A vehicle longitudinal acceleration planning method, device, storage medium and equipment

Abstract

The application provides a vehicle longitudinal acceleration planning method and device, a storage medium and equipment. In the method, a longitudinal acceleration MAP is formulated based on a predicted time corresponding to a target time interval of two vehicles. In the process of following a vehicle, a longitudinal acceleration basic value is obtained by querying the longitudinal acceleration MAP according to the current vehicle speed, the distance between the host vehicle and the front vehicle and the relative speed. Meanwhile, a longitudinal acceleration compensation value is obtained based on the acceleration of the front vehicle. Finally, the longitudinal acceleration basic value and the longitudinal acceleration compensation value are added to obtain the target longitudinal acceleration of this planning. In this way, since the influence of the vehicle speed is considered, the comfort can be effectively improved. Meanwhile, the acceleration of the front vehicle is introduced to compensate for the longitudinal acceleration of the host vehicle, so that the response of the host vehicle to the speed change of the front vehicle in the process of following the vehicle can be improved, thereby effectively improving the safety, and the vehicle control giving consideration to the safety and the comfort is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a vehicle longitudinal acceleration planning method and device, a storage medium and equipment. BACKGROUND

[0002] In recent years, automatic driving technology has attracted widespread attention due to its leading edge. Acceleration planning in automatic driving is one of the core links to realize advanced driving functions. The basic principle is to plan the target acceleration in real time based on real-time road information and vehicle surrounding target information, so as to ensure that the vehicle can complete automatic driving functions such as following driving and cruising driving on the actual road. At present, the longitudinal acceleration of the automatic driving vehicle is greatly affected by the preceding vehicle. For example, when the preceding vehicle suddenly brakes at a long distance, the host vehicle may also brake heavily if the speed of the preceding vehicle is similar to that of the host vehicle, which results in poor driving comfort. When the preceding vehicle is stationary or cruising, if the host vehicle needs to decelerate, it may have insufficient deceleration in the early stage, which results in poor braking safety. SUMMARY

[0003] The purpose of the present application is to provide a vehicle longitudinal acceleration planning method, device, storage medium and equipment, aiming to improve driving safety and comfort.

[0004] In a first aspect, the present application provides a vehicle longitudinal acceleration planning method, comprising: querying a longitudinal acceleration map according to the current host vehicle speed, the distance between the host vehicle and the preceding vehicle, and the relative speed, to obtain a longitudinal acceleration basic value; the longitudinal acceleration map is formulated based on the predicted time corresponding to the time distance of the two vehicles reaching the target time distance; the predicted time is determined according to the distance error and the relative speed of the two vehicles; the distance error is the difference between the distance of the two vehicles and the target following distance; obtaining a longitudinal acceleration compensation value based on the acceleration of the preceding vehicle; and determining the sum of the longitudinal acceleration basic value and the longitudinal acceleration compensation value as the target longitudinal acceleration of this planning.

[0005] In the above implementation process, the longitudinal acceleration map is formulated based on the predicted time corresponding to the time distance of the two vehicles reaching the target time distance. In the following process, the longitudinal acceleration map is queried according to the current host vehicle speed, the distance between the host vehicle and the preceding vehicle, and the relative speed, to obtain a longitudinal acceleration basic value. At the same time, a longitudinal acceleration compensation value is obtained based on the acceleration of the preceding vehicle. Finally, the longitudinal acceleration basic value and the longitudinal acceleration compensation value are added to obtain the target longitudinal acceleration of this planning. In this way, since the influence of the host vehicle speed is considered, the comfort can be effectively improved. At the same time, the acceleration of the preceding vehicle is introduced to compensate for the longitudinal acceleration of the host vehicle, which can improve the response of the host vehicle when the speed of the preceding vehicle changes in the following process, thereby effectively improving the safety, and further realizing the vehicle control considering safety and comfort.

[0006] Furthermore, in some examples, the longitudinal acceleration MAP is formulated based on the following method: discretizing the vehicle speed at predetermined intervals to obtain a plurality of discrete vehicle speed points; for each discrete vehicle speed point, determining a predicted time based on the discretized distance between the two vehicles and the relative speed between the two vehicles, and then obtaining a single longitudinal acceleration MAP corresponding to the discrete vehicle speed point based on the predicted time and the acceleration calculation formula; and obtaining the longitudinal acceleration MAP based on the single longitudinal acceleration MAPs corresponding to all discrete vehicle speed points.

[0007] In the above implementation process, a specific method for formulating the longitudinal acceleration MAP is provided. By adopting a discretization method to convert the three-dimensional MAP into multiple two-dimensional MAPs, the complexity of the longitudinal acceleration MAP production can be effectively reduced while improving the adjustability.

[0008] Furthermore, in some examples, the acceleration calculation formula is as follows:

[0009] a=(sT gap *v ego +Δv*t) / (T gap *t+0.5t 2 )

[0010] Where a is the longitudinal acceleration; s is the distance between the two vehicles; T gap is the target time interval; v ego is the speed of the vehicle; Δv is the relative speed of the two vehicles; the relative speed of the two vehicles is the difference between the speed of the front vehicle and the speed of the vehicle; t is the predicted time.

