Path planning method and device, electronic equipment and readable storage medium

Abstract

The embodiment of the invention provides a path planning method and device, electronic equipment and a readable storage medium, and the method comprises the steps: generating a first random number for any round of path exploration, and determining a target exploration strategy corresponding to the round of path exploration based on the first random number and a target probability value corresponding to the round of path exploration; based on the target exploration strategy and the current exploration node, determining a target growth point corresponding to the route exploration of this round; and under the condition that a preset ending condition is met, a target path is determined based on the target growing point corresponding to each round of path exploration. Thus, by avoiding the situation of being limited to one path exploration mode and falling into local optimum or excessive random exploration, balance between randomness and directivity of path exploration is achieved through the first random number and the target probability value, and then different target exploration strategies are selected, so that path exploration efficiency is improved. In this way, the path exploration process is easier to explore in the correct direction, and the efficiency and precision of path planning are further improved.

Description

Technical Field

[0001] The present invention relates to the field of path planning technology, and in particular to a path planning method, device, electronic device and readable storage medium. Background Art

[0002] The current status of mobile robots' path planning based on maps is diversified and highly developed. With the continuous advancement of technology, path planning algorithms are becoming more mature and can cope with various complex environments.

[0003] In related technologies, in order for a mobile robot to plan an optimal path to reach the target based on a known map, it needs to be equipped with sensors such as lidar, sonar, GPS, monocular and binocular cameras to obtain environmental information and perform path planning in real time with human assistance. However, carrying a large number of sensors will increase the cost of path planning and reduce the efficiency of path planning. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present invention provides a path planning method, device, electronic device and readable storage medium.

[0005] In a first aspect, the present invention provides a path planning method, the method comprising:

[0006] For any round of path exploration, a first random number is generated, and based on the first random number and the target probability value corresponding to the current round of path exploration, a target exploration strategy corresponding to the current round of path exploration is determined;

[0007] Based on the target exploration strategy and the current exploration node, determine the target growth point corresponding to the current round of path exploration;

[0008] When the preset end condition is reached, the target path is determined based on the target growth point corresponding to each round of path exploration.

[0009] Optionally, after determining the target growth point corresponding to the current round of path exploration based on the target exploration strategy and the current exploration node, the method further includes:

[0010] Determine a first value based on the target probability value corresponding to the current round of path exploration and a preset attenuation factor; the first value is less than the target probability value;

[0011] The first value is determined as the target probability value corresponding to the next round of path exploration.

[0012] Optionally, determining a target exploration strategy corresponding to the current round of path exploration based on the first random number and the target probability value corresponding to the current round of path exploration includes:

[0013] When the first random number is less than the target probability value corresponding to the current round of path exploration, determining that the target exploration strategy corresponding to the current round of path exploration is the first exploration strategy; the first exploration strategy is to perform path exploration based on a random exploration algorithm;

[0014] When the first random number is greater than or equal to the target probability value corresponding to the current round of path exploration, the target exploration strategy corresponding to the current round of path exploration is determined to be the second exploration strategy; the second exploration strategy is to perform path exploration based on a greedy algorithm.

[0015] Optionally, the method further comprises:

[0016] The target growth point is added to the path growth branch corresponding to the current exploration node.

[0017] Optionally, determining a target growth point corresponding to this round of path exploration based on the target exploration strategy and the current exploration node includes:

[0018] In the case where the target exploration strategy is the first exploration strategy, generating a target point in the target map based on the target probability value corresponding to the current round of path exploration;

[0019] Based on the distance values ​​between the target point and each known point in the target map, determining the known point with the smallest distance value to the target point as the current exploration node;

[0020] A target growth point is generated based on a first direction corresponding to the current exploration node to the target point and a preset step size.

[0021] Optionally, determining a target growth point corresponding to this round of path exploration based on the target exploration strategy and the current exploration node includes:

[0022] When the target exploration strategy is the second target exploration strategy, based on known points on the target map, obtaining an unexplored area in the target map;

[0023] From the end points of each path growth branch, select the end point closest to the target unexplored area with the largest area as the current exploration node;

[0024] A target growth point is generated based on the second direction corresponding to the current exploration node and the center point of the target unexplored area and a preset step size.

[0025] Optionally, the preset end condition includes that all boundary points in the target map are explored, or a preset number of path exploration rounds is reached.

