Sampling-based parking speed planning method and device

Abstract

The invention discloses a parking speed planning method and device based on sampling, and relates to the technical field of automobile intelligent driving, and the parking speed planning method based on sampling comprises the steps: determining a longitudinal speed search space, and obtaining a search point of each moment; determining a transverse velocity search space to obtain a plurality of search end point moments; taking the plurality of search end point moments as parking completion moments, obtaining target search points from the search points according to a preset model, and connecting the target search points through straight lines to obtain a plurality of speed curves; and a parking mode is obtained, a speed curve selection model is determined according to the parking mode, and a target speed curve is obtained from the speed curves through the speed curve selection model. According to the invention, the accuracy of parking speed planning can be improved.

Description

Technical Field

[0001] The present application relates to the field of automobile intelligent driving technology, and in particular to a parking speed planning method and device based on sampling. Background Art

[0002] As the automobile industry develops towards electrification and intelligence, the Automatic Parking Assist (APA) system has become a research hotspot. The APA system can automatically plan a suitable parking path based on the current position of the vehicle and the target parking space information, and control the vehicle to drive along the planned path to achieve automatic parking. At present, the automatic parking speed control method is mainly controlled by the Electronic Stability Controller (ESC), which realizes parking longitudinal control by outputting the maximum parking speed and the remaining target distance. The remaining target distance is generally the smaller value of the distance from the vehicle to the obstacle and the parking planning distance. The speed reaches 0 when the remaining target distance is completed. However, this method cannot plan different parking speed curves for different drivers, so this automatic parking speed control method is not accurate enough in planning the parking speed.

[0003] In summary, how to improve the accuracy of parking speed planning is a problem that still needs to be solved.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a sampling-based parking speed planning method and device, aiming to solve the technical problem of how to improve the accuracy of parking speed planning.

[0006] To achieve the above objectives, the present application proposes a parking speed planning method based on sampling, the method comprising:

[0007] Determine the longitudinal velocity search space and obtain the search points at each moment;

[0008] Determine the lateral velocity search space and obtain multiple search end points;

[0009] taking the plurality of search end points as parking completion points respectively, obtaining target search points from the search points according to a preset model, and connecting the target search points with straight lines to obtain a plurality of speed curves;

[0010] A parking mode is acquired, a speed curve selection model is determined according to the parking mode, and a target speed curve is obtained from the speed curve by using the speed curve selection model.

[0011] In one embodiment, the step of determining the longitudinal velocity search space and obtaining the search points at each moment includes:

[0012] Draw a horizontal line along the time direction according to the distance at the previous moment, and the intersection with the distance at the next moment is the first search point;

[0013] In the longitudinal direction, the number of search points at a later time is determined by presetting the allowed parking speed, the time sampling interval, and the longitudinal sampling interval;

[0014] Taking the first search point as the starting point, the remaining search points are determined in sequence according to the longitudinal sampling interval in the direction of increasing distance along the longitudinal axis, and multiple search points at the next moment are obtained according to the number of search points.

[0015] In one embodiment, the step of determining the lateral velocity search space and obtaining multiple search end points comprises:

[0016] Determine the range of the search end time according to the preset maximum speed, target distance and the total parking time allowed for a single route;

[0017] According to the preset maximum speed, time sampling interval, target distance and preset parameters, the speed lateral search space is determined by searching within the range to obtain multiple search end points.

[0018] In one embodiment, the step of obtaining a target search point from the search points according to a preset model includes:

[0019] Calculating the velocity, acceleration and jerk of the search point;

[0020] Get comfort mode acceleration;

[0021] The economic mode acceleration is determined by the battery charge status, the battery recharge power allowed, the motor speed, the transmission system efficiency, the vehicle mass, the tire radius and the reduction ratio;

[0022] The cost of the search point is evaluated according to the speed, the acceleration, the jerk, the economy mode acceleration and the comfort mode acceleration according to a preset model, and the search point with the smallest cost is selected as the target search point.

[0023] In one embodiment, the steps of acquiring a parking mode, determining a speed curve selection model according to the parking mode, and obtaining a target speed curve from the speed curve by using the speed curve selection model include:

[0024] The parking mode obtained is comfort mode;

[0025] In the comfort mode, a speed curve cost value is calculated according to the acceleration and jerk of each search point of the speed curve;

[0026] A target speed curve is selected from the speed curves according to the speed curve cost value.

[0027] In one embodiment, the steps of acquiring a parking mode, determining a speed curve selection model according to the parking mode, and obtaining a target speed curve from the speed curve by using the speed curve selection model include:

[0028] The parking mode obtained is the economic mode;

[0029] In the economic mode, a speed curve cost value is calculated according to the acceleration of each search point of the speed curve and the acceleration of the economic mode;

[0030] A target speed curve is selected from the speed curves according to the speed curve cost value.

[0031] In one embodiment, the steps of acquiring a parking mode, determining a speed curve selection model according to the parking mode, and obtaining a target speed curve from the speed curve by using the speed curve selection model include:

[0032] The parking mode obtained is the efficiency mode;

[0033] In the efficiency mode, a speed curve cost value is calculated according to the speed of each search point of the speed curve and a preset maximum speed;

[0034] A target speed curve is selected from the speed curves according to the speed curve cost value.