[0011] In the above implementation process, a specific formula for calculating the basic value of longitudinal acceleration is provided. In this formula, the longitudinal acceleration is related to the square of the prediction time, which can achieve the effect of deceleration being large at first and then small, and can provide the driver with a greater sense of security in the following vehicle braking scenario.

[0012] Furthermore, in some examples, the relative speed of the two vehicles is the difference between the speed of the preceding vehicle and the speed of the own vehicle; the predicted time is determined based on the following method: if the relative speed of the two vehicles is less than zero, the predicted time is determined based on the remaining collision time; if the relative speed of the two vehicles is greater than zero, and the distance error is less than zero, when the distance between the two vehicles is less than the minimum safety distance, the predicted time is determined to be a first time value, and when the distance between the two vehicles is greater than or equal to the minimum safety distance, the predicted time is determined to be a second time value; the second time value is greater than the first time value; if the relative speed of the two vehicles is greater than zero, and the distance error is greater than zero, the predicted time is determined to be a third time value; the third time value is greater than the first time value.

[0013] In the implementation process, the longitudinal acceleration map is divided into different zones according to the relative speed and the sign of the distance error, and the prediction time is matched according to the characteristics of each zone, so that the matching efficiency is improved.

[0014] Further, in some examples, the determining the prediction time according to the remaining collision time comprises: determining the remaining collision time according to the distance between the two vehicles and the relative speed between the two vehicles; determining a correction coefficient as the ratio between the distance between the two vehicles and the target following distance; and determining the prediction time as the product of the remaining collision time and the correction coefficient.

[0015] In the implementation process, the ratio between the distance between the two vehicles and the target following distance is used as the correction coefficient, so that the value of the prediction time is reduced, and thus the distance between the two vehicles is prevented from being too close by considering the correction of the distance between the two vehicles, thereby effectively reducing the risk of collision and improving safety.

[0016] Further, in some examples, the obtaining the longitudinal acceleration compensation value based on the front vehicle acceleration comprises: obtaining a longitudinal acceleration compensation coefficient based on the current time interval between the two vehicles; and determining the longitudinal acceleration compensation value as the product of the front vehicle acceleration and the longitudinal acceleration compensation coefficient.

[0017] In the implementation process, the time interval between the two vehicles is introduced to correct the longitudinal acceleration of the ego vehicle, so that the influence of the acceleration of the distant target on the ego vehicle is reduced, and the driving experience is improved.

[0018] Further, in some examples, the obtaining the longitudinal acceleration compensation coefficient based on the current time interval between the two vehicles comprises: if the current time interval between the two vehicles is greater than a preset time interval, determining the longitudinal acceleration compensation coefficient as zero; and if the current time interval between the two vehicles is less than or equal to the preset time interval, determining the longitudinal acceleration compensation coefficient based on a target function; the target function indicates that the longitudinal acceleration compensation coefficient and the current time interval between the two vehicles are negatively correlated, and the maximum value of the longitudinal acceleration compensation coefficient is 0.5.

[0019] In the implementation process, when the time interval between the two vehicles is greater than a certain value, the longitudinal acceleration compensation coefficient is determined as zero, that is, the influence of the front vehicle acceleration is not considered, and when the time interval between the two vehicles is less than or equal to the certain value, the longitudinal acceleration compensation value is gradually increased, and the maximum value is limited, so that the response efficiency of the ego vehicle during following is effectively improved, and the safety and comfort are improved.

[0020] In a second aspect, the application provides a vehicle longitudinal acceleration planning device, comprising: a query module configured to query a longitudinal acceleration map according to a current vehicle speed, a distance between the vehicle and a front vehicle, and a relative speed between the vehicle and the front vehicle, to obtain a longitudinal acceleration basic value; the longitudinal acceleration map is formulated based on a predicted time when a two-vehicle time interval reaches a target time interval; the predicted time is determined according to a distance error and a relative speed between the two vehicles; the distance error is a difference between the distance between the two vehicles and a target following distance; an acquisition module configured to acquire a longitudinal acceleration compensation value based on a front vehicle acceleration; and a determination module configured to determine a sum of the longitudinal acceleration basic value and the longitudinal acceleration compensation value as a target longitudinal acceleration of this planning.

[0021] In a third aspect, the application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the steps of the method according to any one of the first aspect when running the computer program.

[0022] In a fourth aspect, the application provides a computer readable storage medium, and the computer readable storage medium stores instructions, and the instructions make the computer execute the method according to any one of the first aspect when running on the computer.

[0023] In a fifth aspect, the application provides a computer program product, and the computer program product makes the computer execute the method according to any one of the first aspect when running on the computer.

[0024] Other features and advantages of the application will be described in the following description, or can be learned or determined from the description, or can be known or determined by practicing the above-mentioned technologies disclosed in the application.