[0026] In a second aspect, the present invention provides a path planning device, the device comprising:

[0027] A first determination module is used to generate a first random number for any round of path exploration, and determine a target exploration strategy corresponding to the current round of path exploration based on the first random number and the target probability value corresponding to the current round of path exploration;

[0028] A second determination module is used to determine the target growth point corresponding to the current round of path exploration based on the target exploration strategy and the current exploration node;

[0029] The third determination module is used to determine the target path based on the target growth point corresponding to each round of path exploration when a preset end condition is reached.

[0030] Optionally, the device further comprises:

[0031] A fourth determination module is used to determine a first value based on the target probability value corresponding to the current round of path exploration and a preset attenuation factor; the first value is less than the target probability value;

[0032] The fifth determination module is used to determine the first value as the target probability value corresponding to the next round of path exploration.

[0033] Optionally, the first determining module includes:

[0034] A first determination submodule is used to determine that the target exploration strategy corresponding to the current round of path exploration is a first exploration strategy when the first random number is less than the target probability value corresponding to the current round of path exploration; the first exploration strategy is to perform path exploration based on a random exploration algorithm;

[0035] The second determination submodule is used to determine that the target exploration strategy corresponding to this round of path exploration is a second exploration strategy when the first random number is greater than or equal to the target probability value corresponding to the current round of path exploration; the second exploration strategy is based on a greedy algorithm for path exploration.

[0036] Optionally, the device further comprises:

[0037] The first adding module is used to add the target growth point to the path growth branch corresponding to the current exploration node.

[0038] Optionally, the second determining module includes:

[0039] A first generating module, configured to generate a target point in a target map based on a target probability value corresponding to a current round of path exploration when the target exploration strategy is the first exploration strategy;

[0040] A third determination submodule is used to determine, based on the distance values ​​between the target point and each known point in the target map, the known point with the smallest distance value to the target point as the current exploration node;

[0041] The second generation module is used to generate a target growth point based on a first direction corresponding to the current exploration node to the target point and a preset step size.

[0042] Optionally, the second determining module further includes:

[0043] A first acquisition module, configured to acquire an unexplored area in the target map based on known points on the target map when the target exploration strategy is the second target exploration strategy;

[0044] The first selection module is used to select, from the end points of each path growth branch, the end point closest to the target unexplored area with the largest area as the current exploration node;

[0045] The third generation module is used to generate a target growth point based on the second direction corresponding to the current exploration node and the center point of the target unexplored area and a preset step size.

[0046] In a third aspect, the present invention provides an electronic device comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the path planning method described in any one of the first aspects when executing the program.

[0047] In a fourth aspect, the present invention provides a readable storage medium, which, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the steps in the path planning method in any one of the embodiments of the first aspect above.

[0048] In the embodiment of the present invention, for any round of path exploration, a first random number is generated, and based on the first random number and the target probability value corresponding to the current round of path exploration, the target exploration strategy corresponding to the current round of path exploration is determined; based on the target exploration strategy and the current exploration node, the target growth point corresponding to the current round of path exploration is determined; when the preset end condition is reached, the target path is determined based on the target growth point corresponding to each round of path exploration. In this way, by automatically determining the target exploration strategy based on the first random number and the target probability value, and then automatically exploring and determining the target growth point based on the target exploration strategy, the automation of path planning and the autonomous mapping of the mobile robot are realized, while reducing the labor cost, the accuracy of path planning is improved in an automated manner. At the same time, the target exploration strategy corresponding to the current round of path exploration is determined by the target probability value corresponding to each round of path exploration and the generated first random number, so as to avoid being limited to one path exploration mode and falling into a local optimum or excessive random exploration situation. Through the first random number and the target probability value, a balance between the randomness and directionality of path exploration is achieved, and then by selecting different target exploration strategies, the path exploration process is easier to explore in the right direction, further improving the efficiency and accuracy of path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 is a flowchart of the steps of a path planning method provided by an embodiment of the present invention;

[0051] Figure 2 is a flowchart of specific steps of a path planning method provided by an embodiment of the present invention;

[0052] Figure 3 is a path exploration schematic diagram corresponding to a first exploration strategy provided by an embodiment of the present invention;

[0053] Figure 4 is a path exploration schematic diagram corresponding to a second exploration strategy provided by an embodiment of the present invention;

[0054] Figure 5 is a structural diagram of a path planning device provided by an embodiment of the present invention;

[0055] Figure 6 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Figure 1 It is a step flow chart of a path planning method provided by an embodiment of the present invention, which is applied to mobile robots, wherein the mobile robots may include warehouse transport robots, office sweeping robots, household cleaning robots, hospital medicine and material transport robots, etc.