[0035] In one embodiment, the steps of acquiring a parking mode, determining a speed curve selection model according to the parking mode, and obtaining a target speed curve from the speed curve by using the speed curve selection model include:

[0036] The parking mode obtained is a comprehensive mode;

[0037] In the comprehensive mode, the speed curve cost value is calculated according to the speed of each search point of the speed curve, the acceleration of each search point, the jerk of each search point, the preset maximum speed, the comfort mode acceleration and the economy mode acceleration;

[0038] A target speed curve is selected from the speed curves according to the speed curve cost value.

[0039] In one embodiment, after obtaining the target speed curve from the speed curve according to the parking mode, the method further includes:

[0040] Detect whether there are speed bumps on the parking path;

[0041] When a speed bump is detected, the speed bump distance from the starting point to the speed bump, the vehicle wheelbase and the preset speed bump travel speed are obtained;

[0042] The speed bump passing time is calculated by using the vehicle wheelbase and the preset speed bump travel speed;

[0043] Determine a target intersection point between the speed reduction belt distance and the target speed curve;

[0044] Taking the target intersection as the center, the preset speed bump speed as the slope, and the speed bump passing time as the length along the time direction, a target line segment is obtained;

[0045] Calculate the additional time required for passing through the speed bump, translate the target line segment in the direction of time increase by the distance required for the additional time, obtain a second target line segment, and use the two endpoints of the second target line segment as new target search points;

[0046] According to the new target search point, the longitudinal speed search space and the lateral speed search space are re-determined to obtain a new target speed curve.

[0047] In addition, to achieve the above purpose, the present application also proposes a parking speed planning device based on sampling, and the parking speed planning device based on sampling includes:

[0048] A longitudinal determination module is used to determine the longitudinal velocity search space and obtain the search points at each moment;

[0049] A lateral determination module is used to determine a lateral velocity search space and obtain multiple search end points;

[0050] a calculation module, configured to respectively use the plurality of search end points as parking completion points, obtain target search points from the search points according to a preset model, and connect the target search points with straight lines to obtain a plurality of speed curves;

[0051] The selection module is used to obtain a parking mode, determine a speed curve selection model according to the parking mode, and obtain a target speed curve from the speed curve through the speed curve selection model.

[0052] In addition, to achieve the above-mentioned purpose, the present application also proposes a sampling-based parking speed planning device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the sampling-based parking speed planning method as described above.

[0053] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the sampling-based parking speed planning method as described above are implemented.

[0054] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the sampling-based parking speed planning method as described above are implemented.

[0055] The present application provides a parking speed planning method based on sampling, which determines a longitudinal speed search space to obtain search points at various moments; determines a lateral speed search space to obtain multiple search end moments; uses the multiple search end moments as parking completion moments, obtains target search points from the search points according to a preset model, connects the target search points through straight lines to obtain multiple speed curves; obtains a parking mode, determines a speed curve selection model according to the parking mode, and obtains a target speed curve from the speed curve through the speed curve selection model.

[0056] In summary, the present application determines a speed search space to obtain multiple speed curves, and selects a suitable speed curve from the multiple speed curves by selecting different models through different parking modes, thereby improving the accuracy of parking speed planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0059] Figure 1 A flow chart of the first embodiment of the parking speed planning method based on sampling provided in the present application;

[0060] Figure 2 A flow chart of the second embodiment of the parking speed planning method based on sampling provided in the present application;

[0061] Figure 3 This is a schematic diagram of determining the longitudinal speed search space in the second embodiment of the sampling-based parking speed planning method of the present application;

[0062] Figure 4 This is a schematic diagram of determining a lateral speed search space in Embodiment 2 of the sampling-based parking speed planning method of the present application;

[0063] Figure 5 A flowchart diagram of the third embodiment of the parking speed planning method based on sampling of the present application is provided;

[0064] Figure 6 A flowchart diagram of a fourth embodiment of the parking speed planning method based on sampling of the present application is provided;

[0065] Figure 7 A flowchart diagram of a parking speed planning method based on sampling according to Embodiment 5 of the present application is provided;

[0066] Figure 8 A schematic diagram of replanning a speed curve according to a speed bump in Embodiment 5 of the parking speed planning method based on sampling of the present application;

[0067] Fig. 9 This is a schematic diagram of the module structure of the parking speed planning device based on sampling according to an embodiment of the present application;

[0068] Fig.10 Schematic diagram of the device structure of the hardware operating environment involved in the sampling-based parking speed planning method in the embodiment of the present application.

[0069] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0070] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0071] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0072] The solution of the present application is: determining a longitudinal speed search space to obtain search points at various moments; determining a lateral speed search space to obtain multiple search end moments; using the multiple search end moments as parking completion moments respectively, and obtaining target search points from the search points according to a preset model, connecting the target search points through straight lines to obtain multiple speed curves; obtaining a parking mode, determining a speed curve selection model according to the parking mode, and obtaining a target speed curve from the speed curve through the speed curve selection model.