[0025] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments of the application. It should be understood that the following drawings only show some embodiments of the application, and therefore should not be regarded as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0027] Figure 1 A flow chart of a vehicle longitudinal acceleration planning method provided by the embodiments of the application;

[0028] Figure 2A schematic diagram of the workflow of a longitudinal acceleration planning scheme for an autonomous vehicle following a vehicle provided in an embodiment of the present application;

[0029] Figure 3 A block diagram of a vehicle longitudinal acceleration planning device provided in an embodiment of the present application;

[0030] Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0032] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0033] As described in the background technology, the longitudinal acceleration planning method of autonomous driving vehicles in related technologies has the problem of poor driving safety and comfort. Based on this, the embodiments of the present application provide a new vehicle longitudinal acceleration planning solution to solve the above problems.

[0034] Next, the embodiments of the present application are introduced:

[0035] like Figure 1 As shown, Figure 1 This is a flowchart of a vehicle longitudinal acceleration planning method provided in an embodiment of the present application. The vehicle may be equipped with a driver assistance system, such as an ACC (Adaptive Cruise Control) system or an IACC (Intelligent Adaptive Cruise Control) system. The method can be applied to a vehicle controller.

[0036] The method comprises:

[0037] Step 101: Based on the current vehicle speed, the distance between the vehicle and the preceding vehicle, and the relative speed, query the longitudinal acceleration map to obtain a longitudinal acceleration baseline value. The longitudinal acceleration map is formulated based on a predicted time; the predicted time is determined based on a distance error and the relative speed of the two vehicles; the distance error is the difference between the distance between the two vehicles minus the target following distance.

[0038] The driving assistance system of a vehicle, such as an ACC system, can perceive the driving environment in front of the vehicle using on-board sensors, automatically adjust the vehicle speed to maintain a safe vehicle-to-vehicle distance, and thus reduce the mental burden on the driver. In the embodiment, the vehicle can obtain the vehicle speed of the vehicle in real time using a speed sensor of the vehicle, obtain the speed and position of the preceding vehicle in real time using a radar or other sensors of the vehicle, and then calculate the distance between the vehicle and the preceding vehicle and the relative speed between the vehicle and the preceding vehicle. Subsequently, the vehicle uses the current vehicle speed, the distance between the vehicle and the preceding vehicle, and the relative speed as query conditions to query a longitudinal acceleration map and obtain a longitudinal acceleration base value. Since the influence of the vehicle speed on the calculation of the longitudinal acceleration is considered, the driving assistance support implemented based on the planned longitudinal acceleration can effectively improve comfort.

[0039] The longitudinal acceleration map mentioned in this step can be considered as a three-dimensional MAP or a three-dimensional MAP table. Taking the three-dimensional MAP table as an example, it can be composed of a plurality of key-value pairs. The key in each key-value pair is the vehicle speed, the distance between the vehicle and the preceding vehicle, and the relative speed, and the value is the longitudinal acceleration. When querying, the obtained value can be determined as the longitudinal acceleration base value by linear interpolation. In the embodiment, the longitudinal acceleration map is formulated based on the predicted time when the two-vehicle time distance reaches the target time distance. The two-vehicle time distance is a unit of measurement of the actual physical distance between the vehicle and the preceding vehicle, which is the ratio of the actual physical distance between the vehicle and the preceding vehicle to the vehicle speed, expressed in time units. Correspondingly, the target time distance can be used to represent the expected distance between the vehicle and the preceding vehicle, which can be set according to the requirements of the specific scene. Due to the existence of the longitudinal acceleration, the two-vehicle time distance can change. Assuming that the two-vehicle time distance reaches the target time distance after t time, t is the predicted time mentioned in this step. Therefore, when formulating the longitudinal acceleration map, the longitudinal acceleration corresponding to each vehicle speed, two-vehicle distance, and two-vehicle relative speed can be calculated based on the predicted time, thereby forming the longitudinal acceleration map.

[0040] In some embodiments, the longitudinal acceleration map mentioned in this step can be formulated based on the following method: discretizing the vehicle speed according to a predetermined interval to obtain a plurality of vehicle speed discrete points; for each vehicle speed discrete point, determining the predicted time according to the discretized two-vehicle distance and two-vehicle relative speed, and then obtaining the single longitudinal acceleration map corresponding to the vehicle speed discrete point according to the predicted time and the acceleration calculation formula; and obtaining the longitudinal acceleration map based on the single longitudinal acceleration maps corresponding to all vehicle speed discrete points.

[0041] That is, in formulating the longitudinal acceleration MAP, the host vehicle speed can be discretized, assuming that the host vehicle speed usually ranges from 0 to 40 m / s, and the preset interval is 5 m / s, then 0 m / s, 5 m / s, 10 m / s, 15 m / s, 20 m / s, 25 m / s, 30 m / s, 35 m / s, and 40 m / s can be obtained as the host vehicle speed discrete points, each host vehicle speed discrete point corresponds to a single longitudinal acceleration MAP, and the single longitudinal acceleration MAP is a two-dimensional MAP, taking the distance between the two vehicles as the horizontal coordinate, taking the relative speed between the two vehicles as the vertical coordinate, and the output value being the longitudinal acceleration basic value. In implementation, for any host vehicle speed discrete point, first calculate the distance error according to a discretized distance between the two vehicles, then determine the prediction time according to the distance error and a discretized relative speed between the two vehicles, then input the acceleration calculation formula to obtain a longitudinal acceleration basic value, traverse all discretized distances between the two vehicles and relative speeds between the two vehicles to obtain the single longitudinal acceleration MAP corresponding to the host vehicle speed discrete point, and traverse all host vehicle speed discrete points to obtain the single longitudinal acceleration MAP corresponding to all host vehicle speed discrete points, thereby completing the formulation of the longitudinal acceleration MAP. In this way, by using the discretization method, the three-dimensional MAP is converted into multiple two-dimensional MAPs, which can effectively reduce the complexity of the longitudinal acceleration MAP production, and if it is found during real vehicle testing that the longitudinal acceleration planning is not suitable, targeted local adjustment can be made at any time.

