Vehicle distance and gradient determination method and device, storage medium and electronic equipment

Abstract

The invention discloses a vehicle distance and gradient determination method and device, a storage medium and electronic equipment. The method comprises the following steps: establishing a Kalman filtering equation set between a plurality of state parameters and a plurality of observation parameters according to a first motion parameter set, a second motion parameter set and a third motion parameter set, performing Kalman filtering on the first state parameter according to the Kalman filtering equation set to obtain a first target value, performing Kalman filtering on the second state parameter to obtain a second target value; and according to the first target value of the first state parameter, the second target value of the second state parameter, and the relative gradient and the target vehicle distance between the target vehicle object located on the current ramp and the self-vehicle object located on the target ramp.

Description

Technical Field

[0001] The present application relates to the field of vehicle driving, and in particular, to a method, device, storage medium and electronic device for determining vehicle distance and slope. Background Art

[0002] With the popularization and development of intelligent assisted driving (ADAS) technology, the comfort experience of assisted driving functions under different complex working conditions is becoming higher and higher.

[0003] Assisted driving is different from manual driving. It cannot judge the current driving environment through the driver's visual observation and experience. Instead, it relies on sensor data to analyze the driving environment, such as obtaining the distance to the vehicle in front through sensors.

[0004] However, in the existing assisted driving technology, for the ACC (adaptive cruise control) function, when the ego vehicle is following a vehicle on a slope, due to the limitations of the sensors, the distance and speed of the target vehicle are not accurately calculated, which can easily lead to two-stage braking of the ego vehicle on the slope, and the following-stop distance being too large or too small, which affects the driver's driving comfort. Even through multi-sensor fusion measurement, due to the inaccurate distance and speed information of the target provided by the front radar and the camera, the target longitudinal distance and longitudinal speed information given after multi-sensor fusion are all based on the target information perceived by the front radar, and the longitudinal distance and longitudinal speed of the target on the slope given by the radar are both smaller than the actual values, resulting in two-stage braking in the following-stop process of the ego vehicle, and the braking distance being too large or too small.

[0005] That is to say, in the prior art, since the relative slope cannot be accurately predicted, the driving system cannot reasonably plan the longitudinal acceleration according to the accurate vehicle distance prediction value, resulting in low economy of the whole vehicle. Summary of the invention

[0006] The embodiments of the present application provide a method, device, storage medium and electronic device for determining vehicle distance and slope, so as to at least solve the technical problem in the prior art that the driving system cannot perform reasonable longitudinal acceleration planning according to the accurate vehicle distance prediction value due to the inability to accurately predict the relative slope.

[0007] According to one aspect of an embodiment of the present application, a method for determining a vehicle distance and a slope is provided, comprising: in the case of detecting a target vehicle object traveling on a target ramp, obtaining a first motion parameter set matching the target vehicle object according to an image perception unit, obtaining a second motion parameter set matching the target vehicle object according to a radar perception unit, and obtaining a third motion parameter set matching the self-vehicle object; establishing a Kalman filter equation group between a plurality of state parameters and a plurality of observation parameters according to the first motion parameter set, the second motion parameter set, and the third motion parameter set, wherein the plurality of state parameters include a first state parameter and a second state parameter, the first state parameter being a vertical component of a speed parameter of the target vehicle object, and the second state parameter being a horizontal component of a relative speed parameter between the target vehicle objects; according to the Kalman filter equation group, performing Kalman filtering on the first state parameter to obtain a first target value, and performing Kalman filtering on the second state parameter to obtain a second target value; determining the relative slope and the target vehicle distance between the target vehicle object on the current ramp and the self-vehicle object on the target ramp according to the first target value of the first state parameter and the second target value of the second state parameter.

[0008] According to another aspect of an embodiment of the present application, a device for determining vehicle distance and slope is also provided, including: an acquisition unit, when a target vehicle object traveling on a target slope is detected, acquires a first motion parameter set matching the target vehicle object according to an image perception unit, acquires a second motion parameter set matching the target vehicle object according to a radar perception unit, and acquires a third motion parameter set matching the self-vehicle object; an establishment unit, establishes a Kalman filter equation set between multiple state parameters and multiple observation parameters according to the first motion parameter set, the second motion parameter set and the third motion parameter set, wherein the multiple state parameters include a first state parameter and a second state parameter, wherein the first state parameter is a vertical component of a speed parameter of the target vehicle object, and the second state parameter is a horizontal component of a relative speed parameter between the target vehicle objects; a filtering unit, according to the Kalman filter equation group, performing Kalman filtering on the first state parameter to obtain a first target value, and performing Kalman filtering on the second state parameter to obtain a second target value; a determining unit, according to the first target value of the first state parameter and the second target value of the second state parameter, as well as a relative slope and a target vehicle distance between the target vehicle object on the current ramp and the self-vehicle object on the target ramp.

