Mobile robot local path planning parameter automatic setting method and related equipment

Abstract

The application is suitable for the technical field of robot control, and particularly relates to a mobile robot local path planning parameter automatic setting method and related equipment. The method comprises the following steps: obtaining at least two groups of parameter combination schemes and performance indexes corresponding to the parameter combination schemes; obtaining each control parameter corresponding to a second parameter scheme; obtaining parameter influence data corresponding to each control parameter, analyzing the parameter influence data corresponding to each control parameter, and obtaining target influence data of the second parameter scheme; and selecting at least one parameter scheme from the first parameter scheme and the second parameter scheme after setting the identifier and outputting the at least one parameter scheme. The method provided in the application can solve the problem that, in a traditional local path planning parameter setting process, in order to facilitate operation, a first parameter scheme generated based on basic control parameters is directly output to a robot, the output parameter scheme is not the best scheme, and the working efficiency of the mobile robot is affected.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of robot control, and particularly relates to a mobile robot local path planning parameter automatic setting method and related equipment. BACKGROUND

[0002] A mobile robot is a robot (such as a wheeled robot, a tracked robot, etc.) capable of moving autonomously or semi-autonomously in an environment and completing a specific task, for example, completing a task in different scenes such as indoors and outdoors, on the ground, in the air, etc. Before a mobile robot performs a warehouse goods carrying task or a shelving task, the path of the mobile robot needs to be planned to complete actions such as turning and obstacle avoidance.

[0003] In a conventional local path planning parameter setting process, in order to facilitate operation, a first parameter scheme (such as a fixed turning angular velocity or a preset obstacle avoidance threshold) generated based on basic control parameters is directly output to the robot, that is, the selection probability of the first parameter scheme is higher than that of a second parameter scheme including adaptive adjustment parameters in addition to the basic control parameters, which results in that the output parameter scheme is not the best scheme, thereby affecting the work efficiency of the mobile robot. SUMMARY

[0004] Embodiments of the application provide a mobile robot local path planning parameter automatic setting method and related equipment, which can solve the problem that in a conventional local path planning parameter setting process, in order to facilitate operation, a first parameter scheme generated based on basic control parameters is directly output to the robot, which results in that the output parameter scheme is not the best scheme, thereby affecting the work efficiency of the mobile robot.

[0005] In a first aspect, embodiments of the application provide a mobile robot local path planning parameter automatic setting method, comprising:

[0006] obtaining at least two groups of parameter combination schemes and performance indicators corresponding to the parameter combination schemes; wherein the parameter combination schemes carry a first parameter scheme generated according to basic control parameters and a second parameter scheme generated according to the basic control parameters and adaptive adjustment parameters; and the performance indicators corresponding to the parameter combination schemes are used to reflect the path planning effect of the robot under the current parameter combination;

[0007] obtaining each control parameter corresponding to the second parameter scheme;

[0008] obtain target influence data of the second parameter scheme by analyzing the parameter influence data corresponding to each control parameter; wherein the parameter influence data is data for correcting the performance index; and the target influence data is calculated by taking the parameter influence data of all control parameters in the second parameter scheme according to the importance proportion of the parameter in the motor function;

[0009] set a unique identifier for the second parameter scheme according to the target influence data and the performance index of the second parameter scheme; and set a unique identifier for the first parameter scheme according to the performance index of the first parameter scheme;

[0010] select at least one parameter scheme from the first parameter scheme and the second parameter scheme after setting the identifier for output.

[0011] The technical scheme described above in the embodiments of the present application has at least the following technical effects:

[0012] The mobile robot local path planning parameter automatic setting method provided in the present application obtains at least two groups of parameter combination schemes and performance indexes corresponding to the parameter combination schemes. The method obtains each control parameter corresponding to a second parameter scheme. The method obtains parameter influence data corresponding to each control parameter, analyzes the parameter influence data corresponding to each control parameter, and obtains target influence data of the second parameter scheme. The method sets a unique identifier for the second parameter scheme according to the target influence data and the performance index of the second parameter scheme. The method sets a unique identifier for the first parameter scheme according to the performance index of the first parameter scheme. The method selects at least one parameter scheme from the first parameter scheme and the second parameter scheme after setting the identifier for output. Based on the scheme, in the local path planning parameter setting process, the advantages of the first parameter scheme are retained, the parameter influence data of each control parameter in the second parameter scheme is accurately quantified through the target influence data, the situation that the second parameter scheme cannot accurately measure the comprehensive adaptation ability of the second parameter scheme due to not being quantitatively evaluated is avoided, then at least one parameter scheme is selected from the first parameter scheme and the second parameter scheme after setting the identifier for output, which can avoid the problem that the first parameter scheme is directly output to the robot in the traditional method, resulting in that the output parameter scheme is not the best scheme, and can also avoid the problem that the advantages of the second parameter scheme are covered (for example, the second parameter scheme cannot accurately measure the comprehensive adaptation ability of the second parameter scheme due to not being quantitatively evaluated) or the reasonable value of the first parameter scheme is ignored (for example, the second parameter scheme is blindly selected, and the advantages of the first parameter scheme are ignored), so that the value of each type of scheme can be reflected through the set identifier, and the output parameter scheme is the best scheme, thereby improving the working efficiency of the mobile robot.

[0013] In a second aspect, the embodiments of the present application provide a mobile robot local path planning parameter automatic setting system, applied to a mobile robot local path planning parameter automatic setting device, and used for implementing the mobile robot local path planning parameter automatic setting method in any of the first aspect, the system comprising:

[0014] an acquisition unit configured to acquire at least two groups of parameter combination schemes and performance indexes corresponding to the parameter combination schemes, wherein the parameter combination scheme carries a first parameter scheme generated according to a basic control parameter and a second parameter scheme generated according to the basic control parameter and an adaptive adjustment parameter, and the performance index corresponding to the parameter combination scheme is used to reflect a path planning effect of a robot under a current parameter combination;

[0015] a detection unit configured to acquire each control parameter corresponding to the second parameter scheme;

[0016] a calculation unit configured to acquire parameter influence data corresponding to each control parameter, analyze the parameter influence data corresponding to each control parameter, and obtain target influence data of the second parameter scheme, wherein the parameter influence data is used to correct the performance index, and the target influence data is obtained by calculating the parameter influence data of all control parameters in the second parameter scheme according to an importance proportion of the parameters in a motion function;

[0017] a classification unit configured to set a unique identifier for the second parameter scheme according to the target influence data and the performance index of the second parameter scheme, and set a unique identifier for the first parameter scheme according to the performance index of the first parameter scheme;

[0018] an output unit configured to select at least one parameter scheme from the first parameter scheme and the second parameter scheme after the identifiers are set, and output the at least one parameter scheme.

[0019] In a third aspect, the embodiments of the present application provide a mobile robot local path planning parameter automatic setting device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the mobile robot local path planning parameter automatic setting method in any of the first aspect when executing the computer program.