[0042] The aforementioned acceleration calculation formula is derived based on the prediction time, assuming that the distance between the host vehicle and the preceding vehicle, i.e., the distance between the two vehicles, is s, the host vehicle speed is v ego , and the current time distance between the two vehicles T hw = s / v ego , assuming that the difference between the preceding vehicle speed and the host vehicle speed, i.e., the relative speed between the two vehicles, is Δv, and the longitudinal acceleration of the host vehicle is a, then the distance between the two vehicles after the prediction time t is s+Δv*t-0.5at 2 , the host vehicle speed after t time is v ego +at, and the time distance between the two vehicles after t time reaches the target time distance T gap , that is, T gap =(s+Δv*t-0.5at 2 ) / (v ego +at), based on which, the acceleration calculation formula can be as follows:

[0043] a=(s-T gap *v ego +Δv*t) / (T gap *t+0.5t 2 )

[0044] It can be seen from the above formula that the longitudinal acceleration a is related to the square of the prediction time t, and the effect of the deceleration being large first and small later can be achieved, which can provide the driver with more sufficient safety in the car-following braking scenario.

[0045] In some embodiments, the prediction time mentioned in this step can be determined in the following manner: if the relative speed of the two vehicles is less than zero, the prediction time is determined according to the remaining collision time; if the relative speed of the two vehicles is greater than zero and the distance error is less than zero, when the distance between the two vehicles is less than the minimum safety distance, the prediction time is determined as a first time value, and when the distance between the two vehicles is greater than or equal to the minimum safety distance, the prediction time is determined as a second time value; the second time value is greater than the first time value; if the relative speed of the two vehicles is greater than zero and the distance error is greater than zero, the prediction time is determined as a third time value; the third time value is greater than the first time value.

[0046] That is, when the relative speed of the two vehicles is less than zero, i.e., the speed of the host vehicle is higher than the speed of the preceding vehicle, it indicates that the two vehicles have the possibility of collision, and at this time the prediction time is determined by referring to the remaining collision time, which is usually used to define the size of the collision risk, and the greater the remaining collision time, the smaller the collision risk; when the relative speed of the two vehicles is greater than zero, i.e., the speed of the host vehicle is lower than the speed of the preceding vehicle, it indicates that the two vehicles will not collide, and at this time if the distance error is less than zero, i.e., the distance between the two vehicles is less than the target following distance, the prediction time needs to be matched according to the comparison between the distance between the two vehicles and the minimum safety distance, so as to achieve a certain distance between the two vehicles after the prediction time, otherwise, if the distance error is greater than zero, i.e., the distance between the two vehicles is greater than the target following distance, only the comfort of acceleration needs to be considered, and therefore the prediction time can be set as the third time value. The target following distance is the product of the target time distance and the speed of the host vehicle. Alternatively, to avoid collision risk, the first time value can be 2s or 3s; the second time value can be selected in the range of 4s to 10s according to the distance between the two vehicles; to ensure comfort, the third time value can be greater than or equal to 6s. This setting is equivalent to partitioning the longitudinal acceleration MAP, and matching the prediction time according to the characteristics of each zone, so as to improve the matching efficiency and provide strong support for planning a longitudinal acceleration that can balance safety and comfort.

[0047] For the case that the speed of the host vehicle is higher than the speed of the front vehicle, in some scenarios, the remaining collision time can be directly determined as the prediction time, i.e., t = -s / Δv, but when the speeds of the two vehicles are relatively close and the distance between the two vehicles is also relatively close, the calculated remaining collision time is relatively large, and the two vehicles have a potential collision risk. Therefore, further, the aforementioned determination of the prediction time according to the remaining collision time can include: determining the remaining collision time according to the distance between the two vehicles and the relative speed of the two vehicles; determining a correction coefficient as the ratio between the distance between the two vehicles and the target following distance; and determining the product of the remaining collision time and the correction coefficient as the prediction time. That is, the ratio between the distance between the two vehicles and the target following distance is used as the correction coefficient to reduce the value of the prediction time, i.e., t = -s / Δv*[s / (T gap *v ego )], and in this way, by considering the correction of the distance between the two vehicles, it is ensured that the distance between the two vehicles does not continue to be in a relatively close state. Thus, the collision risk is effectively reduced, and the safety is improved.