[0073] At present, the automatic parking speed control method is mainly controlled by ESC, which realizes parking longitudinal control by outputting the maximum parking speed and the remaining target distance, where the remaining target distance is generally the smaller value of the distance from the vehicle to the obstacle and the parking planning distance. When the remaining target distance is completed, the speed reaches 0. However, this method cannot plan different parking speed curves for different drivers. Therefore, this automatic parking speed control method is not accurate enough in planning the parking speed. How to improve the accuracy of parking speed planning is a problem that still needs to be solved.

[0074] The present application determines a speed search space to obtain multiple speed curves, and selects different models through different parking modes to select a suitable speed curve from the multiple speed curves, taking into account the driving styles of different drivers and improving the accuracy of parking speed planning.

[0075] Based on this, the present application embodiment provides a parking speed planning method based on sampling, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the sampling-based parking speed planning method of the present application.

[0076] In this embodiment, the sampling-based parking speed planning method includes steps S10 to S40:

[0077] Step S10: determine the longitudinal velocity search space and obtain the search points at each moment;

[0078] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a parking speed planning device based on sampling, etc. The following takes the parking speed planning device based on sampling as an example to illustrate this embodiment and the following embodiments.

[0079] It should be noted that the longitudinal speed search space of this embodiment is established in a coordinate system with the distance as the vertical axis and the time as the horizontal axis. In this coordinate system, the slope is the speed. If the functional relationship between the distance s and the time t is:

[0080] s=f(t)

[0081] but Represents speed, represents acceleration, Represents the acceleration.

[0082] It is understandable that the longitudinal speed search space is determined to obtain the search points at each moment, wherein the longitudinal speed search space means that there are multiple search points at each moment, these search points are distributed along the longitudinal axis, and each search point represents a speed option.

[0083] Step S20: determining a lateral velocity search space to obtain multiple search end points;

[0084] It is understandable that the path length of a single parking is generally known, while the total parking time is unknown. The purpose of determining the lateral speed search space is to determine the search end time. Each search end time corresponds to the end point of a speed curve, so the number of search end times is the number of speed curves.

[0085] Step S30: taking the multiple search end points as parking completion points respectively, obtaining target search points from the search points according to a preset model, and connecting the target search points with straight lines to obtain multiple speed curves;

[0086] It is understandable that by determining the target search point from multiple search points according to the preset model, the speed at this moment is determined. By this method, the target search point at each moment can be determined, and each target search point is connected to form a speed curve. Different speed curves can be obtained by using different search end points as the parking completion time, so multiple speed curves are finally obtained.

[0087] Step S40: Acquire a parking mode, determine a speed curve selection model according to the parking mode, and obtain a target speed curve from the speed curve using the speed curve selection model.

[0088] It is understandable that different drivers will choose different parking modes according to their personal needs. This embodiment has four major modes, namely, comfort mode, economy mode, efficiency mode and comprehensive mode. By obtaining the parking mode, the speed curve selection model corresponding to the mode can be obtained. The speed curve selection models of different parking modes will select different speed curves.

[0089] This embodiment first determines a longitudinal speed search space to obtain search points at various moments; determines a lateral speed search space to obtain multiple search end moments; uses the multiple search end moments as parking completion moments, obtains target search points from the search points according to a preset model, connects the target search points through straight lines to obtain multiple speed curves; finally, obtains a parking mode, determines a speed curve selection model according to the parking mode, and obtains a target speed curve from the speed curves through the speed curve selection model.

[0090] In summary, this embodiment obtains multiple speed curves by determining the speed search space, and selects a suitable speed curve from the multiple speed curves by selecting different models according to different parking modes, thereby improving the accuracy of parking speed planning.

[0091] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , the step S10 includes steps S101 to S103:

[0092] Step S101: Draw a horizontal line along the time direction according to the distance at the previous moment, and the intersection with the distance at the next moment is the first search point;

[0093] It should be noted that each moment is sampled by the time interval Δ t To determine, the previous moment passed Δ t The next moment is the next moment. Draw a horizontal line along the time direction through the search point of the previous moment, and the intersection with the next moment is the first search point. Figure 3 As shown, Figure 3 Medium n The time is the previous time, t n+1 is the next moment, t n+1 The bottom search point is the first search point.

[0094] Step S102: determining the number of search points at a later time in the longitudinal direction by presetting the allowed parking speed, the time sampling interval, and the longitudinal sampling interval;

[0095] It should be noted that the number of search points at the next moment is determined by presetting the allowed parking speed, time sampling interval, and ordinate sampling interval. The specific formula is:

[0096]

[0097] Where n is the number of search points, v allow_t is the preset parking speed, Δ t is the time sampling interval, Δ s is the ordinate sampling interval.

[0098] It is understandable that the parking speed allowed can be the smaller of the maximum speed set by the system and the speed determined by the slippery road conditions:

[0099]

[0100] Among them, v max-set is the preset maximum speed, is the speed determined according to the slippery road conditions, f r is the road friction coefficient, G is the vehicle mass, and r is the curvature radius of the path.

[0101] Step S103: taking the first search point as the starting point, determining the remaining search points in sequence according to the longitudinal sampling interval in the direction of increasing distance along the longitudinal axis, and obtaining multiple search points at the next moment according to the number of search points.

[0102] It is understandable that the search point diagram obtained is as follows Figure 3 As shown, t n+1 The search point is to start from the first search point, and the distance increases along the vertical axis ... s Then we get the second search point, and so on, we get all the search points, where the top search point represents a speed of v allow_t .