[0009] As an optional solution, the above-mentioned determination unit includes: a vehicle distance determination module, used to determine the relative slope between the target ramp and the current ramp according to the first target value of the first state parameter and the second target value of the second state parameter; obtain a third target value after performing Kalman filtering on the third state parameter according to the Kalman filter equation group, wherein the multiple state parameters include a third state parameter, and the third state parameter is the object height difference between the target vehicle object and the self-vehicle object; determine the target vehicle distance between the self-vehicle object and the target vehicle object according to the relative slope, the third state parameter, and the first vehicle distance parameter in the first motion parameter set.

[0010] As an optional solution, the above-mentioned vehicle distance determination module is also used to: determine the sum of the second target value and the first reference value of the speed parameter of the target vehicle object as the second reference value, wherein the second reference value is used to indicate the horizontal component of the speed parameter of the target vehicle object; and determine the inverse tangent function value of the ratio between the first target value and the second reference value as the relative slope between the target ramp and the current ramp.

[0011] As an optional solution, the above-mentioned vehicle distance determination module is also used to: use the sine value of the relative slope as a third reference value, and use the tangent value of the relative slope as a fourth reference value; determine the ratio between the third target value and the third reference value as a first target vehicle distance, wherein the first target vehicle distance is the distance between a reference point and the target vehicle object, and the reference point is a connection point between the current ramp and the target ramp; determine the ratio between the third target value and the fourth reference value as a reference vehicle distance, wherein the reference vehicle distance is a horizontal distance between the reference point and the target vehicle object; determine the difference between the first vehicle distance of the first vehicle distance parameter and the reference vehicle distance as a second target vehicle distance, wherein the second target vehicle distance is the distance between the reference point and the self-vehicle object; and determine the target vehicle distance based on the first target vehicle distance and the second target vehicle distance.

[0012] As an optional scheme, the above-mentioned establishment unit includes: a reference establishment module, which is used to establish a first Kalman filter state equation according to the first state parameter and the fourth state parameter, wherein the fourth state parameter is the vertical component of the acceleration parameter of the target vehicle object, and the first Kalman filter state equation is used to indicate that the current state value of the first state parameter is determined according to the historical state value of the first state parameter and the historical state value of the fourth state parameter; establish a second Kalman filter state equation according to the second state parameter and the first acceleration parameter, wherein the first motion parameter set includes the first acceleration parameter, and the second Kalman filter state equation is used to indicate that the current state value of the second state parameter is determined according to the historical state value of the second state parameter and the historical state value of the first acceleration parameter; according to the third state parameter, the first state parameter is determined according to the historical state value of the second state parameter and the historical state value of the first acceleration parameter. A third Kalman filter state equation is established according to the fifth state parameter, the second state parameter and the first acceleration parameter, wherein the fifth state parameter is the first distance parameter in the first motion parameter set, and the fourth Kalman filter state equation is used to indicate that the current state value of the fifth state parameter is determined according to the historical state value of the third state parameter, the historical state value of the first state parameter and the historical state value of the fourth state parameter; a fourth Kalman filter state equation is established according to the fifth state parameter, the second state parameter and the first acceleration parameter, wherein the fifth state parameter is the first distance parameter in the first motion parameter set, and the fourth Kalman filter state equation is used to indicate that the current state value of the fifth state parameter is determined according to the historical state value of the fifth state parameter, the historical state value of the second state parameter and the historical state value of the first acceleration parameter.

[0013] As an optional solution, the above-mentioned vehicle distance and slope determination device also includes: a measurement matrix establishment module, which is used to determine the state quantity matrix used to characterize the Kalman filter equation group based on the first state parameter, the second state parameter, the third state parameter, the fourth state parameter and the fifth state parameter; determine the fifth state parameter as the first observation parameter among the multiple observation parameters, determine the second state parameter as the second observation parameter among the multiple observation parameters, and determine the second distance parameter in the second motion parameter set as the third observation parameter among the multiple observation parameters; determine the observation quantity matrix used to characterize the Kalman filter equation group based on the first observation parameter, the second observation parameter and the third observation parameter.

[0014] As an optional scheme, the above-mentioned establishment unit also includes: a partial derivative reference module, which is used to determine the numerical relationship between the first observation parameter, the third observation parameter and the third state parameter; determine the partial derivative results of the state parameters associated with each observation parameter in the observation matrix according to the numerical relationship, and obtain the observation transformation Jacobian matrix.

[0015] As an optional solution, the above-mentioned vehicle distance and slope determination device further includes: an adjustment unit, which is used to dynamically determine a fourth target value of the speed parameter of the own vehicle object according to the target vehicle distance, the preset vehicle distance threshold and the first reference value of the speed parameter of the own vehicle object through the following formula:

[0016]

[0017] Wherein, V1 is the fourth target value, V2 is the first reference value of the speed parameter of the vehicle object, d1 is the preset vehicle distance threshold, d2 is the target vehicle distance, K i is a variable coefficient.

[0018] According to another aspect of the embodiment of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above method for determining the vehicle distance and the slope.

