target obstacle is pre-marked on the map, and the next optional sampling point can be determined by checking if it is within this preset range.

[0064] When the next selectable sampling point is within the preset range of the target obstacle, it indicates that the mobile robot is about to pass through the target obstacle, and the path through the target obstacle needs to be optimized. The electronic device first uses the current sampling path formed by the current position point and the next selectable sampling point to calculate the angle between the current sampling path and the target obstacle. The direction of the current sampling path is determined, that is, its attitude angle in the map is determined, and the attitude of the target obstacle also includes its attitude angle in the map. Therefore, the angle between the current sampling path and the target obstacle can be calculated using these two attitude angles.

[0065] S13, based on the difference between the included angle and the preset passage angle, plans the path through the target obstacle and determines the target path.

[0066] The preset passage angle is the angle at which the mobile robot can safely pass through the target obstacle. To ensure the mobile robot can safely pass through the target obstacle, the angle at which the mobile robot passes through the target obstacle needs to be optimized to be as close as possible to the preset passage angle. Based on this, the difference between the included angle determined in S12 and the preset passage angle is calculated, and path planning is performed based on this difference to determine the target path through the target obstacle.

[0067] Path planning based on this difference can be achieved by obtaining the absolute value of the difference, comparing it with a threshold, and then performing path planning based on the comparison result. The threshold is the maximum value of the difference. If the absolute value of the difference is greater than the threshold, the current sampling path is discarded, meaning the next sampling point forming the current sampling path is discarded. If the absolute value of the difference is less than or equal to the threshold, the next sampling point forming the current sampling path is retained. After threshold filtering, the remaining next sampling points are used to calculate the target path using a path planning algorithm.

[0068] Path planning can be performed based on this difference, or a penalty term can be calculated for the current sampled path, and then the path planning algorithm can be used to determine the target path based on the penalty term. A larger difference indicates a greater gap between the current sampled path and the ideal path, resulting in a larger penalty term; conversely, a smaller difference indicates a smaller gap between the current sampled path and the ideal path, resulting in a smaller penalty term. The penalty term is a value derived from the difference between the angle between the current sampled path and the target obstacle and a preset travel angle; it can also be understood as a penalty value for the current sampled path. This penalty term is used to adjust the probability of selecting the current sampled path in path planning, thereby ensuring that the angle between the target path and the target obstacle is the preset travel angle.

[0069] For path planning algorithms, the next possible sampling point calculated from the current position can be one or more, etc. If there are multiple next possible sampling points, then the penalty term for the current sampling path corresponding to each next possible sampling point is determined here.

[0070] The path planning method provided in this embodiment, when walking to a preset range of a target obstacle, determines the angle between the current sampling path and the target obstacle, obtains the difference between the angle and a preset passage angle, and then performs path planning based on the difference. In the path planning process, the angle between the current sampling path and the target obstacle is taken into consideration, and the preset passage angle is used as the ideal passage angle for path planning. Therefore, the angle is compared with the preset passage angle, and path planning is performed on this basis, which improves the walking safety when passing through the target obstacle.

[0071] This embodiment provides a path planning method that can be used in the aforementioned electronic devices, such as mobile robots, servers, cleaning robots, etc. Figure 3 This is a flowchart of a path planning method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0072] S21, obtain the next optional sampling point for the current location.

[0073] Please see details Figure 2 S11 of the illustrated embodiment will not be described again here.

[0074] S22, when the next selectable sampling point is within the preset range of the target obstacle, determine the angle between the current sampling path and the target obstacle based on the current sampling path and the posture of the target obstacle.

[0075] Wherein, the current sampling path is the path formed by the current location point and the next optional sampling point;

[0076] Specifically, S22 includes:

[0077] S221, Obtain the semantic map.

[0078] The semantic map is marked with the location and attitude angle of the target obstacle.

[0079] By marking target obstacles in a semantic map, mobile robots can anticipate encountering them. The method for acquiring the semantic map is not limited here; it can be configured according to specific needs.

[0080] S222, Determine the distance between the next optional sampling point and the target obstacle in the semantic map.

[0081] As mentioned above, the location of the target obstacle is fixed on the map, while the location of the next optional sampling point is calculated using a path planning algorithm and is also fixed. Therefore, the distance between the next optional sampling point and the target obstacle can be calculated based on these two fixed locations.