[0058] like Figure 1 As shown, the method may include:

[0059] Step 101: For any round of path exploration, generate a first random number, and determine a target exploration strategy corresponding to this round of path exploration based on the first random number and the target probability value corresponding to this round of path exploration.

[0060] In an embodiment of the present invention, an empty map can be pre-initialized as the target map corresponding to this path planning. The target map can be a map of the target area where the mobile robot needs to perform path planning, such as a grid map, a point cloud map, a topological map, etc. The target map defines the boundary information of the target area, the obstacle information in the target area, etc. Determine the starting point for the mobile robot to perform path planning in the target area, and mark the starting point in the target map. Preset the initial initial probability value, preset attenuation factor, preset step size, and preset number of path exploration rounds. Among them, the initial probability value is used to compare with the random number as the target probability value corresponding to this round of path exploration when the path planning exploration is performed for the first time. The preset attenuation factor can be less than 1, and the preset attenuation factor is used to attenuate the target probability value corresponding to this round of path exploration after each path exploration as the target probability value for the next round of path exploration. The preset step size refers to the distance or spatial range spanned by the mobile robot from the current position to the next exploration point during a movement or search process. The preset step size can be an actual distance in physical space (such as meters, centimeters, etc.), or a measurement in some abstract representation (such as the number of grids in a grid map), and the embodiment of the present invention does not limit this. The preset number of path exploration rounds is used to define the end condition of the path exploration. It can be understood that as the number of rounds of path exploration increases, the initial probability value will gradually decrease based on the processing of the preset attenuation factor, so the size of the initial probability value can be set to a larger value. The settings of the initial probability value, the preset attenuation factor, the preset step size, and the preset number of path exploration rounds can be set according to actual needs, and the embodiment of the present invention does not limit this.

[0061] For any round of path exploration, a first random number is first generated. The first random number is compared with the target probability value corresponding to the current round of path to obtain a size comparison result. According to the size comparison result, the target exploration strategy corresponding to the current round of path exploration is determined. Among them, the target probability value corresponding to the current round of path exploration is the initial probability value in the first path exploration process, and the product result of the target probability value corresponding to the last path exploration process and the preset attenuation factor in the non-first path exploration process. The target exploration strategy may include a first exploration strategy and a second exploration strategy, wherein the first exploration strategy is based on a random exploration algorithm for path exploration, and the random exploration algorithm may be a rapidly expanding random tree (Rapidly-exploring Random Tree, RRT) algorithm, and the first exploration strategy may iteratively explore the search space through random sampling and tree structure until the optimal path based on the starting point is found. It uses randomness to avoid the global information requirements of traditional planning methods, making it particularly suitable for complex and uncertain environments. The second exploration strategy is based on a greedy algorithm for path exploration, and the greedy algorithm may be an ε-greedy strategy for weighing exploration and exploitation. The second exploration strategy allows the robot to use known information to guide to more promising areas, thereby speeding up the exploration. The robot may find it easier to find shorter or better paths and help the robot better adapt to environmental changes.

[0062] Optionally, step 101 may include the following steps:

[0063] Step 1011: When the first random number is less than the target probability value corresponding to this round of path exploration, determine that the target exploration strategy corresponding to this round of path exploration is the first exploration strategy; the first exploration strategy is to perform path exploration based on a random exploration algorithm.

[0064] Step 1012: When the first random number is greater than or equal to the target probability value corresponding to the current round of path exploration, determine that the target exploration strategy corresponding to the current round of path exploration is a second exploration strategy; the second exploration strategy is path exploration based on a greedy algorithm.

[0065] In the embodiment of the present invention, when the size comparison result is that the first random number is greater than or equal to the target probability value corresponding to the current round of path exploration, the target exploration strategy is determined to be the first exploration strategy; when the size comparison result is that the first random number is less than the target probability value corresponding to the current round of path exploration, the target exploration strategy is determined to be the second exploration strategy. That is to say, during each path exploration, when the first random number is less than the target probability value corresponding to the current round of path exploration, the mobile robot uses the first exploration strategy to accumulate and select an available action for exploration with the probability of the target probability value; when the first random number is greater than or equal to the target probability value corresponding to the current round of path exploration, the mobile robot selects the currently known optimal action for use with the probability of 1-target probability value. Among them, the currently known optimal action refers to the node that is already in the growing tree; the available action refers to the node that is about to be generated for the area to be explored.