[0019] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for determining the vehicle distance and slope through the computer program.

[0020] In the above-mentioned embodiment of the present application, first, when a target vehicle object traveling on a target ramp is detected, a first motion parameter set matching the target vehicle object is obtained according to an image perception unit, a second motion parameter set matching the target vehicle object is obtained according to a radar perception unit, and a third motion parameter set matching the self-vehicle object is obtained; and then, according to the first motion parameter set, the second motion parameter set and the third motion parameter set, a Kalman filter equation group between multiple state parameters and multiple observation parameters is established, wherein the multiple state parameters include a first state parameter and a second state parameter, and the first state parameter is a velocity parameter of the target vehicle object. vertical component, and the second state parameter is the horizontal component of the relative speed parameter between the target vehicle object; and according to the Kalman filter equation group, the first state parameter is Kalman filtered to obtain a first target value, and the second state parameter is Kalman filtered to obtain a second target value; further, according to the first target value of the first state parameter and the second target value of the second state parameter, and the geometric position relationship between the target vehicle object located on the current ramp and the self-vehicle object located on the target ramp, the target vehicle distance between the self-vehicle object and the target vehicle object is determined, thereby solving the technical problem of low accuracy in vehicle distance judgment in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1 is a schematic diagram of an application environment of an optional method for determining vehicle distance and slope according to an embodiment of the present application;

[0023] Figure 2 is a flow chart of an optional method for determining vehicle distance and slope according to an embodiment of the present application;

[0024] Figure 3 is a schematic diagram of an optional method for determining vehicle distance and slope according to an embodiment of the present application;

[0025] Figure 4 is a schematic diagram of another optional method for determining vehicle distance and slope according to an embodiment of the present application;

[0026] Figure 5 is a flow chart of another optional method for determining vehicle distance and slope according to an embodiment of the present application;

[0027] Figure 6is a flow chart of another optional method for determining vehicle distance and slope according to an embodiment of the present application;

[0028] Figure 7 is a flow chart of another optional method for determining vehicle distance and slope according to an embodiment of the present application;

[0029] Figure 8 is a schematic diagram of a device for determining vehicle distance and slope according to an embodiment of the present application;

[0030] Fig. 9 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] According to one aspect of an embodiment of the present application, a method for determining vehicle distance and slope is provided. Optionally, as an optional implementation, the above method for determining vehicle distance and slope can be but is not limited to being applied to the following: Figure 1 In the environment shown, it may include but is not limited to a vehicle terminal 102 and a server 104, the vehicle terminal 102 may include but is not limited to a display, a processor and a memory, and the server 104 includes a database and a processing engine.

[0034] The specific process may include the following steps:

[0035] Step S102, the server 104 sends a vehicle distance and slope determination instruction to the vehicle terminal 102 via the network 110;

[0036] Steps S104-S110, when a target vehicle object traveling on a target ramp is detected, a first motion parameter set matching the target vehicle object is obtained according to an image sensing unit, a second motion parameter set matching the target vehicle object is obtained according to a radar sensing unit, and a third motion parameter set matching the self-vehicle object is obtained; a Kalman filter equation group between multiple state parameters and multiple observation parameters is established according to the first motion parameter set, the second motion parameter set, and the third motion parameter set, wherein the multiple state parameters include a first state parameter and a second state parameter, the first state parameter is a vertical component of a speed parameter of the target vehicle object, and the second state parameter is a horizontal component of a relative speed parameter between the target vehicle objects; according to the Kalman filter equation group, a first target value is obtained after Kalman filtering the first state parameter, and a second target value is obtained after Kalman filtering the second state parameter; a target vehicle distance between the self-vehicle object and the target vehicle object is determined according to the first target value of the first state parameter and the second target value of the second state parameter, and the geometric position relationship between the target vehicle object on the current ramp and the self-vehicle object on the target ramp.

[0037] remove Figure 1 In addition to the examples shown, the above steps can be completed independently by the vehicle terminal or the server, or by the vehicle terminal and the server working together, such as the vehicle terminal 102 directly obtaining the conversion instruction set, thereby reducing the processing pressure of the server 104. The present application does not limit the specific implementation of the vehicle terminal 102. The server 104 can be a single server or a server cluster composed of multiple servers, or a cloud server.

[0038] As an optional implementation, Figure 2 As shown, the method for determining the vehicle distance and the slope can be executed by an electronic device, such as Figure 1 The user device or server shown in the figure comprises:

[0039] S202, when a target vehicle object traveling on a target ramp is detected, a first motion parameter set matching the target vehicle object is obtained according to an image sensing unit, a second motion parameter set matching the target vehicle object is obtained according to a radar sensing unit, and a third motion parameter set matching the ego vehicle object is obtained;

[0040] S204, establishing a Kalman filter equation group between multiple state parameters and multiple observation parameters according to the first motion parameter set, the second motion parameter set and the third motion parameter set, wherein the multiple state parameters include a first state parameter and a second state parameter, the first state parameter is a vertical component of a velocity parameter of the target vehicle object, and the second state parameter is a horizontal component of a relative velocity parameter between the target vehicle objects;

[0041] S206, according to the Kalman filter equation group, performing Kalman filtering on the first state parameter to obtain a first target value, and performing Kalman filtering on the second state parameter to obtain a second target value;

[0042] S208: according to the first target value of the first state parameter and the second target value of the second state parameter, and the relative slope and the target vehicle distance between the target vehicle object on the current ramp and the self-vehicle object on the target ramp.