[0082] S223, when the next selectable sampling point is within the preset range of the target obstacle, calculate the angle between the current sampling path and the target obstacle based on the attitude angle of the target obstacle.

[0083] By comparing the calculated distance with a preset value, it can be determined whether the next optional sampling point is within the preset range of the target obstacle. If the calculated distance is less than the preset value, it means that the next optional sampling point is within the preset range of the target obstacle. At this time, the electronic device uses the attitude angle of the target obstacle to calculate the angle between the current sampling path and the target obstacle.

[0084] In some embodiments, S223 includes:

[0085] (1) Obtain the attitude angle of the current sampling path.

[0086] (2) Calculate the difference between the attitude angle of the current sampling path and the attitude angle of the target obstacle, and determine the included angle.

[0087] As mentioned above, the attitude angle of the current sampling path is calculated based on the current position and the position of the next sampling point. The difference between the attitude angle of the current sampling path and the attitude angle of the target obstacle is determined as the angle between the current sampling path and the target obstacle.

[0088] S23, based on the difference between the included angle and the preset passage angle, plan the path through the target obstacle and determine the target path.

[0089] Specifically, S23 above includes:

[0090] S231, Based on the difference between the included angle and the preset passage angle, determine the penalty term for the current sampling path.

[0091] The penalty term can be the absolute value of the difference, or it can be the absolute value of the difference combined with a penalty term coefficient, to adapt to the needs of path planning with different precision.

[0092] In some embodiments, S231 includes:

[0093] (1) Obtain the penalty coefficient.

[0094] The specific value of the penalty coefficient is determined based on the actual usage scenario. For example, in scenarios with high accuracy requirements, a larger constant is set for the penalty coefficient; in scenarios with low accuracy requirements, a smaller constant is set for the penalty coefficient.

[0095] (2) Determine the penalty term for the current sampling path based on the product of the absolute value penalty coefficients of the difference.

[0096] The penalty term is calculated using the following formula: cost = K * |θ - pit_angle - α|.

[0097] Where cost is the penalty term, K is the penalty coefficient, θ is the attitude angle of the current sampling path, pit_angle is the attitude angle of the target obstacle, and α is the preset passage angle.

[0098] S232, Based on the penalty term, plan the path through the target obstacle and determine the target path.

[0099] The penalty term for the current sampling path is the absolute value of the above difference. For the path planning algorithm, the next possible sampling point for the current position can be one or more, etc. If there are multiple next possible sampling points, then the penalty term for the current sampling path corresponding to each next possible sampling point is determined here.

[0100] After obtaining the penalty term for the current sampled path, path planning continues based on this penalty term. That is, the calculated penalty term is incorporated into the path planning algorithm described above to determine the target path that passes through the target obstacle. Specifically, the penalty term is considered when using different path planning algorithms for calculation.

[0101] For example, after planning the path to the target obstacle, at least one path is obtained, and each path has a corresponding cost. The path with the lowest cost is selected as the target path. Here, the cost represents the price to be paid for each path, and its specific value is related to other obstacles within the path planning area and the penalty for each path at the target obstacle.

[0102] Alternatively, if the path planning algorithm used is a genetic algorithm, this penalty term is introduced when calculating the fitness to obtain the fitness of the current sampling path corresponding to each next optional sampling point, thereby filtering each next sampling path point and finally determining the target path.

[0103] It should be noted that when the penalty term is incorporated into the path planning algorithm, the specific integration method is related to the path planning algorithm used, and is not limited to the cost or fitness in the path planning algorithm mentioned above.

[0104] In some implementations, step S23 above is preceded by: discarding the next selectable sampling point when the included angle is less than an angle threshold. The angle threshold is the minimum angle at which the mobile robot can pass through the target obstacle. When the included angle is less than the angle threshold, it indicates that the mobile robot cannot pass through the target obstacle. That is, the current sampling path is considered impassable, and the next selectable sampling point is discarded.

[0105] For the next selectable sampling point whose included angle is less than the angle threshold, it means that it is obviously impossible to pass through the target obstacle. Discarding it can reduce the amount of data processing and improve the efficiency of path planning.