[0103] The step S20 includes steps S201 to S202:

[0104] Step S201: determining the range of the search end time according to the preset maximum speed, the target distance and the total parking time allowed for a single route;

[0105] It is understandable that the search method is to use (0, 0) as the search starting point, (P i , S target ) as the search end point to search the speed space. In order to control the lateral search space, the search end point P i The range of P i The range is:

[0106]

[0107] Among them, S target is the target distance, v max-set is the preset maximum speed, t allow The total parking time allowed for a single route.

[0108] Step S202: According to the preset maximum speed, time sampling interval, target distance and preset parameters, a speed lateral search space is determined by searching within the range to obtain multiple search end points.

[0109] It is understandable that the search end time P i The calculation formula is:

[0110]

[0111] Where i is a natural number, S target is the target distance, v max-set is the preset maximum speed, Δ t is the time sampling interval, c is the preset parameter determined by autonomous calibration, and this parameter is used to adjust the lateral search space density, such as Figure 4As shown, P0, P1, P2, P n This is the search end time.

[0112] In this embodiment, a horizontal line is drawn along the time direction according to the distance at the previous moment, and the intersection with the next moment is the first search point; the number of search points at the next moment is determined by presetting the allowed parking speed, time sampling interval, and ordinate sampling interval in the vertical axis direction; the first search point is used as the starting point, and the remaining search points are determined in sequence according to the ordinate sampling interval in the direction of increasing distance along the vertical axis, and multiple search points at the next moment are obtained according to the number of search points. The range of the search end time is determined according to the preset maximum speed, target distance, and the total parking time allowed for a single path; according to the preset maximum speed, time sampling interval, target distance, and preset parameters, the speed horizontal search space is determined by searching within the range to obtain multiple search end times.

[0113] In summary, this embodiment can obtain multiple search points and multiple search end points at each moment by determining the lateral speed search space and the longitudinal speed space. In this way, comprehensive speed options at each moment can be compared to ensure the accuracy of the final parking speed planning.

[0114] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 5 , the step S30 includes steps S301 to S304:

[0115] Step S301: Calculate the speed, acceleration and jerk of the search point;

[0116] It is understandable that in a coordinate system with distance as the vertical axis and time as the horizontal axis, Represents speed, represents acceleration, Represents the acceleration.

[0117] Step S302: Acquire the comfort mode acceleration;

[0118] It should be noted that the comfort mode acceleration is a value obtained based on experience or calibration methods.

[0119] Step S303: determining the economic mode acceleration according to the battery power status, the battery allowable recharging power, the motor speed, the transmission system efficiency, the vehicle mass, the tire radius and the reduction ratio;

[0120] The calculation formula for economic mode acceleration is:

[0121] a economic =min(a economic_soc, a economic_set )

[0122]

[0123] Among them, P is the battery's allowable recharge power, f is the motor speed, η is the transmission system efficiency from the motor to the wheel end, m is the vehicle mass, r is the tire radius, i is the reduction ratio, and a is the transmission system efficiency from the motor to the wheel end. economic_set It can be obtained through experience or calibration method.

[0124] Step S304: evaluating the cost of the search point according to the speed, the acceleration, the jerk, the economy mode acceleration and the comfort mode acceleration according to a preset model, and selecting the search point with the smallest cost as the target search point;

[0125] It is understandable that since there are multiple search points at each moment, the cost value of each search point can be calculated by the preset model to screen out the most suitable search point. The formula for calculating the cost value of the search point is:

[0126]

[0127] Among them, cost represents the cost value, Represents speed, represents acceleration, represents the acceleration, v max is the preset maximum speed, a comfort is the comfort mode acceleration, a economic is the acceleration in economic mode, H(t) represents the heuristic function with the terminal target speed of 0 and the target acceleration of 0, ω v ,ω acc1 ,ω acc2 ,ω jerk , ω1, ω2 are coefficients that increase over time.

[0128] By calculating the cost of each search point at each moment, the search point with the smallest cost can be selected as the target search point, and the speed curve can be obtained by connecting the target search points with a straight line. Each search end moment corresponds to a speed curve. Optionally, in order to make the speed curve smooth, the quadratic programming algorithm can be used to smooth the speed curve.

[0129] This implementation calculates the speed, acceleration and jerk of the search point; obtains the comfort mode acceleration; determines the economy mode acceleration through the battery power status, the battery allowable recharging power, the motor speed, the transmission system efficiency, the vehicle mass, the tire radius and the reduction ratio; evaluates the cost of the search point according to the speed, the acceleration, the jerk, the economy mode acceleration and the comfort mode acceleration according to a preset model, and selects the search point with the smallest cost as the target search point.

[0130] In summary, this embodiment obtains a target search point from multiple search points by calculating the search point cost value, and obtains multiple speed curves with different search end points, thereby improving the accuracy of parking speed planning.

[0131] Based on the first embodiment of the present application, in the fourth embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. Figure 6 , the step S40 includes steps S401 to S403:

[0132] Step S401: the acquired parking mode is the comfort mode;

[0133] It should be noted that the parking mode is selected by the driver, and comfort is generally related to acceleration and jerk. Comfortable acceleration is a comfort It can usually be obtained through experience, and the acceleration should be as constant as possible, that is, the jerk should be as close to 0 as possible.