[0020] It can be understood that the beneficial effects of the second aspect to the third aspect can be referred to the related description in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0022] Figure 1 FIG. 1 is a flowchart of a mobile robot local path planning parameter automatic setting method provided by an embodiment of the present application;

[0023] Figure 2 FIG. 2 is a broken line diagram of parameter influence data in the mobile robot local path planning parameter automatic setting method provided by an embodiment of the present application;

[0024] Figure 3 FIG. 3 is a broken line diagram of environment parameter data in the target environment in the mobile robot local path planning parameter automatic setting method provided by an embodiment of the present application;

[0025] Figure 4 FIG. 4 is a flowchart of sending the scheme to the robot in the mobile robot local path planning parameter automatic setting method provided by an embodiment of the present application;

[0026] Figure 5 FIG. 5 is a structural diagram of a mobile robot local path planning parameter automatic setting system provided by an embodiment of the present application;

[0027] Figure 6 FIG. 6 is a structural diagram of a mobile robot local path planning parameter automatic setting device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0028] In the following description, specific details are set forth in order to provide a thorough understanding of embodiments of the present application. However, persons skilled in the art will understand that embodiments of the present application can be practiced without these specific details. In other instances, well-known structures, devices, circuits, and methods have not been described in detail in order to avoid obscuring the description of embodiments of the present application.

[0029] It should be understood that when used in the specification and the appended claims of the present application, the term includes indicates the presence of described features, integers, steps, operations, elements, and / or a combination thereof, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or a combination thereof.

[0030] It should also be understood that the terms and / or phrases used in this application and the accompanying claims are, unless otherwise indicated, to be construed as one or more of the associated listed items and all possible combinations of those items, including those items which are not expressly listed.

[0031] As used in this application and the appended claims, the term if can be construed as when, upon, or in response to a determination, or in response to detecting. Similarly, the phrase if a described condition or event is determined or detected can be construed as meaning upon determination or in response to determination, or upon detection of the described condition or event or in response to detection of the described condition or event.

[0032] In addition, the description in the application and the accompanying claims, the terms first, second, third, etc. are only used to describe and not to indicate or imply relative importance.

[0033] Reference in this application to one or more embodiments means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. The appearances of the phrases in one embodiment, in some embodiments, in other embodiments, in additional embodiments, etc. in various places in the specification are not necessarily all referring to the same embodiment, although they can. The terms comprising, including, having, and the like are meant to be inclusive and not exclusive, unless it is specifically indicated otherwise.

[0034] In the related art, a mobile robot is a robot (such as a wheeled robot, a tracked robot, etc.) capable of moving autonomously or semi-autonomously in an environment and completing a specific task, for example, can complete tasks in different scenarios such as indoors and outdoors, on the ground, in the air, etc. Before the mobile robot performs warehouse goods handling and inter-shelf shuttle operations, the path of the mobile robot needs to be planned to complete actions such as turning and obstacle avoidance.

[0035] In the conventional local path planning parameter setting process, in order to facilitate operation, a first parameter scheme (such as a fixed turning angular velocity, a preset obstacle avoidance threshold) generated based on basic control parameters is usually directly output to the robot, that is, the selection probability of the first parameter scheme is higher than that of a second parameter scheme including adaptive adjustment parameters in addition to the basic control parameters, resulting in that the output parameter scheme is not the best scheme, thereby affecting the work efficiency of the mobile robot.

[0036] For example, in order to be simple to operate, the parameter setting method usually directly outputs the first parameter scheme generated based on the basic control parameters to the robot, although it has the characteristics of fewer parameters and simple setting process, but it cannot cope with dynamic changes in the environment. A few parameter setting methods try to introduce a second parameter scheme containing basic control parameters and adaptive adjustment parameters, but there is a core defect in the evaluation link of the parameter scheme: the parameter influence data of each control parameter in the second parameter scheme is not quantified, which leads to the advantage of the second parameter scheme cannot be reasonably measured, that is, only the first parameter scheme generated by the basic parameters is selected, and the second parameter scheme more suitable for the environment is ignored, or the second parameter scheme is blindly selected, ignoring the advantage of the first parameter scheme, resulting in that the output parameter scheme is not the best scheme, thereby affecting the working efficiency of the mobile robot.

[0037] To solve the above problems, the embodiment of the present application provides a mobile robot local path planning parameter automatic setting method and related equipment.

[0038] In the method, at least two groups of parameter combination schemes and performance indicators corresponding to the parameter combination schemes are obtained. Each control parameter corresponding to the second parameter scheme is obtained. The parameter influence data corresponding to each control parameter is obtained, and the target influence data of the second parameter scheme is obtained by analyzing the parameter influence data corresponding to each control parameter. The unique identifier is set for the second parameter scheme according to the target influence data and the performance indicator of the second parameter scheme. And the unique identifier is set for the first parameter scheme according to the performance indicator of the first parameter scheme. At least one parameter scheme is selected from the first parameter scheme and the second parameter scheme after the identifier is set, and the at least one parameter scheme is output. Based on the scheme, in the local path planning parameter setting process, the advantages of the first parameter scheme are retained, and the parameter influence data of each control parameter in the second parameter scheme is accurately quantified through the target influence data, avoiding the situation that the comprehensive adaptation ability of the second parameter scheme cannot be accurately measured because the second parameter scheme is not quantitatively evaluated. Then, at least one parameter scheme is selected from the first parameter scheme and the second parameter scheme after the identifier is set, and the at least one parameter scheme is output. In this way, the problem that the first parameter scheme is directly output to the robot in the traditional method, resulting in that the output parameter scheme is not the best scheme, can be avoided, and the problem that the advantage of the second parameter scheme is covered (for example, the comprehensive adaptation ability of the second parameter scheme cannot be accurately measured because the second parameter scheme is not quantitatively evaluated) or the reasonable value of the first parameter scheme is ignored (for example, the second parameter scheme is blindly selected, ignoring the advantage of the first parameter scheme) can be avoided, so that the value of each type of scheme can be reflected through the set identifier, and the output parameter scheme is the best scheme, thereby improving the working efficiency of the mobile robot.

[0039] The mobile robot local path planning parameter automatic setting method provided by the embodiments of the present application can be applied to a mobile robot local path planning parameter automatic setting device, and in this case, the mobile robot local path planning parameter automatic setting device is the execution subject of the mobile robot local path planning parameter automatic setting method provided by the embodiments of the present application, and the embodiments of the present application do not limit the specific type of the mobile robot local path planning parameter automatic setting device.

[0040] For example, the mobile robot local path planning parameter automatic setting device can be a single-chip microcomputer, a mobile phone, a tablet computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a desktop computer, a computing device, or a computer connected to a wireless modem, a laptop computer, a handheld communication device, a handheld computing device, and the like.

[0041] In order to better understand the mobile robot local path planning parameter automatic setting method provided by the embodiments of the present application, the specific implementation process of the mobile robot local path planning parameter automatic setting method provided by the embodiments of the present application is exemplarily introduced below.

[0042] Figure 1 A schematic flowchart of the mobile robot local path planning parameter automatic setting method provided by the embodiments of the present application is shown, and the mobile robot local path planning parameter automatic setting method comprises:

[0043] S100, at least two groups of parameter combination schemes and performance indicators corresponding to the parameter combination schemes are obtained. The parameter combination scheme carries a first parameter scheme generated according to a basic control parameter and a second parameter scheme generated according to the basic control parameter and an adaptive adjustment parameter. The performance indicator corresponding to the parameter combination scheme is used to reflect the path planning effect of the robot under the current parameter combination.