[0106] The path planning method provided in this embodiment marks target obstacles in a semantic map, enabling the path planning process to incorporate the results of semantic annotation, thereby improving the accuracy of the angle between the determined current sampling path and the target obstacle. Simultaneously, the introduction of a penalty coefficient allows the calculation results of the penalty term to meet the needs of different scenarios, expanding the application scope of this path planning method. The penalty term for the current sampling path is determined using the difference between the angle between the current sampling path and the target obstacle and a preset passage angle. Based on this penalty term, a path passing through the target obstacle is planned. Since the penalty term incorporates the difference between the angle and the preset passage angle, a penalty term is applied to the next selectable sampling point that does not meet the preset passage angle, ensuring that a better target path passing through the target obstacle can be selected, thus guaranteeing that the target obstacle can be passed at the preset passage angle.

[0107] This embodiment provides a path planning method that can be used in the aforementioned electronic devices, such as mobile robots, servers, cleaning robots, etc. Figure 4 This is a flowchart of a path planning method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps:

[0108] S31, obtain the next optional sampling point for the current position.

[0109] Please see details Figure 2 S11 of the illustrated embodiment will not be described again here.

[0110] S32, when the next selectable sampling point is within the preset range of the target obstacle, determine the angle between the current sampling path and the target obstacle based on the current sampling path and the posture of the target obstacle.

[0111] Wherein, the current sampling path is the path formed by the current location point and the next optional sampling point;

[0112] Please see details Figure 3 S22 of the illustrated embodiment will not be described again here.

[0113] S33, based on the difference between the included angle and the preset passage angle, plans the path through the target obstacle and determines the target path.

[0114] Specifically, S34 includes:

[0115] S341, Based on the difference between the included angle and the preset passage angle, determine the penalty term for the current sampling path.

[0116] Please see details Figure 3 S231 of the illustrated embodiment will not be described again here.

[0117] S342, obtain the cost of the next optional sampling point.

[0118] The cost value is determined based on the distance between the next selectable sampling point and the obstacle.

[0119] The cost value of each location point within the planning area is represented by a cost map, which is a grid map. Each location point on the map has a certain cost value; the closer to an obstacle, the greater the cost value, and the farther away from an obstacle, the smaller the cost value. By querying this cost map based on the next possible sampling point, the cost value of the next possible sampling point can be determined.

[0120] S343 integrates the cost value with the penalty term to determine the target cost value for the next selectable sampling point.

[0121] The fusion of the cost value and the penalty term can be achieved by calculating the sum of the cost value and the penalty term, or by weighted calculation, etc. In this case, fusing the cost value and the penalty term determines the target cost value for the next possible location point.

[0122] S344: Based on the target cost, plan the path through the target obstacle to determine the target path.

[0123] The electronic device calculates the path planning algorithm based on the target cost, plans the path through the target obstacle, and determines the target path through the target obstacle.

[0124] In some implementations, S344 includes:

[0125] (1) Heuristic values ​​in the hybrid A-star algorithm based on target value calculation.

[0126] (2) Select the candidate sampling point corresponding to the smallest heuristic value from the heuristic values.

[0127] (3) Determine the candidate sampling point as the next target sampling point of the current location point in order to determine the target path.

[0128] The hybrid A* algorithm only considers the kinematics of the mobile robot and does not take into account the actual semantic information. Therefore, in this embodiment, the hybrid A* algorithm is constrained by the target obstacle to ensure that the searched path meets the requirement of passing the target obstacle. The process of using the hybrid A* algorithm is as follows:

[0129] Motion model of mobile robot:

[0130] v x =vcos(θ)

[0131] v y =vsin(θ)

[0132]

[0133] Where v is the forward velocity of the mobile robot. Let be the steering angle of the mobile robot, and l be the axle distance between the front and rear wheels. The iterative equation for the mobile robot can be obtained through integration:

[0134] x = x + v x *t

[0135] y = y + v y *t

[0136] yaw = yaw + w*t

[0137] Where (x, y) is the position of the mobile robot, v x ,v y These represent the x-axis velocity and y-axis velocity of the mobile robot, respectively, while yaw represents the robot's posture.

[0138] Control quantity sampling for mobile robots involves sampling the robot's forward velocity, steering angle, and motion time. Assuming the velocity sampling density is 1 / k1, the steering angle sampling density is 1 / k2, and the motion time sampling density is 1 / k3, and assuming C(v, φ) is the set of sampled control quantities and T is the set of sampled time values, then the corresponding set of control quantities and sampled time values ​​can be obtained through sampling.