[0048] Step 102, obtaining a longitudinal acceleration compensation value based on the acceleration of the front vehicle;

[0049] This step refers to the fact that when the front vehicle is decelerating or accelerating, the change in actual speed and the change in the distance between the two vehicles have a certain hysteresis. Therefore, the acceleration of the front vehicle is considered to compensate for the longitudinal acceleration of the host vehicle, so as to improve the response of the host vehicle when the front vehicle is decelerating or accelerating. If the front vehicle is braking urgently, the braking safety can be effectively improved.

[0050] In some embodiments, this step can include: obtaining a longitudinal acceleration compensation coefficient based on the current time interval between the two vehicles; and determining the product of the acceleration of the front vehicle and the longitudinal acceleration compensation coefficient as the longitudinal acceleration compensation value. That is, the longitudinal acceleration compensation value a cps may be the product of the acceleration a f of the front vehicle and the longitudinal acceleration compensation coefficient k cps , i.e., a cps = a f *k cps , where the longitudinal acceleration compensation coefficient k cps is obtained based on the current time interval T hw between the two vehicles. In this way, the time interval between the two vehicles is introduced to correct the longitudinal acceleration of the host vehicle, reduce the influence of the acceleration of the distant target on the host vehicle, and improve the driving experience.

[0051] Further, in some embodiments, the aforementioned obtaining the longitudinal acceleration compensation coefficient based on the current two-vehicle time interval can comprise: if the current two-vehicle time interval is greater than a preset time interval, determining the longitudinal acceleration compensation coefficient as zero; if the current two-vehicle time interval is less than or equal to the preset time interval, determining the longitudinal acceleration compensation coefficient based on a target function; the target function indicates that the longitudinal acceleration compensation coefficient and the current two-vehicle time interval are negatively correlated, and the maximum value of the longitudinal acceleration compensation coefficient is 0.5. That is, when the two-vehicle time interval is greater than a certain value, the longitudinal acceleration compensation coefficient k cps is determined as zero, that is, the influence of the front vehicle acceleration is not considered, and from the certain value, the longitudinal acceleration compensation value is gradually increased as the two-vehicle time interval continuously decreases, and the maximum value of the longitudinal acceleration compensation value is limited to 0.5. In this way, the response efficiency of the ego vehicle in the following process is effectively improved, the safety is improved, and the comfort is effectively ensured.

[0052] In addition, when following at a stable following distance, in order to avoid the influence of the front vehicle small braking intensity point brake, the speed of the ego vehicle can be introduced to perform quadratic correction on the longitudinal acceleration compensation coefficient obtained based on the current two-vehicle time interval. When the speed of the ego vehicle is relatively high, the two-vehicle stable following distance is relatively far, and there is a sufficient braking distance, the longitudinal acceleration compensation coefficient obtained based on the current two-vehicle time interval can be appropriately reduced to obtain the final longitudinal acceleration compensation coefficient.

[0053] Step 103, determining the sum of the longitudinal acceleration base value and the longitudinal acceleration compensation value as the target longitudinal acceleration of this planning.

[0054] This step refers to: after obtaining the longitudinal acceleration base value and the longitudinal acceleration compensation value, the two values can be added, that is, the target longitudinal acceleration of the planning can be obtained. The driving assistance system can control the driving speed of the vehicle based on the target longitudinal acceleration, so as to adjust the distance between the ego vehicle and the front vehicle in real time, and ensure driving within a safe range.

[0055] In the embodiments of the present application, the longitudinal acceleration MAP is formulated based on the predicted time corresponding to the target time interval of the two-vehicle time interval. In the following process, the longitudinal acceleration MAP is queried according to the current speed of the ego vehicle, the distance between the ego vehicle and the front vehicle, and the relative speed, to obtain a longitudinal acceleration base value. Meanwhile, the longitudinal acceleration compensation value is obtained based on the front vehicle acceleration. Finally, the longitudinal acceleration base value and the longitudinal acceleration compensation value are added, to obtain the target longitudinal acceleration of this planning. In this way, since the influence of the speed of the ego vehicle is considered, the comfort can be effectively improved. Meanwhile, the front vehicle acceleration is introduced to compensate for the longitudinal acceleration of the ego vehicle, the response of the ego vehicle when the front vehicle speed changes in the following process can be improved, so as to effectively improve the safety, and thus the vehicle control considering both safety and comfort is realized.

[0056] In order to make a more detailed description of the scheme of the present application, a specific embodiment is introduced as follows:

[0057] The embodiment provides a longitudinal acceleration planning scheme for a self-driving vehicle following a target vehicle. The scheme takes a target time interval set by a user as a control target, predicts a target time interval of the self-driving vehicle after t time, assumes that the target vehicle travels at a constant speed, calculates a longitudinal acceleration basic value according to a motion relationship, calculates a longitudinal acceleration compensation coefficient according to a current time interval and a vehicle speed of the self-driving vehicle when the target vehicle has an acceleration, multiplies the target vehicle acceleration by the longitudinal acceleration compensation coefficient to obtain a longitudinal acceleration compensation value, and sums the longitudinal acceleration basic value and the longitudinal acceleration compensation value to obtain a planned longitudinal acceleration. In addition, the scheme is also applicable to following control in a cut-in scenario.