[0043] It can be understood that in the above step S202, the above image sensing unit can be a camera installed on the vehicle and capable of photographing the target vehicle, and the above radar sensing unit can be a vehicle-mounted radar installed on the vehicle and capable of detecting the target object, which is not specifically limited here.

[0044] It should be noted that, in the above step S202, the first motion parameter set includes the longitudinal distance of the target vehicle object obtained by the image perception unit, and the longitudinal acceleration of the target vehicle object, the above second motion parameter set includes the longitudinal distance of the target vehicle object obtained by the radar perception unit, and the longitudinal acceleration of the target vehicle object, and the above third motion set includes the vehicle speed and the vehicle acceleration.

[0045] It is worth noting that due to the device setting angle, position, and its own characteristics, the longitudinal distance and longitudinal acceleration of the target vehicle object obtained by the image sensing unit may not be the same as the longitudinal distance and longitudinal acceleration of the target vehicle object obtained by the radar sensing unit. Figure 3 As shown, Figure 3 The longitudinal distance R of the target vehicle object obtained by the image perception unit vision The longitudinal distance R of the target vehicle object obtained by the radar sensing unit radar Not the same line segment.

[0046] It can be understood that the distance between the object in the picture taken by the image sensing unit and itself is the distance from the image sensing unit to the photographed object in the horizontal direction, and the distance between itself and the detected object determined by the radar sensing unit is the minimum distance between the radar sensing unit and the detected object. Therefore, the longitudinal distance R of the target vehicle object obtained by the image sensing unit is visionThe longitudinal distance R of the target vehicle object obtained by the radar sensing unit radar Not the same.

[0047] It should be noted that no matter the longitudinal distance R of the target vehicle object obtained by the image perception unit vision , or the longitudinal distance R of the target vehicle object obtained by the radar sensing unit radar , which is essentially a straight line segment, actually represents the distance between the ego vehicle object and the target vehicle object on a certain plane. However, when the ego vehicle object and the target vehicle object are on two planes with different slopes, a straight line segment will not accurately represent the actual distance between the ego vehicle object and the target vehicle object. Figure 3 As shown, the actual distance between the target vehicle object 304 and the vehicle object 302 should be the sum of the two straight line segments c and d, rather than the longitudinal distance R of the target vehicle object obtained by the image perception unit. vision , nor the longitudinal distance R of the target vehicle object obtained by the radar perception unit radar .

[0048] In addition, since in some embodiments of the present application, the information such as the relative distance and relative speed between the target vehicle and the vehicle is calculated, the calculation process can also be simplified to the vehicle driving on a flat road. Figure 3 The whole vehicle object 302 is rotated by a certain angle so that the vehicle object 302 is on the horizontal plane. Figure 4 As shown, Figure 4 In the figure, the target vehicle object 404 is the rotated target vehicle object 304, and the ego vehicle object 402 is the rotated ego vehicle object 302. It can be understood that the relative geometric relationship between the target vehicle object 404 and the ego vehicle object 402 is the same as Figure 3 The relative geometric relationship between the target vehicle object 304 and the ego vehicle object 302 is the same, for example, Figure 4 The relative slope of the target vehicle object 404 relative to the vehicle object 402 is Figure 3 The relative slopes of the target vehicle object 304 and the ego vehicle object 302 are the same, both being β.

[0049] Will Figure 3 The sum of the line segment c and the line segment d in is taken as the relative distance between the target vehicle object 304 and the vehicle object 302. It can be understood that the relative distance between the target vehicle object 304 and the vehicle object 302 after the overall rotation is, that is, Figure 4 The relative distance between the target vehicle object 404 and the vehicle object 402 in the image does not change due to the overall rotation of the image. In other words, the calculated Figure 3 The relative distance between the target vehicle object 304 and the vehicle object 302 is converted into the calculation Figure 4 The sum of line segment c and line segment d in .

[0050] It is understandable that if the slope angle of the vehicle object 302 is Figure 3 The angle of the ramp where the target vehicle object 304 is Figure 3 In the figure, α is obviously simplified to the case where the vehicle is traveling on a flat road, and the slope β of the target vehicle object 304 relative to the vehicle object 302 is equal to α minus θ.

[0051] After executing step S202 and acquiring the first motion parameter set, the second motion parameter set, and the third motion parameter set, the above step S204 is executed to establish a Kalman filter equation group.