[0139] After obtaining the velocity, turning angle, and motion time, substituting them into the iterative equation above, the position of the mobile robot in the next state can be obtained. During the process, if the sampling path of the mobile robot passes through the target obstacle, and if the angle between the sampling path and the target obstacle is less than the angle threshold, then the sampling path is considered impassable, and this sampling point is discarded.

[0140] During the sampling process, a penalty term is applied to the attitude of the sampled path. This penalty term is then fused with the cost value and added to the heuristic function calculation in the Hybrid A* algorithm. The Hybrid A* algorithm then selects the candidate point with the smallest heuristic value in the next iteration. Because a penalty term is added to the planned path, a better extended path through the target obstacle is selected. This step ensures that the planned path better meets the preset passage angle. The remaining steps are consistent with the Hybrid A* algorithm.

[0141] A penalty term is applied to the sampling path of the hybrid A* algorithm so that the target path planned by the hybrid A* algorithm satisfies both the kinematic constraints of the mobile robot and the requirement to pass through the target obstacle.

[0142] The path planning method provided in this embodiment uses the value to represent the distance between the path and the obstacle. When planning the path, it not only takes into account the surrounding obstacles, but also the penalty for the target obstacle, which can further improve the accuracy of the determined target path.

[0143] This embodiment also provides a path planning device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0144] This embodiment provides a path planning device, such as Figure 5 As shown, it includes:

[0145] Module 41 is used to obtain the next optional sampling point of the current position.

[0146] The first determining module 42 is used to determine the angle between the current sampling path and the target obstacle based on the current sampling path and the posture of the target obstacle when the next optional sampling point is located within a preset range of the target obstacle. The current sampling path is the path formed by the current position point and the next optional sampling point.

[0147] The second determining module 43 is used to plan the path through the target obstacle based on the difference between the included angle and the preset passage angle, and to determine the target path.

[0148] In some implementations, when the next selectable sampling point is located within a preset range of the target obstacle, the first determining module 42 includes:

[0149] The first acquisition unit is used to acquire a semantic map, wherein the position and attitude angle of the target obstacle are marked in the semantic map;

[0150] The first determining unit is configured to determine the distance between the next optional sampling point and the target obstacle in the semantic map;

[0151] The calculation unit is used to calculate the angle between the current sampling path and the target obstacle based on the attitude angle of the target obstacle when the next selectable sampling point is located within a preset range of the target obstacle.

[0152] In some implementations, the computing unit includes:

[0153] The first acquisition subunit is used to acquire the attitude angle of the current sampling path;

[0154] The first calculation subunit is used to calculate the difference between the attitude angle of the current sampling path and the attitude angle of the target obstacle, and to determine the included angle.

[0155] In some implementations, the second determining module 43 includes:

[0156] The penalty item determination unit is used to determine the penalty item based on the difference between the included angle and the preset passage angle;

[0157] A path planning unit is used to plan a path through the target obstacle based on the penalty term, and to determine the target path.

[0158] In some implementations, the penalty determination unit includes:

[0159] The second acquisition subunit is used to acquire the penalty coefficient;

[0160] The first determining subunit is used to determine the penalty term of the current sampling path based on the product of the penalty coefficients and the absolute value of the difference.

[0161] In some embodiments, the device further includes:

[0162] The discard module is used to discard the next selectable sampling point when the included angle is less than the angle threshold.

[0163] In some implementations, the path planning unit includes:

[0164] The third acquisition subunit is used to acquire the cost value of the next optional sampling point, the cost value being determined based on the distance between the next optional sampling point and the obstacle;

[0165] A fusion unit is used to fuse the cost value with the penalty term to determine the target cost value of the next optional sampling point;

[0166] The planning subunit is used to plan the path through the target obstacle based on the target cost value, and to determine the target path.

[0167] In some implementations, the planning subunit includes:

[0168] The second computational subunit is used to calculate the heuristic value in the hybrid A-Star algorithm based on the target cost value;

[0169] A filtering subunit is used to filter out the candidate sampling point corresponding to the smallest heuristic value from the heuristic values;

[0170] The second determining subunit is used to determine the candidate sampling point as the next target sampling point of the current position point, so as to determine the target path.