[0066] Step 102: Based on the target exploration strategy and the current exploration node, determine the target growth point corresponding to this round of path exploration.

[0067] In an embodiment of the present invention, after each path exploration, the target map will be updated. When a target growth point is determined in this round of path exploration, the target growth point will be added to the target map, and one or more path growth branches will be formed on the target map. The target growth points marked on the target map can be regarded as known points, that is, the known points on the target map can include the starting point and the target growth points determined in each round of path exploration. The current exploration nodes corresponding to different target exploration strategies are different. According to the different target exploration strategies corresponding to this round of path exploration, the current exploration point corresponding to this round of path exploration is selected. When the target exploration strategy is the first exploration strategy, the current exploration node can be the known point on the target map that is closest to the random point; when the target exploration strategy is the second exploration strategy, the current exploration point can be the known end point on the target map that is closest to the unexplored area with the largest area. It can be understood that when this round of path exploration is the first path exploration, the current exploration point is the starting point on the target map.

[0068] Based on the current exploration node, the exploration point corresponding to this round of path exploration is determined through the target exploration strategy as the target growth point. The target growth point is marked at the corresponding position of the target map. It is understandable that if the target growth point coincides with the position of the obstacle in the target map, the target growth node can be discarded and not marked in the target map, and this path exploration is deemed to have not obtained the target growth point.

[0069] Step 103: When the preset end condition is met, determine the target path based on the target growth point corresponding to each round of path exploration.

[0070] In an embodiment of the present invention, when a preset end condition is reached, the path exploration process is characterized to be ended, and the target path is determined based on the target growth points corresponding to each round of path exploration. The preset end condition may include that all boundary points in the target map have been explored or a preset number of path exploration rounds have been reached. When all boundary points in the target map have been explored in the historical path exploration process, or when the number of path exploration rounds is greater than or equal to the preset number of path exploration rounds, the path exploration is stopped. According to the sensor set on the mobile robot, it is detected whether the historical path exploration process has completed the exploration of all boundary points on the target map. Exemplarily, assuming that the shape of the target map is a rectangle, the sensor can output the length and width, which can be obtained by comparing the length and width of the target map or comparing whether the current area currently detected is equal to the known map area of ​​the target map.

[0071] After stopping the path exploration, the path growth branch formed by each known point on the target map can be determined as the target path based on the path growth branch with the largest number of known points.

[0072] In summary, in the embodiment of the present invention, for any round of path exploration, a first random number is generated, and based on the first random number and the target probability value corresponding to the current round of path exploration, the target exploration strategy corresponding to the current round of path exploration is determined; based on the target exploration strategy and the current exploration node, the target growth point corresponding to the current round of path exploration is determined; when the preset end condition is reached, the target path is determined based on the target growth point corresponding to each round of path exploration. In this way, by automatically determining the target exploration strategy based on the first random number and the target probability value, and then automatically exploring and determining the target growth point based on the target exploration strategy, the automation of path planning and the autonomous mapping of the mobile robot are realized, while reducing the labor cost, the accuracy of path planning is improved in an automated manner. At the same time, the target exploration strategy corresponding to the current round of path exploration is determined by the target probability value corresponding to each round of path exploration and the generated first random number, so as to avoid being limited to one path exploration mode, falling into a local optimum or excessive random exploration situation, and achieving a balance between the randomness and directionality of path exploration through the first random number and the target probability value, and then by selecting different target exploration strategies, the path exploration process is easier to explore in the right direction, further improving the efficiency and accuracy of path planning.

[0073] Furthermore, since using the RRT algorithm alone for path planning is prone to uncontrollable randomness, it is easy to cause the inability to confirm whether it is exploring in the positive direction in complex scenarios, resulting in a long path planning time. By setting the target probability value, this randomness can be controlled based on the target probability value variable, and complete randomness can be transformed into directional randomness (that is, random exploration will only be performed when the first random number is less than the target probability value corresponding to this round of path exploration). In this way, in the process of path planning, there will be no situation where "it is impossible to confirm whether it is exploring in the positive direction", which improves the rationality and accuracy of path planning.