[0058] The working process of the scheme is shown in Figure 2 , and includes the following steps.

[0059] S201, setting a longitudinal acceleration basic value calculation formula;

[0060] Specifically, when the self-driving vehicle follows the target vehicle, a current time interval T hw is calculated according to a formula T hw =s / v ego , where s is a distance between the self-driving vehicle and the target vehicle, and v ego is a vehicle speed of the self-driving vehicle.

[0061] Supposing that a vehicle speed of the target vehicle is v f , a relative vehicle speed between the self-driving vehicle and the target vehicle is Δv, i.e., Δv=v f -v ego , and a distance between the two vehicles after t time is s+Δv*t-0.5at 2 .

[0062] A vehicle speed of the self-driving vehicle after t time is v ego +at, and the time interval between the two vehicles after t time reaches a target time interval T gap , i.e., T gap =(s+Δv*t-0.5at 2 ) / (v ego +at), so a calculation formula of the longitudinal acceleration basic value is obtained as follows:

[0063] a=(s-T gap *v ego +Δv*t) / (T gap *t+0.5t 2 )

[0064] S202, performing discrete processing on the longitudinal acceleration basic value;

[0065] Specifically, the ego vehicle speed is discretized at intervals of 5 m / s, and the ego vehicle speed usually ranges from 0 to 40 m / s; each ego vehicle speed corresponds to a two-dimensional MAP, and the output value of the two-dimensional MAP is a longitudinal acceleration basic value, which is referred to as a longitudinal acceleration MAP hereinafter; the two-dimensional MAP takes the distance between the two vehicles as the horizontal coordinate and the relative speed between the two vehicles as the vertical coordinate; the maximum distance between the two vehicles is determined by the maximum capability of the perception system, and the maximum distance between the two vehicles is 150 m optionally;

[0066] S203, form a prediction time matching strategy;

[0067] Specifically, according to the signs of the distance error Δs and the relative speed Δv, the longitudinal acceleration MAP is divided into four regions, which are:

[0068] 1 region: Δs > 0, Δv < 0;

[0069] 2 region: Δs < 0, Δv < 0;

[0070] 3 region: Δs < 0, Δv > 0;

[0071] 4 region: Δs > 0, Δv > 0;

[0072] Wherein, Δs = s - T gap *v ego ;

[0073] 1 region and 2 region are both that the ego vehicle speed is higher than the target vehicle speed, and the two vehicles have the possibility of collision, so the prediction time t is matched by referring to the remaining collision time, that is, t = -s / Δv*[s / (T gap *v ego )]; 3 region is that the target vehicle speed is higher than the ego vehicle speed, and the prediction time t needs to be matched according to the distance error, when the distance between the two vehicles is less than the minimum safety distance, in order to avoid the risk of collision, t = 2s or t = 3s is set, when the distance between the two vehicles is greater than or equal to the minimum safety distance, the prediction time t is selected in the range of 4s to 10s according to the distance between the two vehicles; 4 region is that the target vehicle speed is higher than the ego vehicle speed, and since the distance between the two vehicles is greater than the target following distance, there is no risk of collision, therefore, in order to ensure comfort, the prediction time t is set to be not less than 6s;

[0074] S204, form a longitudinal acceleration MAP;

[0075] Specifically, a discretized vehicle speed, a discretized distance between two vehicles, a discretized relative speed between two vehicles are selected to obtain a prediction time t, and then a longitudinal acceleration basic value is calculated by inputting the calculation formula of the longitudinal acceleration basic value set in S201, so as to obtain a longitudinal acceleration basic value; all discretized distances between two vehicles and relative speeds between two vehicles are traversed, so as to obtain a longitudinal acceleration MAP corresponding to a vehicle speed; all discretized vehicle speeds are traversed, so as to obtain longitudinal acceleration MAPs corresponding to all vehicle speeds;

[0076] S205, obtaining a longitudinal acceleration basic value;

[0077] Specifically, the longitudinal acceleration MAP established in S204 is used to obtain a current longitudinal acceleration basic value by linear interpolation based on the current vehicle speed, the distance between two vehicles and the relative speed between two vehicles;

[0078] S206, obtaining a longitudinal acceleration compensation value;

[0079] Specifically, different longitudinal acceleration compensation coefficients are set based on the current time interval, and the vehicle speed is further corrected to output a final longitudinal acceleration compensation coefficient, which is a calibration quantity. Optionally, the value of the longitudinal acceleration compensation coefficient is 0-0.5.

[0080] The longitudinal acceleration compensation value is obtained by multiplying the longitudinal acceleration compensation coefficient by the acceleration of the preceding vehicle.

[0081] S207, obtaining a longitudinal acceleration planning result;

[0082] Specifically, the longitudinal acceleration basic value obtained in S205 and the longitudinal acceleration compensation value obtained in S206 are added, so as to obtain the planned longitudinal acceleration.