[0052] As an optional implementation, the above step S204, establishing a Kalman filter equation group between multiple state parameters and multiple observation parameters according to the first motion parameter set, the second motion parameter set and the third motion parameter set, includes the following steps:

[0053] S204-1, establishing a first Kalman filter state equation according to the first state parameter and the fourth state parameter, wherein the fourth state parameter is a vertical component of an acceleration parameter of the target vehicle object, and the first Kalman filter state equation is used to indicate that a current state value of the first state parameter is determined according to a historical state value of the first state parameter and a historical state value of the fourth state parameter;

[0054] S204-2, establishing a second Kalman filter state equation according to the second state parameter and the first acceleration parameter, wherein the first motion parameter set includes the first acceleration parameter, and the second Kalman filter state equation is used to indicate that a current state value of the second state parameter is determined according to a historical state value of the second state parameter and a historical state value of the first acceleration parameter;

[0055] S204-3, establishing a third Kalman filter state equation according to the third state parameter, the first state parameter and the fourth state parameter, wherein the third state parameter is the object height difference between the target vehicle object and the self-vehicle object, and the third Kalman filter state equation is used to indicate that the current state value of the third state parameter is determined according to the historical state value of the third state parameter, the historical state value of the first state parameter and the historical state value of the fourth state parameter;

[0056] S204-4 establishes a fourth Kalman filter state equation based on the fifth state parameter, the second state parameter and the first acceleration parameter, wherein the fifth state parameter is the first distance parameter in the first motion parameter set, and the fourth Kalman filter state equation is used to indicate that the current state value of the fifth state parameter is determined based on the historical state value of the fifth state parameter, the historical state value of the second state parameter and the historical state value of the first acceleration parameter.

[0057] It should be noted that in the above step S202-1, the above first state parameter is the vertical speed V of the target vehicle object. vertical The fourth object parameter is the vertical acceleration a of the target vehicle object. vertical , and further, the first Kalman filter state equation established according to the first state parameter and the fourth state parameter can be in the following form:

[0058] V vertical(k) =V vertical(k-1) +a vertical(k-1) T

[0059] In the first Kalman filter state equation, k represents the current state value, k-1 represents the historical state value, and T represents the time coefficient, which is usually the ACC (adaptive cruise control) program operation cycle, such as 25ms, and is not specifically limited here. Similarly, in the subsequent descriptions of this application, if there is no special explanation, k represents the current state value, k-1 represents the historical state value, and T represents the time coefficient, which will not be repeated hereafter.

[0060] It should be noted that in the above step S204-2, the above second state parameter is the relative speed RR between the target vehicle object and the vehicle in the horizontal direction. vision , the first acceleration parameter is the longitudinal acceleration a of the target vehicle object vision , a vision The data obtained by the image sensing unit, and then the second Kalman filter state equation established according to the second state parameter and the first acceleration parameter can conform to the following form:

[0061] RR vision(k) =RR vision(k-1) +a vision(k-1) T

[0062] Optionally, in the above step S204-3, the above third state parameter is the height Height of the target vehicle object. It should be noted that the height Height of the target vehicle object is the relative height between the target vehicle object and the vehicle. Figure 3 As shown. It is understandable that Figure 3 The relative height in is equivalent to Figure 4 The first state parameter and the fourth state parameter have been described above and will not be repeated here. Furthermore, the third Kalman filter state equation established according to the third state parameter, the first state parameter and the fourth state parameter may conform to the following form:

[0063]

[0064] In addition, in the above step S204-5, the fifth state parameter is the longitudinal distance R of the target vehicle object obtained by the image perception unit.vision (first distance parameter), and then, the fourth Kalman filter state equation established according to the fifth state parameter, the second state parameter and the first acceleration parameter can conform to the following form:

[0065]

[0066] Through the above steps S204 - 1 to S204 - 4 , a Kalman filter equation group between multiple state parameters and multiple observation parameters is established.

[0067] In addition, before the above step S204, the following steps may be performed:

[0068] S6001, determining a state quantity matrix for characterizing the Kalman filter equation group according to a first state parameter, a second state parameter, a third state parameter, a fourth state parameter, and a fifth state parameter;

[0069] S6002, determining the fifth state parameter as the first observation parameter among the multiple observation parameters, determining the second state parameter as the second observation parameter among the multiple observation parameters, and determining the second distance parameter in the second motion parameter set as the third observation parameter among the multiple observation parameters;

[0070] S6003, determining an observation matrix for characterizing the Kalman filter equation group according to the first observation parameter, the second observation parameter and the third observation parameter.