[0074] Optionally, after step 102, the embodiment of the present invention may include the following steps:

[0075] Step 201: Determine a first value based on the target probability value corresponding to the current round of path exploration and a preset attenuation factor; the first value is smaller than the target probability value.

[0076] In the embodiment of the present invention, after completing a round of path exploration, the first value is determined based on the target probability value corresponding to the current round of path exploration and the preset attenuation factor. Specifically, the target probability value can be multiplied by the preset attenuation factor, and the product is used as the first value. It can be understood that since the preset attenuation factor is less than 1, the first value is less than the target probability value.

[0077] Step 202: Determine the first value as the target probability value corresponding to the next round of path exploration.

[0078] In the embodiment of the present invention, the first value is determined as the target probability value corresponding to the next round of path exploration. In this way, as the number of path exploration rounds increases, the target probability value of each round of path exploration will gradually decrease. In addition, when the first random number is less than the target probability value of the current round of path exploration, the path exploration will be performed based on the random exploration algorithm. When the first random number is greater than or equal to the target probability value, the path exploration will be performed based on the greedy algorithm. When the target probability value gradually decreases, it indicates that as the number of path exploration rounds increases, the possibility of the target exploration strategy being the second exploration strategy increases, that is, the probability of selecting the path exploration based on the greedy algorithm increases. In this way, as the number of path exploration rounds increases, the probability of selecting the currently known optimal action for use gradually increases, and the probability of randomly selecting an available action for exploration is reduced. As the path exploration time goes by, more and more known information on the target map is known, and more known information is used for path planning, that is, more second exploration strategies are used for path planning, so that each path exploration of the mobile robot is directed to a more useful area, and the number of times that an available action is randomly selected for exploration is reduced, thereby speeding up the path planning speed, reducing the time of the path planning process, and reducing the amount of calculation in the path planning process.

[0079] Optionally, the embodiment of the present invention may further include the following steps:

[0080] Step 301: Add the target growth point to the path growth branch corresponding to the current exploration node.

[0081] In the embodiment of the present invention, after each path exploration, the target map is updated. When a target growth point is determined in the current round of path exploration, the target growth point is added to the target map, and one or more path growth branches are formed on the target map. The target growth points marked on the target map can be regarded as known points, that is, the known points on the target map can include the starting point and the target growth points determined in each round of path exploration.

[0082] Optionally, step 102 may include the following steps:

[0083] Step 401: When the target exploration strategy is the first exploration strategy, a random point is generated in the target map based on the target probability value corresponding to the current round of path exploration.

[0084] In an embodiment of the present invention, when the target exploration strategy is the first exploration strategy, it is characterized that this round of path exploration is based on a random exploration algorithm to perform path exploration. Then, based on the target probability value corresponding to this round of path exploration, a target point can be randomly generated in the target map. The target point can be divided into boundary points and random points. Specifically, a boundary point closest to the current position can be selected in the target map with the probability of the target probability value, and a random point can be selected in the target map with the probability of 1-target probability value. Exemplarily, assuming that the target probability value is 0.3, when a target point is randomly selected in the target map, there is a 0.3 probability that the target point is a boundary point, and there is a 0.7 probability that the target point is a random point. Among them, the role of the boundary point is to allow the mobile robot to explore along the boundary of the target map as much as possible. The benefits of exploring along the boundary of the target map are boundary determination, reducing omissions in map exploration, and improving positioning accuracy.

[0085] It is understandable that in the process of randomly generating target points based on target probability values, if the generated target point coincides with an obstacle, a new target point can be generated. That is, in the process of generating target points, the target point is not selected within the range of obstacles in the target map.

[0086] Step 402: Based on the distance values ​​between the target point and each known point in the target map, determine the known point with the smallest distance value to the target point as the current exploration node.

[0087] In an embodiment of the present invention, during this round of path exploration, known points in the current target map are determined, and the distance between each known point and the target point is calculated. Based on the distance between the target point and each known point in the target map, the known point with the smallest distance value is selected as the current exploration node corresponding to this path exploration process.

[0088] Step 403: Generate a target growth point based on the first direction corresponding to the current exploration node to the target point and a preset step size.