[0134] Step S402: in the comfort mode, calculating the speed curve cost value according to the acceleration and jerk of each search point of the speed curve;

[0135] The formula for calculating the speed curve cost value in comfort mode is:

[0136]

[0137] Among them, cost is the cost value of the speed curve, n is the number of target search points on the curve, is the acceleration, is the acceleration, a comfort is the comfort mode acceleration, ω acc1 With ω jerk is the coefficient.

[0138] Step S403: selecting a target speed curve from the speed curves according to the speed curve cost value.

[0139] The speed curve cost value of each speed curve can be calculated through the calculation formula of the comfort mode, and the speed curve with the smallest speed curve cost value is selected as the final target speed curve.

[0140] When other parking modes are selected, step S40 may include:

[0141] The parking mode obtained is the economic mode;

[0142] In the economic mode, a speed curve cost value is calculated according to the acceleration of each search point of the speed curve and the acceleration of the economic mode;

[0143] A target speed curve is selected from the speed curves according to the speed curve cost value.

[0144] It should be noted that the economic mode mainly considers the energy consumption problem. Generally speaking, energy consumption decreases as the energy recovery intensity increases. When the energy recovery intensity increases to a certain value, energy consumption increases again as the energy recovery intensity increases. The formula for calculating the speed curve cost value in the economic mode is:

[0145]

[0146] Among them, a economic is the economic mode acceleration. By calculating the speed curve cost value of each speed curve, the speed curve with the smallest speed curve cost value can be selected as the final target speed curve.

[0147] The step S40 may further include:

[0148] The parking mode obtained is the efficiency mode;

[0149] In the efficiency mode, a speed curve cost value is calculated according to the speed of each search point of the speed curve and a preset maximum speed;

[0150] A target speed curve is selected from the speed curves according to the speed curve cost value.

[0151] It should be noted that in the efficiency mode, efficiency refers to the shortest time for the same distance, which can be converted into maximum speed priority. The formula for calculating the speed curve cost value in the efficiency mode is:

[0152]

[0153] Among them, v max By calculating the speed curve cost value of each speed curve, the speed curve with the smallest speed curve cost value can be selected as the final target speed curve.

[0154] The step S40 may further include:

[0155] The parking mode obtained is a comprehensive mode;

[0156] In the comprehensive mode, the speed curve cost value is calculated according to the speed of each search point of the speed curve, the acceleration of each search point, the jerk of each search point, the preset maximum speed, the comfort mode acceleration and the economy mode acceleration;

[0157] A target speed curve is selected from the speed curves according to the speed curve cost value.

[0158] It should be noted that the comprehensive mode refers to the comprehensive consideration of comfort, economy and efficiency to determine the target speed curve. The formula for calculating the speed curve cost value in the comprehensive mode is:

[0159]

[0160] in, Represents speed, represents acceleration, represents the acceleration, v max is the preset maximum speed, a comfort is the comfort mode acceleration, a economic is the economic mode acceleration, ω v ,ω acc1 ,ω acc2 ,ω jerk , ω1, ω2 are coefficients that increase with time. By calculating the speed curve cost value of each speed curve, the speed curve with the smallest speed curve cost value can be selected as the final target speed curve.

[0161] The parking mode obtained in this embodiment is the comfort mode; in the comfort mode, a speed curve cost value is calculated according to the acceleration and jerk of each search point of the speed curve; and a target speed curve is selected from the speed curve according to the speed curve cost value. When the parking mode obtained is other modes, the speed curve cost value is also calculated according to the corresponding calculation formula, and the target curve is selected.

[0162] In summary, this embodiment can determine different speed planning curves according to different parking modes, provide multiple parking options, and improve the accuracy of parking speed planning.

[0163] Based on the first embodiment of the present application, in the fifth embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 7 After step S40, the sampling-based parking speed planning may further include steps S41 to S47:

[0164] Step S41: Detect whether there is a speed bump on the parking path;

[0165] It is understandable that when a speed bump is encountered on the parking path, the vehicle needs to slow down to pass through it, so it is necessary to detect whether there is a speed bump on the parking path to determine whether the target speed curve is feasible.

[0166] Step S42: when a speed bump is detected, obtaining the speed bump distance from the starting point to the speed bump, the vehicle wheelbase and the preset speed bump travel speed;

[0167] It should be noted that when a speed bump is detected, it indicates that the previously determined speed curve needs to be adjusted. The speed bump distance is the distance from the starting point to the speed bump. In this embodiment, S speedup Indicates the distance of the speed bump; the vehicle wheelbase is the distance between the midpoints of two adjacent wheels on the same side of the vehicle and the two perpendicular lines perpendicular to the longitudinal symmetry plane of the vehicle. In simple terms, it is the straight-line distance from the center of the front axle to the center of the rear axle.

[0168] Step S43: Calculating the speed bump passing time by using the vehicle wheelbase and the preset speed bump travel speed;

[0169] It is understandable that the formula for calculating the speed bump passing time is:

[0170] t speedup =L / v speedup

[0171] Where L is the vehicle wheelbase, v speedup The speed for traveling on the preset speed bump.