[0044] It can be understood that at least two groups of parameter combination schemes can be a plurality of sets of control parameters designed to achieve the local path planning goal of the mobile robot (such as obstacle avoidance, path minimization, motion smoothness), and each set can directly affect the parameters of the motion state of the robot. The performance index can be an evaluation value obtained by quantifying the path planning effect of the robot under the parameter combination, for example, the obstacle avoidance success rate (such as whether it can 100% bypass when facing a static obstacle), the path smoothness (such as the angle deviation of the path inflection point, the smaller the deviation, the higher the smoothness), the motion time consumption (such as the travel time from the starting point to the target point), the energy consumption level (such as the average current consumption of the motor drive), and the like. The basic control parameters in the first parameter scheme generated based on the basic control parameters can be the core parameters for maintaining the basic local path planning function of the robot, such as: speed threshold, steering angular velocity, safety distance reference, and the like. The adaptive adjustment parameters in the second parameter scheme generated based on the basic control parameters and the adaptive adjustment parameters are variable parameters used to cope with dynamic and complex environments based on the basic control parameters, which can be adjusted in real time according to environmental changes (such as the number of obstacles, terrain slope, target point moving speed).

[0045] For example, in a simulation environment, after loading the parameter scheme, the robot completes 10 times of the same path task, and the average value of each index is calculated, and then the final performance index is calculated through a weighted algorithm (such as obstacle avoidance success rate value 0.4, path smoothness value 0.3, motion time consumption value 0.2, and energy consumption level value 0.1). The higher the performance index, the better the path planning effect of the parameter scheme.

[0046] In one possible implementation, obtaining at least two groups of parameter combination schemes and performance indexes corresponding to the parameter combination schemes comprises:

[0047] In S110, environment feature information and motion target information are obtained.

[0048] It can be understood that the environment feature information can be the environmental attribute information in the working space of the mobile robot that can affect the local path planning, which can be obtained in real time by the sensors (such as laser radar, visual camera, ultrasonic sensor) carried by the robot or pre-map construction, and the environment feature information can include static environment features, dynamic environment features, and the like. The motion target information can be information related to the local path planning task that the robot needs to complete, which can be set by a system instruction or a user.

[0049] In S120, at least two groups of parameter combination schemes are determined according to the environment feature information and the motion target information.

[0050] It can be understood that when the environmental features are few static obstacles (such as ≤2), no dynamic interference, flat ground, and the moving target is a simple point-to-point movement (no strict time limit), it is determined as a simple scene, and the first parameter scheme is matched. When the environmental features are many static obstacles (such as ≥5), there are dynamic obstacles (such as pedestrians / other robots), the ground is not flat (such as there is a slope of ≤5°), and the moving target is high time efficiency / high safety requirement (such as the obstacle avoidance response needs to be ≤0.3s), it is determined as a complex scene, and the second parameter scheme (including basic control parameters + adaptive adjustment parameters) is matched.

[0051] For example, in order to cover possible scene changes, at least two groups of schemes (such as a simple scene standard scheme, such as the first parameter scheme A, a simple scene low energy consumption scheme, such as the first parameter scheme B, a complex scene people flow scheme, such as the second parameter scheme C, and a complex scene multi-obstacle scheme, such as the second parameter scheme D) can be designed, and the parameter values of each group of schemes need to be significantly different.

[0052] In S130, a performance index corresponding to the parameter combination scheme is determined according to control parameters corresponding to the parameter combination scheme.

[0053] It can be understood that since the control parameters of the first parameter scheme and the second parameter scheme are different, the evaluation dimensions and calculation logic of the performance indexes need to be designed differently to accurately reflect the actual effect of different types of parameters.

[0054] For example, in a simulation environment, after loading the parameter scheme, the robot completes 10 same path tasks, the average values of various indexes are counted, and the final performance index is calculated through a weighting algorithm (such as an obstacle avoidance success rate value of 0.4, a path smoothness value of 0.3, a motion time consumption value of 0.2, and an energy consumption level value of 0.1, wherein the obstacle avoidance success rate is obtained by successively avoiding fixed obstacles ÷ total number of obstacles, the path smoothness value is (1- deviation from the preset channel ratio) × 100, the motion time consumption value can be obtained according to the timer, and the energy consumption level value is theoretical minimum energy consumption ÷ actual energy consumption). The higher the performance index, the better the path planning effect of the parameter scheme.

[0055] In this way, the core advantages of different parameter schemes can be truly reflected, and accurate basis is provided for subsequent comparison.

[0056] In one possible implementation, in S130, a performance index corresponding to the parameter combination scheme is determined according to control parameters corresponding to the parameter combination scheme, including:

[0057] In S131, a motion stage corresponding to the parameter combination scheme and control parameters corresponding to each motion stage are obtained.

[0058] It can be understood that the local path planning process of the mobile robot is not a single continuous motion state, but can be divided into multiple motion stages, the core task of each stage is different, and the corresponding control parameters called are also different. The motion stage can be determined according to the motion state change of the robot and the task target setting.

[0059] Exemplarily, after generating the local path, the speed change points (such as the starting point, the obstacle position, and the target point) on the path are automatically analyzed, the corresponding stages are divided, the control parameters corresponding to each stage are extracted from the parameter combination scheme, a stage-parameter mapping table is formed, and the stage-parameter mapping table is used for subsequent performance evaluation.

[0060] In S132, based on the obtained control parameters, motion indexes corresponding to each motion stage are obtained.

[0061] It can be understood that the motion index is used to describe the influence of the control parameters of each motion stage on the motion effect of the motion stage.

[0062] Exemplarily, for each motion stage, the motion index corresponding to each motion stage is determined by comparing the actual motion data with the parameter setting target.

[0063] For example, for the start-up acceleration phase: the motion indicators are the acceleration time error (the difference between the actual acceleration time and the upper limit of the parameter set acceleration time, such as setting the acceleration time ≤ 3 s, the actual time is 2.8 s, the error is -0.2 s) and the speed overshoot (the deviation of the actual maximum speed from the target cruise speed, such as the target 0.5 m / s, the actual 0.52 m / s, the overshoot 0.02 m / s), the speed-time curve of the acceleration process is recorded by the speed sensor, and the above two indicators are calculated. For the constant speed cruise phase: the motion indicators are the path tracking deviation (the average distance between the actual driving trajectory and the theoretical path, such as theoretical straight driving, the actual average deviation is 0.08 m) and the speed fluctuation rate (the standard deviation of the actual speed and the cruise speed, such as cruise speed 0.5 m / s, the actual speed fluctuates between 0.48-0.52 m / s, the fluctuation rate is 0.016), the path deviation is calculated by GPS or SLAM positioning data, and the speed fluctuation is calculated by the speed sensor. For the obstacle avoidance steering phase: the motion indicators are the steering response time (the time from detecting the obstacle to starting steering, such as setting the steering delay threshold ≤ 0.2 s, the actual response time is 0.18 s) and the obstacle avoidance distance accuracy (the deviation of the actual distance from the obstacle and the set safety distance, such as setting 0.3 m, the actual 0.32 m, the deviation 0.02 m), the response time is calculated by recording the obstacle appearance time and the steering start time by the obstacle detection sensor (such as laser radar); the minimum distance during obstacle avoidance is recorded by the distance sensor to calculate the deviation from the safety distance. For the deceleration and stopping phase: the motion indicators are the stopping position error (the straight line distance between the actual stopping position and the target point, such as target point (5, 3), actual (5.03, 3.02), error 0.036 m) and the deceleration smoothness (the change rate of acceleration during deceleration, such as acceleration from 0 linearly to -0.15 m / s², the higher the smoothness, the smaller the change rate), the error from the target point is calculated by the positioning system to obtain the stopping position; the acceleration curve of the deceleration process is recorded by the acceleration sensor, and the fluctuation of the curve slope is calculated (the smaller the fluctuation, the higher the smoothness).