[0089] In the embodiment of the present invention, after determining the current exploration node, a first direction from the current exploration node to the target point is determined, and based on the first direction and a preset step length, a target growth point is generated and marked in the target map. It is understandable that when the target growth point coincides with an obstacle in the target map, the target growth point is discarded to ensure that the newly generated target growth point does not conflict with the obstacle.

[0090] In the embodiment of the present invention, path exploration is performed through the first exploration strategy, which can quickly generate target growth points, and high-dimensional space can be searched quickly and effectively through random sampling and incremental expansion, so that the mobile robot can explore the environment and learn new information.

[0091] Optionally, step 102 may include the following steps:

[0092] Step 501: When the target exploration strategy is the second target exploration strategy, based on known points on the target map, obtain an unexplored area in the target map.

[0093] In an embodiment of the present invention, when the target exploration strategy is the second target exploration strategy, it is characterized that this path exploration needs to perform path planning based on a greedy algorithm, and based on known points on the target map, unexplored areas in the target map are determined and determined as unexplored areas.

[0094] Step 502: Select, from the end points of each path growth branch, the end point closest to the target unexplored region with the largest area as the current exploration node.

[0095] In an embodiment of the present invention, based on known points in the target map, the end points of each path growth branch are determined. The area of ​​each unexplored region is determined, and the unexplored region with the largest area is determined as the target unexplored region. From the end points of each path growth branch, the end point closest to the target unexplored region is determined as the current exploration node. Exemplarily, the distance value between each end point and the center point of the target unexplored region can be obtained, and the end point with the smallest distance value is determined as the current exploration node.

[0096] Step 503: Generate a target growth point based on the second direction corresponding to the current exploration node and the center point of the target unexplored area and a preset step size.

[0097] In the embodiment of the present invention, a second direction from the current exploration node to the center point of the target unexplored area is determined, and based on the second direction and the preset compensation, a target growth point is generated and marked on the target map. It is understandable that when the target growth point coincides with an obstacle in the target map, the target growth point is discarded to ensure that the newly generated target growth point does not conflict with the obstacle.

[0098] In an embodiment of the present invention, through the second exploration strategy, path exploration is performed based on the known end points on the target map, which can control the number of iterations to a certain extent, and the path exploration direction can be directed to more promising areas based on known information, thereby accelerating the path exploration speed, making it easier for the mobile robot to find shorter or better paths, and helping the mobile robot better adapt to environmental changes.

[0099] In this way, the target probability value is used as a single factor in the path planning process, and the RRT algorithm and the greedy algorithm are linked by exploration and utilization, so as to achieve a trade-off between randomness and directionality in the path planning process. By randomly selecting actions, the robot can explore the environment and learn new information. By selecting the known optimal action, the robot can use the existing knowledge to obtain the maximum immediate reward, improve the efficiency and accuracy of path planning, and realize the "autonomous" mapping of the mobile robot while maintaining various indicators.

[0100] Exemplarily, an embodiment of the present invention provides a flowchart of specific steps of a path planning method, such as Figure 2 As shown, a target map, an initial probability value, a preset attenuation factor, a preset step size, and a preset number of path exploration rounds are initialized, a first random number is generated, and based on the first random number and the target probability value corresponding to this round of path exploration, the target exploration strategy corresponding to this path exploration is determined. When the target exploration strategy is the first exploration strategy, a boundary point closest to the current position is selected in the target map with the probability of the target probability value, and a random point is selected in the target map with the probability of 1-target probability value. The selected point is taken as the target point, and the known point closest to the target point is selected as the current exploration node. The first direction corresponding to the current exploration node and the current exploration node to the target point is the growth direction, and a growth point with a preset step size is grown as the target growth point for this path exploration. As shown Figure 3 As shown in the figure, assuming that before this round of path exploration, the known points on the target map include the starting point, target growth point 1, target growth point 2, and target growth point 3, when the target exploration strategy is the first exploration strategy, the process of generating target points on the target map is as follows: Figure 3 As shown, the current exploration node can be determined as the target growth point 2 according to the distance between the known point and the target point, and then the target growth point 4 is generated with a preset step size in the first direction of the target growth point 2 pointing to the target point.