[0083] The embodiment has at least the following advantages: first, the idea of prediction is adopted to derive a longitudinal acceleration basic value calculation formula, the acceleration is related to the square of the prediction time, and the relationship is similar to a parabola, so that the effect of large deceleration first and small deceleration later can be achieved, and the braking process gives people a sense of safety; second, if it is a following braking scene, the higher the speed of the ego vehicle, the more likely the driver is to panic, so a greater deceleration is needed, and if it is a following acceleration scene, the higher the speed of the ego vehicle, the smaller the acceleration that the person subjectively needs, so the speed of the ego vehicle is introduced in the longitudinal acceleration calculation process to improve driving comfort; third, a discretization method is adopted to convert the calculation formula into a three-dimensional MAP, and then into multiple two-dimensional MAPs, so that the corresponding longitudinal acceleration basic value under a certain ego vehicle speed, relative vehicle speed and distance between the two vehicles can be more intuitively obtained; fourth, the acceleration of the preceding vehicle is considered to compensate for the longitudinal acceleration of the ego vehicle, which can improve the response of the ego vehicle when the target vehicle decelerates / accelerates during following, and effectively improve driving safety.

[0084] Corresponding to the embodiments of the foregoing method, the application also provides embodiments of a vehicle longitudinal acceleration planning device and a terminal applying the same:

[0085] As shown in Figure 3 , Figure 3 is a block diagram of a vehicle longitudinal acceleration planning device provided by an embodiment of the application, and the device comprises:

[0086] The query module 31 is configured to query a longitudinal acceleration MAP according to the current speed of the ego vehicle, the distance between the ego vehicle and the preceding vehicle and the relative vehicle speed, and obtain a longitudinal acceleration basic value; the longitudinal acceleration MAP is formulated based on a prediction time corresponding to the time distance between the two vehicles reaching a target time distance; the prediction time is determined according to a distance error and the relative vehicle speed between the two vehicles; the distance error is a difference value obtained by subtracting a target following distance from the distance between the two vehicles;

[0087] The acquisition module 32 is configured to acquire a longitudinal acceleration compensation value based on the acceleration of the preceding vehicle;

[0088] The determination module 33 is configured to determine the sum of the longitudinal acceleration basic value and the longitudinal acceleration compensation value as a target longitudinal acceleration of this planning.

[0089] The functions and effects of the modules in the device are achieved in the implementation process of the corresponding steps in the above method, which will not be described here.

[0090] The application also provides an electronic device, please see Figure 4 , Figure 4A structural block diagram of an electronic device is provided in the embodiments of the present application. The electronic device can include a processor 410, a communication interface 420, a memory 430, and at least one communication bus 440. The communication bus 440 is used to realize direct connection communication among the components. The communication interface 420 of the electronic device in the embodiments of the present application is used to communicate signaling or data with other node devices. The processor 410 can be an integrated circuit chip with signal processing capability.

[0091] The processor 410 described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; or can be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a ready programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor 410 can also be any conventional processor.

[0092] The memory 430 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read only memory (PROM), an erasable programmable read only memory (EPROM), an electrically erasable programmable read only memory (EEPROM), etc. The memory 430 stores computer readable instructions, which, when executed by the processor 410, enable the electronic device to perform the above-mentioned Figure 1 The method embodiments involve various steps.

[0093] Optionally, the electronic device can further include a storage controller, an input / output unit.

[0094] The memory 430, the storage controller, the processor 410, the peripheral interface, and the input / output unit are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses 440. The processor 410 is used to execute executable modules stored in the memory 430, such as software function modules or computer programs included in the electronic device.

[0095] The input / output unit is configured to provide a user with a creation of a task and a creation of a selectable period of time or a preset execution time for the task to realize the interaction between the user and the server. The input / output unit can be, but is not limited to, a mouse, a keyboard, and the like.

[0096] It can be understood that Figure 4 The structure shown is only schematic, and the electronic device can further include more or fewer components than shown, or have a different configuration of components than shown. Figure 4 The components shown in the figures can be implemented in hardware, software, or a combination thereof. Figure 4 The components shown in the figures can be implemented in hardware, software, or a combination thereof. Figure 4 The components shown in the figures can be implemented in hardware, software, or a combination thereof.

[0097] The embodiments of the present application further provide a storage medium, wherein instructions are stored on the storage medium, and when the instructions are run on a computer, the computer program is executed by a processor to implement the method of the method embodiments. To avoid repetition, details are not described here.

[0098] The present application also provides a computer program product, which, when run on a computer, causes the computer to execute the method of the method embodiments.