[0064] S133, based on the motion indicators, obtaining a comprehensive indicator of the parameter combination scheme.

[0065] It can be understood that the comprehensive indicator can be a whole evaluation of the motion indicators of each motion phase, and the motion indicators of the dispersed phases are integrated into a comprehensive indicator by weighted calculation according to the importance difference (i.e. weight) of different phases in the whole path planning, to reflect the overall effect of the parameter combination scheme.

[0066] For example, the weights are set according to the influence degree of the motion phase on the task target, the motion performance indicators of each phase are standardized to specific numerical values, and then the weighted comprehensive indicators are calculated according to the weights.

[0067] For example, the motion indicators of each stage of a certain parameter scheme correspond to the values of 80 (start acceleration), 70 (constant cruising), 90 (obstacle avoidance steering), and 85 (deceleration and stopping), respectively, and the weights of each stage are 10% for the start acceleration stage, 20% for the constant cruising stage, 30% for the obstacle avoidance steering stage, and 40% for the deceleration and stopping stage. Therefore, the comprehensive performance = 80 x 0.1 + 70 x 0.2 + 90 x 0.3 + 85 x 0.4 = 8 + 14 + 27 + 34 = 83.

[0068] In S134, the comprehensive indicator is taken as the performance indicator corresponding to the parameter combination scheme.

[0069] It can be understood that the comprehensive indicator can be directly mapped to the performance indicator corresponding to the parameter combination scheme. To cope with the fairness of evaluation in different scenarios, a scenario correction coefficient can be introduced. For example, in a complex dynamic environment, a 1.2 times amplification coefficient is given to the value of the obstacle avoidance steering stage, and the final performance indicator = comprehensive indicator x scenario correction coefficient (such as an obstacle avoidance scenario correction coefficient of 1.1, 83 x 1.1 = 91.3), which highlights the advantages of the scheme in the target scenario.

[0070] In this way, the overall effect of the parameter combination scheme can be converted into intuitive data to provide data support for subsequent judgment.

[0071] In S200, each control parameter corresponding to a second parameter scheme is obtained.

[0072] It can be understood that each control parameter corresponding to the second parameter scheme can be all the parameters contained in the second parameter scheme, i.e., basic control parameters (such as speed threshold and steering angular velocity) and adaptive adjustment parameters (such as dynamic obstacle avoidance value and terrain adaptation value). For example, the complete control parameters of a certain second parameter scheme are speed threshold 0.5 m / s, steering angular velocity 20° / s, safety distance reference 0.3 m, dynamic obstacle avoidance value 0.8, terrain adaptation value 0.6, and path correction step 0.1 m.

[0073] In S300, parameter influence data corresponding to each control parameter is obtained, and the target influence data of the second parameter scheme is obtained by analyzing the parameter influence data corresponding to each control parameter. The parameter influence data is used to correct the performance indicator. The target influence data is calculated according to the importance proportion of the parameters in the motion function.

[0074] It can be understood that the parameter influence data can be a quantitative index for measuring the influence degree of a single control parameter on the path planning performance index, and the greater the value of the parameter influence data, the more significant the influence of the parameter on the performance index. The target influence data is used to avoid focusing only on the influence of a single parameter and ignoring the balance of the overall scheme. For example, in a certain second parameter scheme, the influence value of dynamic obstacle avoidance is as high as 0.9, but the influence value of terrain adaptation is only 0.2. If only the dynamic obstacle avoidance weight is considered, it can be considered that this scheme is the best, but the comprehensive average value is 0.55 (assuming that the average value of other parameters is 0.4), which indicates that the scheme has a short board in terrain adaptation and the overall balance is general, thereby providing a more comprehensive evaluation basis for subsequent ranking, rather than relying on the advantage of a single parameter to judge the pros and cons of the scheme.

[0075] Exemplarily, as Figure 2 Under the premise of fixing other parameters, the value of the target parameter is adjusted alone, the change amplitude of the performance index after each adjustment is recorded, and the parameter influence data is calculated according to the change amplitude. For example, the performance index changes by 8 when the dynamic obstacle avoidance value is adjusted by 0.1, and the performance index changes by only 3 when the safety distance benchmark is adjusted by 0.1, so the influence value of dynamic obstacle avoidance is set to 0.8, and the influence value of the safety distance benchmark is set to 0.3.

[0076] Exemplarily, the parameter influence data of all control parameters in the second parameter scheme is calculated (such as being calculated according to the importance proportion of the parameters in the motion function) to comprehensively reflect the overall influence degree of all parameters in the scheme on the performance index, and then the target influence data of the second parameter scheme is obtained.

[0077] For example, the complexity proportion of each stage is calculated first, then the average value of the parameter influence data after adjustment in each stage is calculated, and the target influence data is calculated by weighting according to the stage proportion.

[0078] S400, according to the target influence data and the performance index of the second parameter scheme, a unique identifier is set for the second parameter scheme. And a unique identifier is set for the first parameter scheme according to the performance index of the first parameter scheme.

[0079] It can be understood that the original performance index of the second parameter scheme is corrected by the target influence data to obtain an adjusted performance index, and a unique identifier is set for the adjusted performance index. A unique identifier is set for the first parameter scheme according to the performance index of the first parameter scheme. Since the first parameter scheme only contains basic control parameters and does not have adaptive adjustment parameters, the parameter influence data is relatively fixed (the influence degree of the basic parameters changes little, and there is no need to calculate the target influence data additionally), so the original performance index can be directly compared with the original performance index of other first parameter schemes, or it can be corrected.

[0080] It should be noted that the comparison of the performance indicators of the second parameter scheme and the comparison of the original performance indicators of the first parameter scheme are two independent comparison processes, that is, the internal comparison of the two types of schemes is first compared, and then the comparison results of the two types of schemes are integrated in the subsequent steps, because the applicable scenarios of the two types of schemes may be different, separate comparison can enable quick invocation of the best scheme of the corresponding category according to the scene requirements when outputting, avoiding the adaptability deviation or value misjudgment caused by using a single standard to evaluate different types of schemes. The problems caused by mixing the two types of schemes together for comparison are described in detail as follows:

[0081] Problem: If the original performance indicator of the first scheme A1 is 92 (safety distance compliance, obstacle avoidance success rate 100%), and the original indicator of the second scheme B1 is 88 (but contains dynamic obstacle avoidance influence value, target influence data is 1.2), if the mixed comparison is used, the modified indicator (B1 modified to 105.6), will cause A1 (static scene optimal) to be set to 2, and B1 to be set to 1, but the reliability of A1 in the static scene is much better than that of B1, the mixed comparison result will misjudge, causing the output parameter scheme to be not the best scheme, thereby affecting the working efficiency of the mobile robot.

[0082] By way of example, the adjusted performance indicator of the second parameter scheme can be compared with the adjusted performance indicators of other second parameter schemes, the value of the performance indicator is set to 1, the second largest is set to 2, the third largest is set to 3, and so on.