[0101] When the target exploration strategy is the second exploration strategy, determine the unexplored area in the target map, and then determine the end point closest to the largest unexplored area among all the end points in the target map as the current exploration node. Take the second direction corresponding to the current exploration node and the center point of the largest unexplored area as the growth direction, and grow a growth point with a preset step length as the target growth point for this path exploration. Figure 4 As shown in FIG. 1 , assuming that before this round of path exploration, the known points on the target map include the starting point, target growth point 1, target growth point 2, target growth point 3, and target growth point 4, then when the target exploration strategy is the second exploration strategy, the process of generating target points on the target map is as follows: Figure 4 As shown, Figure 4 The middle and end points are target growth point 3 and target growth point 4. According to the distance between target growth point 3 and target growth point 4 and the largest undetected area, target growth point 3 is determined as the current exploration node corresponding to this round of path exploration. Then, in the second direction from target growth point 3 to the center point of the largest undetected area, target growth point 5 is generated with a preset step length.

[0102] Detect whether the target growth point collides with the obstacle in the target map. If so, discard the target growth point. If not, mark the target growth point in the target map and add the target growth point to the path growth branch corresponding to the current exploration node. After completing a round of path exploration, multiply the target probability value of this round of path exploration by the preset attenuation factor to determine the target probability value corresponding to the next round of path exploration. And determine whether the preset end condition is met. If not, regenerate the first random number and conduct the next round of path exploration; if so, stop the path exploration and complete the path planning.

[0103] Figure 5 is a schematic diagram of the structure of a path planning device provided by an embodiment of the present invention, such as Figure 5 As shown, the device may specifically include:

[0104] A first determination module 601 is used to generate a first random number for any round of path exploration, and determine a target exploration strategy corresponding to the current round of path exploration based on the first random number and the target probability value corresponding to the current round of path exploration;

[0105] A second determination module 602 is used to determine the target growth point corresponding to the current round of path exploration based on the target exploration strategy and the current exploration node;

[0106] The third determination module 603 is used to determine the target path based on the target growth point corresponding to each round of path exploration when a preset end condition is met.

[0107] The embodiment of the present invention provides a path planning device, which generates a first random number for any round of path exploration, and determines the target exploration strategy corresponding to the current round of path exploration based on the first random number and the target probability value corresponding to the current round of path exploration; determines the target growth point corresponding to the current round of path exploration based on the target exploration strategy and the current exploration node; and determines the target path based on the target growth point corresponding to each round of path exploration when the preset end condition is reached. In this way, by automatically determining the target exploration strategy based on the first random number and the target probability value, and then automatically exploring and determining the target growth point based on the target exploration strategy, the automation of path planning and the autonomous mapping of the mobile robot are realized, while reducing the labor cost, the accuracy of path planning is improved in an automated manner. At the same time, the target exploration strategy corresponding to the current round of path exploration is determined by the target probability value corresponding to each round of path exploration and the generated first random number, so as to avoid being limited to one path exploration mode and falling into a local optimum or excessive random exploration situation. The first random number and the target probability value are used to achieve a balance between the randomness and directionality of path exploration, and then by selecting different target exploration strategies, the path exploration process is easier to explore in the correct direction, further improving the efficiency and accuracy of path planning.

[0108] Optionally, the device may further include:

[0109] A fourth determination module is used to determine a first value based on the target probability value corresponding to the current round of path exploration and a preset attenuation factor; the first value is less than the target probability value;

[0110] The fifth determination module is used to determine the first value as the target probability value corresponding to the next round of path exploration.

[0111] Optionally, the first determining module 601 includes:

[0112] A first determination submodule is used to determine that the target exploration strategy corresponding to the current round of path exploration is a first exploration strategy when the first random number is less than the target probability value corresponding to the current round of path exploration; the first exploration strategy is to perform path exploration based on a random exploration algorithm;

[0113] The second determination submodule is used to determine that the target exploration strategy corresponding to this round of path exploration is a second exploration strategy when the first random number is greater than or equal to the target probability value corresponding to the current round of path exploration; the second exploration strategy is based on a greedy algorithm for path exploration.

[0114] Optionally, the device may further include:

[0115] The first adding module is used to add the target growth point to the path growth branch corresponding to the current exploration node.

[0116] Optionally, the second determining module 602 includes:

[0117] A first generating module, configured to generate a target point in a target map based on a target probability value corresponding to a current round of path exploration when the target exploration strategy is the first exploration strategy;

[0118] A third determination submodule is used to determine, based on the distance values ​​between the target point and each known point in the target map, the known point with the smallest distance value to the target point as the current exploration node;

[0119] The second generation module is used to generate a target growth point based on a first direction corresponding to the current exploration node to the target point and a preset step size.