[0171] The path planning device in this embodiment is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0172] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0173] This invention also provides an electronic device having the above-described features. Figure 5 The path planning device shown.

[0174] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an optional embodiment of the present invention, such as... Figure 6As shown, the electronic device may include: at least one processor 51, such as a CPU (Central Processing Unit), at least one communication interface 53, memory 54, and at least one communication bus 52. The communication bus 52 is used to enable communication between these components. The communication interface 53 may include a display screen or a keyboard; optionally, the communication interface 53 may also include a standard wired interface or a wireless interface. The memory 54 may be high-speed RAM (Random Access Memory) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 54 may also be at least one storage device located remotely from the aforementioned processor 51. The processor 51 may be combined with... Figure 5 The described apparatus has an application program stored in memory 54, and the processor 51 calls the program code stored in memory 54 to perform any of the above method steps.

[0175] The communication bus 52 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 52 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0176] The memory 54 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 54 may also include a combination of the above types of memory.

[0177] The processor 51 can be a central processing unit (CPU), a network processor (NP), or a combination of CPU and NP.

[0178] The processor 51 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0179] Optionally, memory 54 is also used to store program instructions. Processor 51 can invoke program instructions to implement the path planning method as shown in any embodiment of this application.

[0180] This invention also provides a non-transitory computer storage medium storing computer-executable instructions that can execute the path planning method in any of the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0181] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A path planning method, characterized in that, include: Get the next possible sampling point at the current location; When the next optional sampling point is within a preset range of the target obstacle, the angle between the current sampling path and the target obstacle is determined based on the current sampling path and the posture of the target obstacle. The current sampling path is the path formed by the current position point and the next optional sampling point. The path through the target obstacle is planned based on the difference between the included angle and the preset passage angle, and the target path is determined.

2. The method according to claim 1, characterized in that, When the next selectable sampling point is within a preset range of the target obstacle, determining the angle between the current sampling path and the target obstacle based on the current sampling path and the pose of the target obstacle includes: Obtain a semantic map, which is marked with the position and attitude angle of the target obstacle; Determine the distance between the next optional sampling point and the target obstacle in the semantic map; When the next selectable sampling point is within a preset range of the target obstacle, the angle between the current sampling path and the target obstacle is calculated based on the attitude angle of the target obstacle.

3. The method according to claim 2, characterized in that, The calculation of the angle between the current sampling path and the target obstacle based on the attitude angle of the target obstacle includes: Obtain the attitude angle of the current sampling path; Calculate the difference between the attitude angle of the current sampling path and the attitude angle of the target obstacle to determine the included angle.

4. The method according to claim 1, characterized in that, The step of planning a path through the target obstacle based on the difference between the included angle and the preset passage angle, and determining the target path, includes: The penalty is determined based on the difference between the included angle and the preset passage angle; Based on the penalty term, a path is planned to pass through the target obstacle, and the target path is determined.

5. The method according to claim 4, characterized in that, The penalty term for determining the current sampling path based on the difference between the included angle and the preset passage angle includes: Obtain the penalty coefficient; The penalty term for the current sampling path is determined by multiplying the penalty coefficients based on the absolute value of the difference.

6. The method according to claim 4, characterized in that, Before the step of determining the penalty term for the current sampling path based on the difference between the included angle and the preset passage angle, the following steps are included: When the included angle is less than the angle threshold, the next selectable sampling point is discarded.

7. The method according to any one of claims 4-6, characterized in that, The step of planning the path through the target obstacle based on the penalty term and determining the target path includes: Obtain the cost of the next possible location point, the cost of which is determined based on the distance between the next possible location point and the obstacle; The cost value is combined with the penalty term to determine the target cost value of the next selectable location point; Based on the target cost value, a path is planned to pass through the target obstacle, and the target path is determined.

8. The method according to claim 7, characterized in that, The step of planning a path through the target obstacle based on the target cost value and determining the target path includes: Calculate the heuristic value in the hybrid A-Star algorithm based on the target cost value; The candidate sampling point corresponding to the smallest heuristic value is selected from the heuristic values; The candidate sampling point is determined as the next target sampling point of the current location point to determine the target path.

9. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the path planning method of any one of claims 1-8 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the path planning method according to any one of claims 1-8.

Images