[0083] By way of example, the adjusted performance indicator can be the product of the original performance indicator and the target influence data (for example, original performance indicator x target influence data) or the sum of the original performance indicator and ten times the target influence data (for example, original performance indicator + (target influence data x 10), which can be calibrated according to the indicator range, such as full 100, the latter can avoid the adjusted indicator exceeding the range). For example, the original indicator of a certain second parameter scheme A is 90, the comprehensive coefficient is 0.6, the adjusted indicator is 90x0.6=54, or the original indicator of a second parameter scheme B is 85, the comprehensive coefficient is 0.7, the adjusted indicator is 85x0.7=59.5.

[0084] For example, according to the calculation results described above, the scheme B (59.5) is ranked higher than the scheme A (54). The beneficial effect of this comparison method is that if the original indexes of two schemes are close, the scheme with higher target impact data (representing better overall impact of parameters and better balance) will be ranked higher, avoiding the inaccurate measurement of the comprehensive adaptation ability of the parameter scheme due to the unquantified evaluation, for example, the original index of the scheme C is 88, the comprehensive coefficient is 0.5 (after adjustment, 44), the original index of the scheme D is 86, the comprehensive coefficient is 0.6 (after adjustment, 51.6). If not quantified, it will be considered that the scheme C is better than the scheme D (i.e., the original index of the scheme C is 88, which is greater than the original index of the scheme D, which is 86), but at this time, the scheme D is ranked better (because the overall support of the parameters of the scheme D to the performance is stronger), which will lead to the inaccurate measurement of the comprehensive adaptation ability of the parameter scheme, and further lead to the output of the parameter scheme that is not the best scheme, thereby affecting the working efficiency of the mobile robot.

[0085] S500, selecting at least one parameter scheme from the first parameter scheme and the second parameter scheme after setting the identifier to output.

[0086] It can be understood that the two types of schemes compared in the foregoing are integrated according to the scene adaptation priority and then output, and the output content can include key information of the scheme, and the output object needs to be connected to the control or decision system of the robot.

[0087] For example, when the robot enters the shopping mall scene, the second parameter scheme of the identifier 1 can be automatically called to load the corresponding parameters to realize the adaptive optimization of the local path planning. When the robot enters the warehouse scene, the first parameter scheme of the identifier 1 is called to realize the accurate matching of the scene and the parameters.

[0088] It should be noted that the scheme output to the robot can be one parameter scheme or more than one parameter scheme, for example, the working task of the robot can include entering the shopping mall first and then entering the warehouse scene, so that the parameter scheme matching the shopping mall and the parameter scheme matching the warehouse need to be output, such as the second parameter scheme of the identifier 1 and the first parameter scheme of the identifier 1.

[0089] In this way, in the local path planning parameter setting process, the advantages of the first parameter scheme debugging are retained, and the parameter influence data of each control parameter in the second parameter scheme is accurately quantified through the target influence data, avoiding the situation that the second parameter scheme cannot accurately measure the comprehensive adaptation ability of the second parameter scheme due to unquantized evaluation. In this way, the problem that the output parameter scheme is not the best scheme due to directly outputting the first parameter scheme to the robot in the traditional method can be avoided, and the problem that the advantages of the second parameter scheme are covered (for example, the comprehensive adaptation ability of the second parameter scheme cannot be accurately measured due to unquantized evaluation) or the reasonable value of the first parameter scheme is ignored (for example, the second parameter scheme is blindly selected, and the advantages of the first parameter scheme are ignored) can be avoided. The value of each scheme can be reflected through the set identifier, so that the output parameter scheme is the best scheme, thereby improving the working efficiency of the mobile robot.

[0090] In a possible implementation, the mobile robot local path planning parameter automatic setting method further includes:

[0091] S501, obtaining parameter influence data of the basic control parameters and the adaptive adjustment parameters in the target environment.

[0092] It can be understood that the target environment can be a standardized simulation environment constructed according to the actual working scene of the robot, which is used to accurately simulate the characteristics of a specific environment (such as obstacle distribution, dynamic interference intensity, etc.). The parameter influence data can be a quantitative value obtained by separately evaluating the influence degree of each parameter on the path planning performance in the above specific environment.

[0093] Exemplarily, in the target environment, all control parameters except the to-be-evaluated parameter are kept unchanged, the to-be-evaluated parameter is adjusted in a fixed step within its value range, the change amount of the performance index after each adjustment is calculated, the change amount is normalized, the parameter influence data of each adjustment is obtained, and the average value of the parameter influence data of all adjustment points of the parameter is obtained. The parameter influence data of the target environment.

[0094] S502, obtaining environmental parameter data of the second parameter scheme in the target environment according to the parameter influence data of each control parameter in the target environment.

[0095] It can be understood that the environmental parameter data can be the average value of the parameter influence data of all control parameters of the second parameter scheme in the target environment, which is used to reflect the overall parameter influence level of the scheme in the environment.

[0096] Exemplarily, the parameter influence data of all control parameters in the second parameter scheme is arithmetically averaged to comprehensively reflect the overall influence degree of all parameters in the scheme on the performance index, and then the environmental parameter data of the second parameter scheme is obtained.

[0097] In a possible implementation, S502, the environmental parameter data of the second parameter scheme in the target environment is obtained according to the parameter influence data of each control parameter in the target environment, including:

[0098] S512, obtaining the environmental complexity of each motion stage in the second parameter scheme, and the key control parameters in the parameter combination scheme that meet the preset condition.

[0099] It can be understood that the environmental complexity of each motion stage can be a quantitative value of the complexity of the environment in which the robot is located in different motion stages (start-up acceleration, uniform cruise, obstacle avoidance steering, and deceleration stop), which can be evaluated in combination with the environmental characteristics (such as obstacle density and dynamic interference intensity) of the stage, and is used to reflect the necessity of parameter adjustment in the stage (the higher the complexity, the more attention is needed for parameter influence). The key control parameters in the parameter combination scheme that meet the preset condition can be core parameters that have a decisive effect on the performance of the corresponding motion stage in the parameter combination scheme. The preset condition is used to select the judgment standard of the control parameters that have a significant impact on the performance, for example, it can be a condition in which the influence degree on the performance index of the running stage is ranked first, such as dynamic obstacle avoidance in the obstacle avoidance steering stage, which has the highest influence degree on the obstacle avoidance success rate and is listed as a key parameter.

[0100] For example, for each stage, the sub-indicators are calculated based on the environmental feature information, and then the comprehensive complexity is obtained by weighted summation: environmental complexity = static complexity x 0.3 + dynamic complexity x 0.5 + terrain complexity x 0.2.

[0101] Static complexity calculation example: obstacle density = 3 / m², spatial constraint degree = channel width / robot width = 1.2 (corresponding to 0.8), then static complexity = (3 / 5) x 0.5 + (1-1.2 / 2) x 0.5 = 0.3 + 0.2 = 0.5

[0102] Dynamic complexity calculation example: dynamic obstacle number = 2 (corresponding to 0.6), motion direction and robot angle = 30°, then dynamic complexity = 0.6 x 0.6 + 0.5 x 0.4 = 0.36 + 0.2 = 0.56; then the comprehensive environmental complexity = 0.5 x 0.3 + 0.56 x 0.5 + 0.2 x 0.2 = 0.15 + 0.28 + 0.04 = 0.47.