[0071] It can be understood that, in the above step S6001, the first state parameter, the second state parameter, the third state parameter, the fourth state parameter and the fifth state parameter are used as the state quantity matrix X in the extended Kalman filter, that is,

[0072]

[0073] At the same time, steps S6002 to S6003 are executed to determine the observation matrix Z for characterizing the extended Kalman filter equations using the first observation parameter, the second observation parameter and the third observation parameter, that is,

[0074]

[0075] Furthermore, based on obtaining the state quantity matrix X and the observation quantity matrix Z, the above step S204 may further include:

[0076] S2040-1, determining a numerical relationship among a first observation parameter, a third observation parameter, and a third state parameter;

[0077] S2040-2, determine the partial derivative results of the state parameters associated with each observation parameter in the observation matrix according to the numerical relationship, and obtain the observation transformation Jacobian matrix.

[0078] It should be noted that the first observation parameter is the longitudinal distance R of the target vehicle object obtained by the radar sensing unit. vision The third observation parameter is the longitudinal distance R of the target vehicle object obtained by the radar perception unit. radar , the third state parameter is the height of the target vehicle object. Then, the above numerical relationship can conform to the following form:

[0079]

[0080] It is understandable that if Figure 3 As shown, the longitudinal distance R of the target vehicle object obtained by the radar sensing unit Radar , R obtained by the radar perception unit vision , and the height of the target car object Height, form a right triangle, so the relationship between the three conforms to the Pythagorean theorem.

[0081] Furthermore, the observation transformation Jacobian matrix is ​​obtained by taking partial derivatives of the equivalent expression of each observation in the observation matrix Z.

[0082] R vision For example, due to

[0083]

[0084] for R vision , RR vision 、Height、V vertical 、a vertical By taking the partial derivatives respectively, we can get the resulting values ​​1, T, 0, 0, 0 respectively.

[0085] Similarly, for RR vision Corresponding RR vision(k-1) +a vision(k-1) T, and also R vision , RR vision 、Height、V vertical 、a vertical By taking partial derivatives respectively, we can get the resulting values ​​0, 1, 0, 0, 0 respectively.

[0086] For R radar Corresponding Also for R vision , RR vision 、Height、V vertical 、a vertical By calculating the partial derivatives respectively, we can get the result values ​​respectively. 0. 0, 0.

[0087] Thus, the above partial derivative results are used as the observation transformation Jacobian matrix H, that is,

[0088]

[0089] After obtaining the Kalman filter equation group between multiple state parameters and multiple observation parameters through the above step S204, execute step S206, and obtain the first target value after Kalman filtering the first state parameter according to the Kalman filter equation group, and obtain the second target value after Kalman filtering the second state parameter.

[0090] Then, after iterative calculation, the filtered vertical velocity V of the target vehicle can be obtained. vertical (first target value), and the filtered horizontal relative speed RR of the target vehicle object visiion (Second target value).

[0091] After the first target value and the second target value are obtained, step S208 is executed to determine the target vehicle distance between the self-vehicle object and the target vehicle object according to the first target value of the first state parameter and the second target value of the second state parameter, and the geometric position relationship between the target vehicle object located on the current ramp and the self-vehicle object located on the target ramp. Specifically, the above step S208 may include the following steps:

[0092] S208-1, determining a relative slope between a target ramp and a current ramp according to a first target value of a first state parameter and a second target value of a second state parameter;

[0093] S208-2, obtaining a third target value after performing Kalman filtering on a third state parameter according to the Kalman filter equation group, wherein the plurality of state parameters include the third state parameter, and the third state parameter is an object height difference between the target vehicle object and the self-vehicle object;

[0094] S208-3, determining a target vehicle distance between the ego vehicle object and the target vehicle object according to the relative slope, the third state parameter, and the first vehicle distance parameter in the first motion parameter set.

[0095] The above step S208-1 specifically includes the following steps:

[0096] Determining a relative slope between a target ramp and a current ramp according to the first target value and the second target value includes:

[0097] S2081-1, determining a sum of the second target value and the first reference value of the speed parameter of the target vehicle object as a second reference value, wherein the second reference value is used to indicate a horizontal component of the speed parameter of the target vehicle object;

[0098] S2081-2, determining the inverse tangent function value of the ratio between the first target value and the second reference value as the relative slope between the target ramp and the current ramp.

[0099] It should be noted that if Figure 4 As shown, the vertical velocity V of the target vehicle object 404 vertical With horizontal speed V vision The ratio is the tangent value of the relative slope β. That is,

[0100]

[0101] Wherein, the horizontal speed V of the target vehicle object 404 is vision The horizontal velocity V of the vehicle object 402 host The difference is the relative speed RR of the target vehicle object 404 and the self-vehicle object 402 on the horizontal plane. vision .Right now,

[0102] V vision =RR vision +V host

[0103] Furthermore, the process of solving the relative slope through the above steps S2081-1 to S2081-2 can be concretely solved by the following formula:

[0104]

[0105] Where β is the relative slope between the target ramp and the current ramp (the relative slope can be found in Figure 4 β in), V host is the first reference value of the velocity parameter of the vehicle object, which is used to represent the velocity of the vehicle on the horizontal plane. arctan is the inverse tangent function. V vertical is the vertical speed of the target vehicle after filtering (the first target value), RR visiion is the horizontal relative speed of the target vehicle object after filtering (the second target value).