[0172] Step S44: determining a target intersection point between the speed reduction belt distance and the target speed curve;

[0173] like Figure 8 As shown, O~P i The curve is a target speed curve, and G1 is a target intersection point between the speed reduction belt distance and the target speed curve.

[0174] Step S45: Taking the target intersection as the center, the preset speed bump speed as the slope, and the speed bump passing time as the length along the time direction, a target line segment is obtained;

[0175] like Figure 8 As shown, line segment F 1- F2 is the target line segment, line segment F 1- The length of F2 on the horizontal axis of time is the time it takes to pass the speed bump. 1- The slope of F2 is the preset speed bump driving speed.

[0176] Step S46: calculating the additional time required for passing through the speed bump, translating the target line segment in the time increasing direction by the distance required for the additional time, obtaining a second target line segment, and using the two endpoints of the second target line segment as new target search points;

[0177] like Figure 8 As shown, the line segment F 1- After F2 is translated along the time increasing direction by the distance required to increase the time length, the resulting line segment F 11 -F 21 This is the second target segment, F 11 Dot and F 21 The points are the two new target search points.

[0178] Step S47: re-determine the longitudinal speed search space and the lateral speed search space according to the new target search point to obtain a new target speed curve.

[0179] It is understandable that, through the new target search point, a new target speed curve can be obtained according to the method of determining the longitudinal speed search space and the lateral speed search space, such as Figure 8 As shown, O~P i1 This is the new target speed curve.

[0180] This embodiment detects whether there is a speed bump on the parking path; when the existence of a speed bump is detected, the speed bump distance from the starting point to the speed bump, the vehicle wheelbase and the preset speed bump speed are obtained; the speed bump passing time is calculated by the vehicle wheelbase and the preset speed bump speed; the target intersection point of the speed bump distance and the target speed curve is determined; with the target intersection point as the center, the preset speed bump speed as the slope, and the speed bump passing time as the length along the time direction, a target segment is obtained; the additional time consumed due to passing the speed bump is calculated, the target segment is translated along the time increasing direction by the distance required to increase the time, to obtain a second target segment, and the two endpoints of the second target segment are used as new target search points; according to the new target search point, the longitudinal speed search space and the lateral speed search space are re-determined to obtain a new target speed curve.

[0181] In summary, this embodiment can re-plan the speed curve when encountering a speed bump in the parking path, so that the parking process meets the deceleration requirements of the speed bump, thereby improving the accuracy of parking speed planning.

[0182] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the sampling-based parking speed planning method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0183] This application also provides a parking speed planning device based on sampling, please refer to Fig. 9 , the sampling-based parking speed planning device includes:

[0184] A longitudinal determination module 10 is used to determine the longitudinal velocity search space and obtain the search points at each moment;

[0185] A lateral determination module 20, used to determine a lateral velocity search space and obtain a plurality of search end points;

[0186] A calculation module 30, configured to respectively use the plurality of search end points as parking completion points, obtain target search points from the search points according to a preset model, and connect the target search points with straight lines to obtain a plurality of speed curves;

[0187] The selection module 40 is used to obtain a parking mode, determine a speed curve selection model according to the parking mode, and obtain a target speed curve from the speed curve through the speed curve selection model.

[0188] This embodiment first determines a longitudinal speed search space to obtain search points at various moments; determines a lateral speed search space to obtain multiple search end moments; uses the multiple search end moments as parking completion moments, obtains target search points from the search points according to a preset model, connects the target search points through straight lines to obtain multiple speed curves; finally, obtains a parking mode, determines a speed curve selection model according to the parking mode, and obtains a target speed curve from the speed curves through the speed curve selection model.

[0189] In summary, this embodiment obtains multiple speed curves by determining the speed search space, and selects a suitable speed curve from the multiple speed curves by selecting different models according to different parking modes, thereby improving the accuracy of parking speed planning.

[0190] In one embodiment, the longitudinal determination module 10 is further used to draw a horizontal line along the time direction according to the distance at the previous moment, and the intersection with the next moment is the first search point; in the longitudinal axis direction, the number of search points at the next moment is determined by presetting the allowed parking speed, the time sampling interval, and the longitudinal coordinate sampling interval; taking the first search point as the starting point, in the direction of increasing distance along the longitudinal axis, the remaining search points are determined in sequence according to the longitudinal coordinate sampling interval, and multiple search points at the next moment are obtained according to the number of search points.

[0191] In one embodiment, the lateral determination module 20 is further used to determine the range of the search end time according to the preset maximum speed, the target distance and the total parking time allowed for a single path; according to the preset maximum speed, the time sampling interval, the target distance and the preset parameters, the speed lateral search space is determined by searching within the range to obtain multiple search end times.

[0192] In one embodiment, the calculation module 30 is also used to calculate the speed, acceleration and jerk of the search point; obtain the comfort mode acceleration; determine the economy mode acceleration through the battery power status, the battery allowable recharging power, the motor speed, the transmission system efficiency, the vehicle mass, the tire radius and the reduction ratio; evaluate the cost of the search point according to the speed, the acceleration, the jerk, the economy mode acceleration and the comfort mode acceleration according to a preset model, and select the search point with the smallest cost as the target search point.