[0103] S522, adjusting the parameter influence data based on the environmental complexity and the key control parameters in the parameter combination scheme that meet the preset condition.

[0104] It can be understood that the environmental complexity is mapped to the stage adjustment coefficient, the key control parameter is given a corresponding weight, the non-key parameter is given a corresponding weight, that is, the influence weight of important parameters in complex environment is amplified according to the environmental complexity, that is, the higher the stage of environmental complexity, the higher the weight of the parameter influence data of the key control parameter; the parameter influence data of the non-key parameter or the parameter of the low complexity stage is appropriately reduced. For example, the adjusted parameter influence data = original parameter influence data x stage adjustment coefficient x individual adjustment coefficient.

[0105] In this way, through such adjustment, the influence of the key parameter in the complex stage is sufficiently amplified, which is more in line with the priority of the parameter in the actual scene.

[0106] S532, according to the adjusted parameter influence data of each control parameter in the target environment, obtaining the environmental parameter data of the second parameter scheme in the target environment.

[0107] It can be understood that all control parameters are integrated through the environmental complexity and the adjusted parameter influence data of the key parameter, and the overall parameter influence level of the second parameter scheme in the target environment, that is, the environmental parameter data, is obtained by average calculation. For example, the proportion of each stage complexity is calculated first, then the average value of the adjusted parameter influence data in each stage is calculated, and the environmental parameter data is calculated by weighting according to the stage proportion.

[0108] In this way, both the individual differences of the parameters and the comprehensive influence of the environment and the stage are reflected.

[0109] In one possible implementation, please refer to Figure 3 The target environment includes at least one of static obstacles, dynamic interference and terrain features, and the mobile robot local path planning parameter automatic setting method further includes:

[0110] S5321, the parameter influence data of each control parameter under static obstacles is averaged to obtain static parameter data.

[0111] It can be understood that the static obstacle is used to describe an environment containing only fixed obstacles. The dynamic interference is used to describe an environment containing moving obstacles. The terrain feature is used to describe an environment with changing ground physical properties.

[0112] For example, in the static obstacle, the influence of each parameter on the performance is tested by the control variable method (for example, when the safety distance reference increases from 0.2 m to 0.5 m, the obstacle avoidance success rate increases from 80% to 100%, and the static parameter data is calculated). For example, the parameter influence data of a second parameter scheme in the static obstacle is: safety distance reference 0.6, steering angular velocity 0.5, cruise speed 0.3, static obstacle avoidance 0.7, path bypass coefficient 0.4, a total of 5 parameters. Static parameter data = (0.6 + 0.5 + 0.3 + 0.7 + 0.4) ÷ 5 = 2.5 ÷ 5 = 0.5.

[0113] S5322, the parameter influence data of each control parameter under dynamic interference is averaged to obtain dynamic parameter data.

[0114] It can be understood that in the dynamic interference, the influence of each parameter on the dynamic obstacle avoidance performance is tested (for example, when the dynamic obstacle avoidance weight increases from 0.3 to 0.8, the dynamic obstacle avoidance success rate increases from 60% to 95%, and the dynamic parameter data is calculated). For example, the parameter influence data of a second parameter scheme in dynamic interference is: deceleration threshold 0.4, maximum steering angular velocity 0.5, dynamic obstacle avoidance 0.8, motion prediction coefficient 0.7, response delay 0.6, a total of 5 parameters. Dynamic parameter data = (0.4 + 0.5 + 0.8 + 0.7 + 0.6) ÷ 5 = 3.0 ÷ 5 = 0.6.

[0115] S5323, the parameter influence data of each control parameter under the terrain feature is averaged to obtain terrain parameter data. The parameter influence data corresponding to the control parameters in different target environments is different.

[0116] It can be understood that in the terrain feature, the influence of each parameter on the terrain adaptation performance is tested (for example, when the terrain adaptation coefficient increases from 0.5 to 0.9, the slope passing rate increases from 70% to 98%, and the terrain parameter data is calculated). For example, the parameter influence data of a second parameter scheme in the terrain feature is: climbing speed threshold 0.3, grip force compensation coefficient 0.4, terrain adaptation coefficient 0.9, slope response weight 0.7, damping coefficient 0.5, a total of 5 parameters. Terrain parameter coefficient = (0.3 + 0.4 + 0.9 + 0.7 + 0.5) / 5 = 2.8 / 5 = 0.56

[0117] In this way, the parameter influence data can be calculated for different environments, thereby providing a reliable basis for the calculation of target influence data.

[0118] S503, obtaining the target influence data of the second parameter scheme according to the environment parameter data.

[0119] It can be understood that the environment parameter data can be directly mapped to the target influence data of the second parameter scheme

[0120] In this way, the actual application value of the second parameter scheme can be objectively reflected, and data support can be provided for subsequent judgment.

[0121] In a possible implementation, the mobile robot local path planning parameter automatic setting method further includes:

[0122] S504, obtaining a basic control parameter in the first parameter scheme.

[0123] It can be understood that the parameters in the first parameter scheme are selected to ensure basic movement and obstacle avoidance, for example, speed-related parameters, obstacle avoidance basic parameters, path tracking parameters, and the like.

[0124] S505, obtaining parameter adjustment data of the first parameter scheme according to parameter influence data corresponding to the basic control parameter.

[0125] It can be understood that other parameters are fixed, and only the target parameter is adjusted (for example, the maximum speed and path error are fixed, and the static safety distance is increased from 0.3 m to 0.5 m), the change rate of the performance index is recorded, and the parameter influence data corresponding to the basic control parameter is calculated according to the change range. The parameter influence data of all control parameters in the first parameter scheme is calculated (for example, the calculation is performed according to the importance proportion of the parameter in the basic function), and the parameter adjustment data of the first parameter scheme is obtained.

[0126] For example, if the static safety distance is increased from 0.2 m to 0.3 m, and the performance index (for example, the obstacle avoidance success rate) is increased from 80% to 95% (a change of 15%), and the maximum change range is 20% (the limit influence of parameter adjustment), then the influence data of the parameter is 15 / 20=0.75.

[0127] S506, adjusting the performance index of the first parameter scheme according to the parameter adjustment data.

[0128] It can be understood that the original performance index can be corrected by the parameter adjustment data. For example, the original performance index x parameter adjustment data.

[0129] S507, setting a unique identifier for the first parameter scheme according to the adjusted performance index.

[0130] It can be understood that a unique identifier is set for the adjusted performance index.

[0131] For example, the adjusted performance index of the first parameter scheme can be compared with the adjusted performance index of other first parameter schemes, the value of the performance index is set to 1, the second largest is set to 2, the third largest is set to 3, and so on.

[0132] In this way, the robot control can be provided with clear scheme selection basis, and the output parameter scheme is not the best scheme, thereby affecting the working efficiency of the mobile robot.

[0133] In a possible implementation, the mobile robot local path planning parameter automatic setting method further includes:

[0134] S508, adjusting the performance index of the second parameter scheme according to the target influence data to obtain an adjusted performance index.

[0135] It can be understood that the original performance index of the second parameter scheme can be corrected by the target influence data to obtain the adjusted performance index, for example, the adjusted performance index can be obtained according to the product of the original performance index and the target influence data (for example, the original performance index x the target influence data) or the sum of the original performance index and ten times of the target influence data (for example, the original performance index + (the target influence data x 10)).