[0106] Furthermore, after the relative slope β is obtained through the above step S208-1, step S208-2 is executed to obtain the third target value after Kalman filtering the third state parameter according to the Kalman filter equation group, wherein the multiple state parameters include the third state parameter, and the third state parameter is the object height difference between the target vehicle object and the own vehicle object; it can be understood that the filtered third target value is the relative height Height between the filtered target vehicle object and the own vehicle.

[0107] Further, step S208-3 is executed to determine a target vehicle distance between the ego vehicle object and the target vehicle object according to the relative slope, the third state parameter, and the first vehicle distance parameter in the first motion parameter set.

[0108] Optionally, the above step S208-3 may specifically include the following steps:

[0109] S2083-1, using the sine value of the relative slope as a third reference value, and using the tangent value of the relative slope as a fourth reference value;

[0110] S2083-2, determining a ratio between the third target value and the third reference value as a first target vehicle distance, wherein the first target vehicle distance is a distance between a reference point and a target vehicle object, and the reference point is a connection point between the current ramp and the target ramp;

[0111] S2083-3, determining a ratio between the third target value and the fourth reference value as a reference vehicle distance, wherein the reference vehicle distance is a horizontal distance between the reference point and the target vehicle object;

[0112] S2083-4, determining a difference between the first vehicle distance of the first vehicle distance parameter and the reference vehicle distance as a second target vehicle distance, wherein the second target vehicle distance is a distance between the reference point and the self-vehicle object;

[0113] S2083-5, determining the target vehicle distance based on the first target vehicle distance and the second target vehicle distance.

[0114] The following combination Figure 4 The above steps S2083-1 to S2083-5 are further explained as follows: Figure 4 As shown, the first target vehicle distance is Figure 4 The portion indicated by the line segment d in the figure, the second target vehicle distance is Figure 4 In the portion indicated by line segment c, the sum of line segment c and line segment d is determined as the actual distance between the vehicle and the target vehicle (the above-mentioned target vehicle distance).

[0115] Specifically, according to the definition of the sine function, sinβ is the ratio of line segment e to line segment d. Further, Height is approximated as the length of line segment e. Then, the process of calculating the first target vehicle distance in step S2083-2 can be in accordance with the following calculation formula:

[0116]

[0117] Where d is the first target vehicle distance ( Figure 4 In the middle line segment d), Height is the third target value, and sinβ is the sine value of the relative slope (third reference value).

[0118] In addition, by Figure 4It can be seen that the ratio of line segment e to line segment f is tanβ. If Height is approximated as the length of line segment e and line segment g is approximated as the length of line segment f, then the ratio of Height to line segment g is tanβ.

[0119] Furthermore, since the sum of line segment g and line segment c is R vision Furthermore, the process of determining the second target vehicle distance from step S2083-3 to step S2083-4 may conform to the following calculation formula:

[0120]

[0121] Among them, R vision is the first vehicle distance of the first vehicle distance parameter, Height is the third target value, and tanβ is the fourth reference value.

[0122] After the first target vehicle distance and the second target vehicle distance are determined, step S208-5 is executed to determine the target vehicle distance according to the first target vehicle distance and the second target vehicle distance. Specifically, the sum of the first target vehicle distance and the second target vehicle distance is used as the target vehicle distance, that is, the target vehicle distance can be calculated by the following formula:

[0123]

[0124] Among them, D is the above-mentioned target vehicle distance, and the other variables are explained in the above description of this application and will not be repeated here.

[0125] Through the above-mentioned implementation mode of the present application, first, when a target vehicle object traveling on a target ramp is detected, a first motion parameter set matching the target vehicle object is obtained according to an image perception unit, a second motion parameter set matching the target vehicle object is obtained according to a radar perception unit, and a third motion parameter set matching the self-vehicle object is obtained; and then, according to the first motion parameter set, the second motion parameter set and the third motion parameter set, a Kalman filter equation group between multiple state parameters and multiple observation parameters is established, wherein the multiple state parameters include a first state parameter and a second state parameter, the first state parameter being the vertical component of the velocity parameter of the target vehicle object, and the second state parameter being the horizontal component of the relative velocity parameter between the target vehicle objects. and according to the Kalman filter equation group, performing Kalman filtering on the first state parameter to obtain a first target value, and performing Kalman filtering on the second state parameter to obtain a second target value; further determining the relative slope between the target vehicle object on the current ramp and the self-vehicle object on the target ramp according to the first target value of the first state parameter and the second target value of the second state parameter, and further determining the target vehicle distance between the self-vehicle object and the target vehicle object based on the relative slope, thereby solving the technical problem in the prior art that the driving system cannot calculate the accurate vehicle distance due to inaccurate slope prediction, and further solving the problem that reasonable longitudinal acceleration planning cannot be performed according to the accurate vehicle distance prediction value, thereby improving the economy of the entire vehicle.