[0193] In one embodiment, the selection module 40 is further configured to obtain a parking mode that is a comfort mode; in the comfort mode, a speed curve cost value is calculated based on the acceleration and jerk of each search point of the speed curve; and a target speed curve is selected from the speed curve based on the speed curve cost value.

[0194] In one embodiment, the selection module 40 is further used to obtain a parking mode, determine a speed curve selection model according to the parking mode, and obtain a target speed curve from the speed curve through the speed curve selection model. The steps include: the parking mode obtained is an economic mode; in the economic mode, a speed curve cost value is calculated according to the acceleration of each search point of the speed curve and the acceleration of the economic mode; and a target speed curve is selected from the speed curve according to the speed curve cost value.

[0195] In one embodiment, the selection module 40 is further used to obtain a parking mode, determine a speed curve selection model according to the parking mode, and obtain a target speed curve from the speed curve through the speed curve selection model. The steps include: the parking mode obtained is an efficiency mode; in the efficiency mode, a speed curve cost value is calculated according to the speed of each search point of the speed curve and a preset maximum speed; and a target speed curve is selected from the speed curve according to the speed curve cost value.

[0196] In one embodiment, the selection module 40 is further used to obtain a parking mode, determine a speed curve selection model according to the parking mode, and obtain a target speed curve from the speed curve through the speed curve selection model. The steps include: the parking mode obtained is a comprehensive mode; in the comprehensive mode, a speed curve cost value is calculated according to the speed of each search point of the speed curve, the acceleration of each search point, the acceleration of each search point, the preset maximum speed, the comfort mode acceleration and the economy mode acceleration; and a target speed curve is selected from the speed curve according to the speed curve cost value.

[0197] In one embodiment, the selection module 40 is further configured to include: detecting whether there is a speed bump on the parking path; when the presence of a speed bump is detected, obtaining the speed bump distance from the starting point to the speed bump, the vehicle wheelbase and the preset speed bump speed; calculating the speed bump passing time by the vehicle wheelbase and the preset speed bump speed; determining a target intersection point of the speed bump distance and the target speed curve; taking the target intersection point as the center, the preset speed bump speed as the slope, and the speed bump passing time as the length along the time direction to obtain a target segment; calculating the additional time consumed due to passing the speed bump, translating the target segment along the time increasing direction by the distance required to increase the time, obtaining a second target segment, and using the two endpoints of the second target segment as new target search points; and re-determining the longitudinal speed search space and the lateral speed search space according to the new target search point to obtain a new target speed curve.

[0198] The sampling-based parking speed planning device provided in the present application adopts the sampling-based parking speed planning method in the above embodiment, which can solve the technical problem of how to improve the accuracy of parking speed planning. Compared with the prior art, the sampling-based parking speed planning device provided in the present application has the same beneficial effects as the sampling-based parking speed planning method provided in the above embodiment, and other technical features in the sampling-based parking speed planning device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0199] The present application provides a sampling-based parking speed planning device, which includes: at least one processor; and a memory in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the sampling-based parking speed planning method in the above-mentioned embodiment 1.

[0200] Reference below Fig.10, which shows a schematic diagram of the structure of a sampling-based parking speed planning device suitable for implementing the embodiment of the present application. The sampling-based parking speed planning device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.10 The sampling-based parking speed planning device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0201] like Fig.10 As shown, the sampling-based parking speed planning device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the sampling-based parking speed planning device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the sampling-based parking speed planning device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a sampling-based parking speed planning device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0202] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0203] The sampling-based parking speed planning device provided in the present application adopts the sampling-based parking speed planning method in the above embodiment, which can solve the technical problem of how to improve the accuracy of parking speed planning. Compared with the prior art, the sampling-based parking speed planning device provided in the present application has the same beneficial effects as the sampling-based parking speed planning method provided in the above embodiment, and other technical features in the sampling-based parking speed planning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0204] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0205] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0206] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the sampling-based parking speed planning method in the above-mentioned embodiment.

[0207] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0208] The computer-readable storage medium may be included in the sampling-based parking speed planning device; or may exist independently without being assembled into the sampling-based parking speed planning device.

[0209] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the sampling-based parking speed planning device, the sampling-based parking speed planning device: determines a longitudinal speed search space to obtain search points at various moments; determines a lateral speed search space to obtain multiple search end moments; uses the multiple search end moments as parking completion moments respectively, obtains target search points from the search points according to a preset model, connects the target search points through straight lines, and obtains multiple speed curves; obtains a parking mode, determines a speed curve selection model according to the parking mode, and obtains a target speed curve from the speed curve through the speed curve selection model.

[0210] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0211] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0212] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0213] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned sampling-based parking speed planning method, and can solve the technical problem of how to improve the accuracy of parking speed planning. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the sampling-based parking speed planning method provided in the above-mentioned embodiment, and will not be repeated here.

[0214] The present application also provides a computer program product, including a computer program, which implements the steps of the sampling-based parking speed planning method as described above when executed by a processor.

[0215] The computer program product provided in this application can solve the technical problem of how to improve the accuracy of parking speed planning. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the sampling-based parking speed planning method provided in the above embodiment, which will not be repeated here.