[0136] S509, setting a unique identifier for the second parameter scheme according to the adjusted performance index.

[0137] It can be understood that the adjusted performance index of the second parameter scheme can be compared with the adjusted performance index of other second parameter schemes, the value of the performance index is the largest, and the value of the performance index is the second largest, the value of the performance index is the third largest, and so on.

[0138] In this way, the robot control can be provided with clear scheme selection basis, and the output parameter scheme is not the best scheme, thereby affecting the working efficiency of the mobile robot.

[0139] In a possible implementation, the mobile robot local path planning parameter automatic setting method further includes:

[0140] S600, obtaining comparison data of the second parameter scheme and the first parameter scheme according to the comparison relationship between the performance index of the first parameter scheme and the adjusted performance index of the second parameter scheme. The adjusted performance index is an index obtained by adjusting the performance index of the second parameter scheme according to the target influence data.

[0141] It can be understood that all the adjusted performance indexes of the first parameter schemes and all the adjusted performance indexes of the second parameter schemes are collected, and the two types of schemes are compared in their respective professional dimensions to obtain the comparison data of the second parameter scheme and the first parameter scheme.

[0142] S700, combining the second parameter scheme and the first parameter scheme according to the comparison data to obtain a scheme list.

[0143] It can be understood that the unified list formed by merging the first and second parameter schemes according to the identification contains complete parameter information, adjusted performance indicators and category labels of all schemes, and is a basic data set for subsequent screening of schemes.

[0144] It should be noted that the unified list formed by merging the first and second parameter schemes does not require the system to only select the largest identification, but provides a basis for matching by scene. For example, the system detects that the current environment is static, and will preferentially select the first scheme with the largest identification from the unified list; detects a dynamic environment, and will preferentially select the second scheme with the largest identification. The benefit of the unified list is to "narrow the candidate range", rather than "force a single selection".

[0145] S800, in the scheme list, a pre-set screening rule is used to select the scheme corresponding to the identification for output or sending to the robot for execution.

[0146] It can be understood that the screening rule is a screening standard set according to actual application requirements, for example, selecting schemes with identifications 1, 2 and 3 in the scheme list, and containing at least one group of first parameter schemes and one group of second parameter schemes. For another example, the screening rule is to select schemes with identifications 1, 2 and 3 in the scheme list, and including at least two groups of second parameter schemes. For another example, the screening rule is to select the scheme with identification 1 in the scheme list, and the category of the scheme belongs to the second parameter scheme. The scheme list is traversed, and whether the screening rule is met is checked one by one, and the scheme meeting the screening rule is output or sent to the robot for execution (such as Figure 4 ), for example, the parameter values of the scheme are directly sent to the robot through TCP / IP or ROS topic communication.

[0147] In this way, in the local path planning parameter setting process, the advantages of convenient debugging of the first parameter scheme are retained, and the parameter influence data of each control parameter in the second parameter scheme is accurately quantified through the target influence data, avoiding the situation that the second parameter scheme cannot accurately measure the comprehensive adaptation ability of the second parameter scheme due to unquantized evaluation, which can avoid the problem that the output parameter scheme is not the best scheme in the traditional method, and can avoid the problem that the advantages of the second parameter scheme are covered (for example, the second parameter scheme cannot accurately measure the comprehensive adaptation ability of the second parameter scheme due to unquantized evaluation) or the reasonable value of the first parameter scheme is ignored (for example, the second parameter scheme is blindly selected, and the advantages of the first parameter scheme are ignored), so that the value of each type of scheme can be reflected through the set identification, and the output parameter scheme is the best scheme, thereby improving the working efficiency of the mobile robot.

[0148] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0149] Corresponding to the mobile robot local path planning parameter automatic setting method described in the above embodiments, the embodiments of the present application also provide a mobile robot local path planning parameter automatic setting system, and each unit of the system can realize each step of the mobile robot local path planning parameter automatic setting method. Figure 5 The structure block diagram of the mobile robot local path planning parameter automatic setting system provided by the embodiments of the present application is shown, and only the parts related to the embodiments of the present application are shown for ease of illustration.

[0150] Referring to Figure 5 The mobile robot local path planning parameter automatic setting system comprises:

[0151] An acquisition unit is configured to acquire at least two sets of parameter combination schemes and performance indicators corresponding to the parameter combination schemes; wherein the parameter combination scheme carries a first parameter scheme generated according to a basic control parameter and a second parameter scheme generated according to the basic control parameter and an adaptive adjustment parameter; and the performance indicator corresponding to the parameter combination scheme is used to reflect the path planning effect of the robot under the current parameter combination.

[0152] A detection unit is configured to acquire each control parameter corresponding to the second parameter scheme.

[0153] A calculation unit is configured to acquire parameter influence data corresponding to each control parameter, analyze the parameter influence data corresponding to each control parameter to obtain target influence data of the second parameter scheme; wherein the parameter influence data is used to correct the performance indicator; and the target influence data is data obtained according to the parameter influence data of multiple control parameters.

[0154] A classification unit is configured to set a unique identifier for the second parameter scheme according to the target influence data and the performance indicator of the second parameter scheme; and set a unique identifier for the first parameter scheme according to the performance indicator of the first parameter scheme.

[0155] An output unit is configured to select at least one parameter scheme from the first parameter scheme and the second parameter scheme after the identifiers are set and output the at least one parameter scheme.

[0156] It should be noted that the information interaction, execution process and the like between the above system / units, since based on the same concept as the method embodiments of the present application, the specific functions and the technical effects brought by them can be referred to the method embodiments part, and will not be repeated here.

[0157] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned functional units are taken as examples, and in actual application, the above-mentioned functions can be completed by different functional units according to needs, that is, the internal structure of the system is divided into different functional units to complete all or part of the functions described above. Each functional unit in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific name of each functional unit is only for mutual distinction, and is not used to limit the protection scope of the present application. The specific working process of the unit in the system can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0158] The embodiment of the present application also provides a mobile robot local path planning parameter automatic setting device, Figure 6 The mobile robot local path planning parameter automatic setting device provided by the embodiment of the present application is shown in a structural schematic diagram. As shown in the figure, the mobile robot local path planning parameter automatic setting device 6 of the embodiment includes at least one processor 60 (only one is shown in the figure), at least one memory 61 (only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the mobile robot local path planning parameter automatic setting device 6 realizes the steps in any of the above-mentioned various mobile robot local path planning parameter automatic setting method embodiments, or the mobile robot local path planning parameter automatic setting device 6 realizes the functions of each unit in the above-mentioned various system embodiments. Figure 6 Figure 6 Figure 6

[0159] Exemplarily, the computer program 62 can be divided into one or more units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 62 in the mobile robot local path planning parameter automatic setting device 6.

[0160] ​​​The mobile robot local path planning parameter automatic setting device 6 can be a single-chip microcomputer, a mobile phone, a tablet computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a desktop computer, a computing device, or a computer connected to a wireless modem, a laptop computer, a handheld communication device, a handheld computing device, etc. The mobile robot local path planning parameter automatic setting device 6 can include, but is not limited to, a processor 60, a memory 61. Those skilled in the art can understand that Figure 6 The mobile robot local path planning parameter automatic setting device 6 is only an example and does not constitute a limitation on the mobile robot local path planning parameter automatic setting device 6, and can include more or fewer components than shown, or combine certain components, or different components, for example, can also include an input / output device, a network access device, a bus, etc.