[0099] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can also be implemented by other manners. The apparatus embodiments described above are only schematic, for example, the flowcharts and block diagrams in the drawings show the possible implementation architectures, functions and operations of the apparatus, method and computer program product according to the embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that, in some alternative implementation manners, the functions noted in the blocks can also occur in different orders from those noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can also be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system for executing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0100] In addition, each functional module in the embodiments of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0101] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts of the prior art that make contributions or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0102] The above merely provides an example of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0103] The above merely provides an example of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that similar reference numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0104] It should be noted that, in this document, the terms such as first and second are used merely to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the processes, methods, articles or devices including a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

Claims

1. A vehicle longitudinal acceleration planning method, characterized by, The method comprises the following steps: According to the current vehicle speed, the distance between the host vehicle and the front vehicle, and the relative speed, a longitudinal acceleration map is queried to obtain a longitudinal acceleration basic value; the longitudinal acceleration map is formulated based on the predicted time corresponding to the time interval between the two vehicles reaching the target time interval; the predicted time is determined according to the distance error and the relative speed between the two vehicles; the distance error is the difference between the distance between the two vehicles and the target following distance; Based on the acceleration of the front vehicle, a longitudinal acceleration compensation value is obtained; The sum of the longitudinal acceleration basic value and the longitudinal acceleration compensation value is determined as the target longitudinal acceleration of this planning; The method for obtaining the longitudinal acceleration compensation value based on the acceleration of the front vehicle comprises the following steps: A longitudinal acceleration compensation coefficient is obtained based on the current time interval between the two vehicles; The product of the acceleration of the front vehicle and the longitudinal acceleration compensation coefficient is determined as the longitudinal acceleration compensation value; The method for obtaining the longitudinal acceleration compensation coefficient based on the current time interval between the two vehicles comprises the following steps: If the current time interval between the two vehicles is greater than the preset time interval, the longitudinal acceleration compensation coefficient is determined as zero; If the current time interval between the two vehicles is less than or equal to the preset time interval, the longitudinal acceleration compensation coefficient is determined based on a target function; the target function indicates that the longitudinal acceleration compensation coefficient and the current time interval between the two vehicles are negatively correlated, and the maximum value of the longitudinal acceleration compensation coefficient is 0.

5.

2. The method of claim 1, wherein, The longitudinal acceleration map is formulated in the following way: The vehicle speed is discretized at a predetermined interval to obtain a plurality of vehicle speed discrete points; For each vehicle speed discrete point, the predicted time is determined according to the discretized distance between the two vehicles and the relative speed between the two vehicles, and then the single longitudinal acceleration map corresponding to the vehicle speed discrete point is obtained according to the predicted time and an acceleration calculation formula; The longitudinal acceleration map is obtained based on the single longitudinal acceleration maps corresponding to all vehicle speed discrete points.

3. The method of claim 2, wherein, The acceleration calculation formula is as follows: In the formula, is the longitudinal acceleration; is the distance between the two vehicles; is the target time distance; is the vehicle speed of the subject vehicle; is the relative speed between the two vehicles; the relative speed between the two vehicles is the difference between the vehicle speed of the preceding vehicle and the vehicle speed of the subject vehicle; is the prediction time.

4. The method of claim 1, wherein, The relative speed between the two vehicles is the difference between the speed of the front vehicle and the speed of the host vehicle; the predicted time is determined in the following way: If the relative speed between the two vehicles is less than zero, the predicted time is determined according to the remaining collision time; If the relative speed between the two vehicles is greater than zero and the distance error is less than zero, when the distance between the two vehicles is less than the minimum safety distance, the predicted time is determined as a first time value; when the distance between the two vehicles is greater than or equal to the minimum safety distance, the predicted time is determined as a second time value; the second time value is greater than the first time value; If the relative speed between the two vehicles is greater than zero and the distance error is greater than zero, the predicted time is determined as a third time value; the third time value is greater than the first time value.

5. The method of claim 4, wherein, The method for determining the predicted time according to the remaining collision time comprises the following steps: The remaining collision time is determined according to the distance between the two vehicles and the relative speed between the two vehicles; A correction coefficient is determined as the ratio between the distance between the two vehicles and the target following distance; The product of the remaining collision time and the correction coefficient is determined as the predicted time.

6. A vehicle longitudinal acceleration planning device characterized by comprising: The method comprises the following steps: The query module is configured to query a longitudinal acceleration map according to the current vehicle speed, the distance between the host vehicle and the front vehicle, and the relative speed, to obtain a longitudinal acceleration basic value; the longitudinal acceleration map is formulated based on a predicted time corresponding to a target time interval of the two vehicles; the predicted time is determined according to a distance error and the relative speed of the two vehicles; the distance error is a difference value obtained by subtracting a target following distance from the distance between the two vehicles; The acquisition module is configured to acquire a longitudinal acceleration compensation value based on the front vehicle acceleration; The determination module is configured to determine a sum of the longitudinal acceleration basic value and the longitudinal acceleration compensation value as a target longitudinal acceleration of the current planning; The acquisition module is specifically configured to: if the current time interval of the two vehicles is greater than a preset time interval, determine that a longitudinal acceleration compensation coefficient is zero; if the current time interval of the two vehicles is less than or equal to the preset time interval, determine the longitudinal acceleration compensation coefficient based on a target function. The target function indicates that the longitudinal acceleration compensation coefficient and the current time interval of the two vehicles are in a negative correlation relationship, and the maximum value of the longitudinal acceleration compensation coefficient is 0.5; and a product of the front vehicle acceleration and the longitudinal acceleration compensation coefficient is determined as the longitudinal acceleration compensation value.

7. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 5.

8. An electronic device, comprising: A computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 5.

Images