[0216] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A parking speed planning method based on sampling, It is characterized in that The method includes: Determine the longitudinal velocity search space and obtain the search points at each moment; Determine the lateral velocity search space and obtain multiple search end points; taking the plurality of search end points as parking completion points respectively, obtaining target search points from the search points according to a preset model, and connecting the target search points with straight lines to obtain a plurality of speed curves; A parking mode is acquired, a speed curve selection model is determined according to the parking mode, and a target speed curve is obtained from the speed curve by using the speed curve selection model.

2. The method according to claim 1, It is characterized in that The step of determining the longitudinal velocity search space and obtaining the search points at each moment comprises: Draw a horizontal line along the time direction according to the distance at the previous moment, and the intersection with the distance at the next moment is the first search point; In the longitudinal direction, the number of search points at a later time is determined by presetting the allowed parking speed, the time sampling interval, and the longitudinal sampling interval; Taking the first search point as the starting point, the remaining search points are determined in sequence according to the longitudinal sampling interval in the direction of increasing distance along the longitudinal axis, and multiple search points at the next moment are obtained according to the number of search points.

3. The method according to claim 1, It is characterized in that The step of determining the lateral velocity search space and obtaining multiple search end points comprises: Determine the range of the search end time according to the preset maximum speed, target distance and the total parking time allowed for a single route; According to the preset maximum speed, time sampling interval, target distance and preset parameters, the speed lateral search space is determined by searching within the range to obtain multiple search end points.

4. The method according to claim 1, It is characterized in that The step of obtaining a target search point from the search points according to a preset model comprises: Calculating the velocity, acceleration and jerk of the search point; Get comfort mode acceleration; The economic mode acceleration is determined by the battery charge status, the battery recharge power allowed, the motor speed, the transmission system efficiency, the vehicle mass, the tire radius and the reduction ratio; The cost of the search point is evaluated according to the speed, the acceleration, the jerk, the economic mode acceleration and the comfort mode acceleration according to a preset model, and the search point with the smallest cost is selected as the target search point.

5. The method according to claim 1, It is characterized in that The steps of acquiring a parking mode, determining a speed curve selection model according to the parking mode, and obtaining a target speed curve from the speed curve by using the speed curve selection model include: The parking mode obtained is comfort mode; In the comfort mode, a speed curve cost value is calculated according to the acceleration and jerk of each search point of the speed curve; A target speed curve is selected from the speed curves according to the speed curve cost value.

6. The method according to claim 1, It is characterized in that The steps of acquiring a parking mode, determining a speed curve selection model according to the parking mode, and obtaining a target speed curve from the speed curve by using the speed curve selection model include: The parking mode obtained is the economic mode; In the economic mode, a speed curve cost value is calculated according to the acceleration of each search point of the speed curve and the acceleration of the economic mode; A target speed curve is selected from the speed curves according to the speed curve cost value.

7. The method according to claim 1, It is characterized in that The steps of acquiring a parking mode, determining a speed curve selection model according to the parking mode, and obtaining a target speed curve from the speed curve by using the speed curve selection model include: The parking mode obtained is the efficiency mode; In the efficiency mode, a speed curve cost value is calculated according to the speed of each search point of the speed curve and a preset maximum speed; A target speed curve is selected from the speed curves according to the speed curve cost value.

8. The method according to claim 1, It is characterized in that The steps of acquiring a parking mode, determining a speed curve selection model according to the parking mode, and obtaining a target speed curve from the speed curve by using the speed curve selection model include: The parking mode obtained is a comprehensive mode; In the comprehensive mode, the speed curve cost value is calculated according to the speed of each search point of the speed curve, the acceleration of each search point, the jerk of each search point, the preset maximum speed, the comfort mode acceleration and the economy mode acceleration; A target speed curve is selected from the speed curves according to the speed curve cost value.

9. The method according to claim 1, It is characterized in that After obtaining the target speed curve from the speed curve according to the parking mode, the method further includes: Detect whether there are speed bumps on the parking path; When a speed bump is detected, the speed bump distance from the starting point to the speed bump, the vehicle wheelbase and the preset speed bump travel speed are obtained; The speed bump passing time is calculated by using the vehicle wheelbase and the preset speed bump travel speed; Determine a target intersection point between the speed reduction belt distance and the target speed curve; Taking the target intersection as the center, the preset speed bump speed as the slope, and the speed bump passing time as the length along the time direction, a target line segment is obtained; Calculate the additional time required for passing through the speed bump, translate the target line segment in the direction of time increase by the distance required for the additional time, obtain a second target line segment, and use the two endpoints of the second target line segment as new target search points; According to the new target search point, the longitudinal speed search space and the lateral speed search space are re-determined to obtain a new target speed curve.

10. A parking speed planning device based on sampling, It is characterized in that The device comprises: A longitudinal determination module is used to determine the longitudinal velocity search space and obtain the search points at each moment; A lateral determination module is used to determine a lateral velocity search space and obtain multiple search end points; a calculation module, configured to respectively use the plurality of search end points as parking completion points, obtain target search points from the search points according to a preset model, and connect the target search points with straight lines to obtain a plurality of speed curves; The selection module is used to obtain a parking mode, determine a speed curve selection model according to the parking mode, and obtain a target speed curve from the speed curve through the speed curve selection model.

Images