[0120] Optionally, the second determining module 602 further includes:

[0121] A first acquisition module, configured to acquire an unexplored area in the target map based on known points on the target map when the target exploration strategy is the second target exploration strategy;

[0122] The first selection module is used to select, from the end points of each path growth branch, the end point closest to the target unexplored area with the largest area as the current exploration node;

[0123] The third generation module is used to generate a target growth point based on the second direction corresponding to the current exploration node and the center point of the target unexplored area and a preset step size.

[0124] The present invention also provides an electronic device, see Figure 6 , including: a processor 701, a memory 702, and a computer program 7021 stored in the memory and executable on the processor, wherein the processor implements the path planning method of the aforementioned embodiment when executing the program.

[0125] The present invention also provides a readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the path planning method of the aforementioned embodiment.

[0126] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0127] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0128] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0129] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0130] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0131] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the sorting device according to the present invention. The present invention may also be implemented as a device or apparatus program for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0132] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0135] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0136] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A path planning method, characterized in that: The method comprises: For any round of path exploration, a first random number is generated, and based on the first random number and the target probability value corresponding to the current round of path exploration, a target exploration strategy corresponding to the current round of path exploration is determined; Based on the target exploration strategy and the current exploration node, determine the target growth point corresponding to the current round of path exploration; When the preset end condition is reached, the target path is determined based on the target growth point corresponding to each round of path exploration.

2. The method according to claim 1, characterized in that After determining the target growth point corresponding to the current round of path exploration based on the target exploration strategy and the current exploration node, the method further includes: Determine a first value based on the target probability value corresponding to the current round of path exploration and a preset attenuation factor; the first value is less than the target probability value; The first value is determined as the target probability value corresponding to the next round of path exploration.

3. The method according to claim 1, characterized in that The determining, based on the first random number and the target probability value corresponding to the current round of path exploration, a target exploration strategy corresponding to the current round of path exploration includes: When the first random number is less than the target probability value corresponding to the current round of path exploration, determining that the target exploration strategy corresponding to the current round of path exploration is the first exploration strategy; the first exploration strategy is to perform path exploration based on a random exploration algorithm; When the first random number is greater than or equal to the target probability value corresponding to the current round of path exploration, the target exploration strategy corresponding to the current round of path exploration is determined to be the second exploration strategy; the second exploration strategy is to perform path exploration based on a greedy algorithm.

4. The method according to claim 1, characterized in that: The method further comprises: The target growth point is added to the path growth branch corresponding to the current exploration node.

5. The method according to claim 1, characterized in that: The determining of the target growth point corresponding to the current round of path exploration based on the target exploration strategy and the current exploration node includes: In the case where the target exploration strategy is the first exploration strategy, generating a target point in the target map based on the target probability value corresponding to the current round of path exploration; Based on the distance values ​​between the target point and each known point in the target map, determining the known point with the smallest distance value to the target point as the current exploration node; A target growth point is generated based on a first direction corresponding to the current exploration node to the target point and a preset step size.

6. The method according to claim 1, characterized in that The determining of the target growth point corresponding to the current round of path exploration based on the target exploration strategy and the current exploration node includes: When the target exploration strategy is the second target exploration strategy, based on known points on the target map, obtaining an unexplored area in the target map; From the end points of each path growth branch, select the end point closest to the target unexplored area with the largest area as the current exploration node; A target growth point is generated based on the second direction corresponding to the current exploration node and the center point of the target unexplored area and a preset step size.

7. The method according to claim 1, characterized in that The preset end condition includes that all boundary points in the target map are explored and completed or a preset number of path exploration rounds is reached.

8. A path planning device, characterized in that: The device comprises: A first determination module is used to generate a first random number for any round of path exploration, and determine a target exploration strategy corresponding to the current round of path exploration based on the first random number and the target probability value corresponding to the current round of path exploration; A second determination module is used to determine the target growth point corresponding to the current round of path exploration based on the target exploration strategy and the current exploration node; The third determination module is used to determine the target path based on the target growth point corresponding to each round of path exploration when a preset end condition is reached.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the path planning method as claimed in any one of claims 1 to 7 when executing the program.

10. A readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the path planning method described in any one of claims 1-7.

Images