[0161] The processor 60 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic components, hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.

[0162] The storage 61 can be an internal storage unit of the mobile robot local path planning parameter automatic setting device 6 in some embodiments, for example, a hard disk or a memory of the mobile robot local path planning parameter automatic setting device 6. The storage 61 can also be an external storage device of the mobile robot local path planning parameter automatic setting device 6 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the mobile robot local path planning parameter automatic setting device 6. Further, the storage 61 can include both the internal storage unit and the external storage device of the mobile robot local path planning parameter automatic setting device 6. The storage 61 is used to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of the computer program, etc. The storage 61 can also be used to temporarily store data that has been output or will be output.

[0163] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in any of the above method embodiments.

[0164] The embodiments of the present application provide a computer program product. When the computer program product is run on a mobile robot local path planning parameter automatic setting device, the mobile robot local path planning parameter automatic setting device implements the steps in any of the above method embodiments.

[0165] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the mobile robot local path planning parameter automatic setting device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software delivery medium, such as U disk, mobile hard disk, magnetic disk or optical disk.

[0166] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0167] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0168] In the embodiments provided in the present application, it should be understood that the disclosed mobile robot local path planning parameter automatic setting device, mobile robot local path planning parameter automatic setting system and mobile robot local path planning parameter automatic setting method can be implemented in other ways. For example, the above-described mobile robot local path planning parameter automatic setting device and mobile robot local path planning parameter automatic setting system embodiments are only illustrative, for example, the division of the unit is only a logical functional division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0169] The units described as separated parts can or can not be physically separated, and the parts displayed as units can or can not be physical units, that is, can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0170] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or the equivalent replacement of some technical features can be made; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for automatically tuning local path planning parameters of a mobile robot, characterized in that, The method includes: Obtain at least two sets of parameter combination schemes and the corresponding performance indicators of the parameter combination schemes; wherein, the parameter combination scheme carries a first parameter scheme generated based on the basic control parameters and a second parameter scheme generated based on the basic control parameters and adaptive adjustment parameters; the performance indicators corresponding to the parameter combination schemes are used to reflect the path planning effect of the robot under the current parameter combination; the adaptive adjustment parameters are variable parameters used to cope with dynamic and complex environments based on the basic control parameters; Obtain each control parameter corresponding to the second parameter scheme; The process involves acquiring parameter impact data for each control parameter, analyzing this data, and obtaining target impact data for the second parameter scheme. This includes: acquiring parameter impact data for the basic control parameters and the adaptive adjustment parameters in a target environment; obtaining environmental parameter data for the second parameter scheme in the target environment based on the parameter impact data for each control parameter; and obtaining target impact data for the second parameter scheme based on the environmental parameter data. The parameter impact data is a quantitative indicator measuring the degree of influence of a single control parameter on path planning performance indicators, and is used to correct these performance indicators. The target impact data is obtained based on the parameter impact data of multiple control parameters. The target impact data is calculated by assigning the parameter impact data of all control parameters in the second parameter scheme to the parameters according to their importance proportion in the motion function. Based on the target impact data and the performance indicators of the second parameter scheme, a unique identifier is set for the second parameter scheme; and, based on the performance indicators of the first parameter scheme, a unique identifier is set for the first parameter scheme; wherein, the original performance indicators of the second parameter scheme are corrected through the target impact data to obtain the adjusted performance indicators, and then a unique identifier is set for the adjusted performance indicators; the comparison of the performance indicators of the second parameter scheme and the comparison of the original performance indicators of the first parameter scheme are two independent comparison processes, that is, firstly, the internal comparisons of the two types of schemes are performed separately, and then the comparison results of the two types of schemes are integrated in subsequent steps, and the adjusted performance indicators of the second parameter scheme are compared with the adjusted performance indicators of other second parameter schemes. The largest performance indicator value is assigned an identifier of 1, the second largest is assigned an identifier of 2, the third largest is assigned an identifier of 3, and so on; Select at least one parameter scheme from the first parameter scheme and the second parameter scheme after setting the identifier, and output it.

2. The automatic tuning method for local path planning parameters of a mobile robot as described in claim 1, characterized in that, Obtain at least two sets of parameter combinations and the corresponding performance metrics for each parameter combination, including: Acquire environmental feature information and moving target information; Based on the environmental feature information and the moving target information, at least two sets of parameter combination schemes are determined; Based on the control parameters corresponding to the parameter combination scheme, determine the performance index corresponding to the parameter combination scheme.

3. The automatic tuning method for local path planning parameters of a mobile robot as described in claim 2, characterized in that, Based on the control parameters corresponding to the parameter combination scheme, determine the performance indicators corresponding to the parameter combination scheme, including: Obtain the motion stage corresponding to the parameter combination scheme and the control parameters corresponding to each motion stage; Based on the acquired control parameters, the motion index corresponding to each motion stage is obtained; Based on the aforementioned motion indicators, a comprehensive index for the parameter combination scheme is obtained; The comprehensive index is used as the performance index corresponding to the parameter combination scheme.

4. The automatic tuning method for local path planning parameters of a mobile robot as described in claim 1, characterized in that, Based on the parameter influence data of each control parameter in the target environment, the environmental parameter data of the second parameter scheme in the target environment are obtained, including: Obtain the environmental complexity of each motion stage in the second parameter scheme, and the key control parameters in the parameter combination scheme that meet the preset conditions; The parameter influence data are adjusted based on the environmental complexity and the key control parameters that meet the preset conditions in the parameter combination scheme. Based on the adjusted parameter impact data of each control parameter in the target environment, the environmental parameter data of the second parameter scheme in the target environment are obtained.

5. The automatic tuning method for local path planning parameters of a mobile robot as described in claim 1, characterized in that, The target environment includes at least one of static obstacles, dynamic disturbances, and terrain features; the method further includes: The static parameter data are obtained by averaging the parameter influence data of each control parameter under the static obstacle. The dynamic parameter data are obtained by averaging the parameter influence data of each control parameter under the dynamic disturbance. The average of the parameter influence data of each control parameter under the terrain feature is used to obtain terrain parameter data; wherein, the parameter influence data corresponding to the control parameters under different target environments are different.

6. The automatic tuning method for local path planning parameters of a mobile robot as described in claim 1, characterized in that, The method further includes: Obtain the basic control parameters in the first parameter scheme; Based on the parameter influence data corresponding to the basic control parameters, the parameter adjustment data of the first parameter scheme is obtained; The performance indicators of the first parameter scheme are adjusted according to the parameter adjustment data. A unique identifier is set for the first parameter scheme based on the adjusted performance indicators.

7. The automatic tuning method for local path planning parameters of a mobile robot as described in claim 1, characterized in that, The method further includes: Based on the comparison between the performance indicators of the first parameter scheme and the adjusted performance indicators of the second parameter scheme, comparison data between the second parameter scheme and the first parameter scheme is obtained; wherein, the adjusted performance indicators are obtained by adjusting the performance indicators of the second parameter scheme based on the target impact data; Based on the comparison data, the second parameter scheme is combined with the first parameter scheme to obtain a scheme list; In the list of solutions, solutions with corresponding identifiers are selected for output using pre-set filtering rules, or sent to a robot for execution.

8. An automatic tuning device for local path planning parameters of a mobile robot, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1 to 7.

Images