[0126] In an optional implementation, after determining the target vehicle distance between the ego vehicle object and the target vehicle object according to the first target value of the first state parameter and the second target value of the second state parameter and the geometric position relationship between the target vehicle object located on the current ramp and the ego vehicle object located on the target ramp, the method further includes:

[0127] S1, dynamically determining a fourth target value of the speed parameter of the ego vehicle object by the following formula according to the target vehicle distance, the preset vehicle distance threshold and the first reference value of the speed parameter of the ego vehicle object:

[0128]

[0129] Wherein, V1 is the fourth target value, V2 is the first reference value of the speed parameter of the vehicle object, d1 is the preset vehicle distance threshold, d2 is the target vehicle distance, K i is a variable coefficient.

[0130] It should be noted that V2 is the speed V of the vehicle object. host , d1 is the safe distance under ideal conditions. It can be understood that when d1 is different from the above target distance, V1 is different from V2. When d1 is the same as the above target distance, V1 is the same as V2. K iIt is a variable coefficient and can be freely adjusted by the user.

[0131] Furthermore, when the ideal safe vehicle distance is different from the above-mentioned target vehicle distance, the speed of the own vehicle object is adjusted according to the above-mentioned fourth target value. Specifically, if the third target value is greater than the target vehicle distance, the own vehicle object is decelerated; if the third target value is less than the target vehicle distance, the own vehicle object is accelerated.

[0132] It is worth noting that the adjustment of vehicle speed is a dynamic and continuous process. In this process, the speed adjustment of the target vehicle object is not controlled by the self-vehicle object. That is to say, when the speed of the self-vehicle object has not been adjusted to the fourth target value, the target vehicle distance and the safety vehicle distance may be the same. At this time, the speed adjustment of the self-vehicle object can be stopped. Through the above implementation of the present application, when the target vehicle distance is less than or equal to the first preset threshold, the speed of the self-vehicle object is reduced until the target vehicle distance is greater than the first preset threshold; when the target vehicle distance is less than or equal to the second preset threshold, the self-vehicle object performs a braking operation, so that the vehicle can perform more accurate deceleration and braking operations according to the accurate vehicle distance.

[0133] The following is an explanation of a complete method for determining vehicle distance and slope.

[0134] like Figure 3 As shown, the ego vehicle object 302 is traveling on a slope with a slope of θ, and the target vehicle object 304 is traveling on a slope with a slope of α.

[0135] As mentioned above, in some embodiments of the present application, the information to be calculated is the relative distance and relative speed between the target vehicle and the vehicle, so the calculation process can also be simplified to the vehicle driving on a flat road. Figure 3 The whole vehicle object 302 is rotated by a certain angle so that the vehicle object 302 is on the horizontal plane. Figure 4 As shown, Figure 4 In the figure, the target vehicle object 404 is the rotated target vehicle object 304, and the ego vehicle object 402 is the rotated ego vehicle object 302. It can be understood that the relative geometric relationship between the target vehicle object 404 and the ego vehicle object 402 is the same as Figure 3 The relative geometric relationship between the target vehicle object 304 and the ego vehicle object 302 is the same.

[0136] Assume that the ACC function of the ego vehicle object 402 is in an activated state at this time, and the ego vehicle object 402 follows the target vehicle object 404 .

[0137] First, execute Figure 6 In step S602, information such as the target longitudinal distance measured by the front radar, the target longitudinal distance and longitudinal speed measured by vision are obtained.

[0138] Specifically, the longitudinal distance R between the vehicle object 402 and the target vehicle object 404 in front of it is perceived by the configured camera. vision , the longitudinal velocity is V vision , the longitudinal acceleration is a vision The longitudinal distance R between the vehicle object 402 and the target vehicle object 404 in front of it is sensed by the configured front radar. Radar , the longitudinal velocity is V Radar , the longitudinal acceleration is a Radar .

[0139] Afterwards, execute Figure 6 In step S604, information such as the vehicle speed and acceleration is obtained.

[0140] It should be noted that the speed and acceleration information of the ego vehicle object 402 is obtained by the IMU sensor of the ego vehicle object 402. After the acquisition, the Kalman filter can be performed according to the speed and acceleration of the ego vehicle object 302 obtained by the IMU sensor to obtain more accurate speed and acceleration information of the ego vehicle object 402 after filtering, that is, perform Figure 5 Steps S502 to S506 in .

[0141] The constraints of Kalman filtering are as follows.

[0142] State space expression:

[0143] X k =AX k-1

[0144] Error state covariance matrix:

[0145] P k =AP k-1 A T +Q

[0146] Kalman gain:

[0147] K k =P k H T (HP k H T +R) ′

[0148] Error status update:

[0149]

[0150] Error state covariance matrix update:

[0151] P k =(IK k H)P k-1

[0152] Vehicle speed V host The constraints are as follows:

[0153] V host(k) =V host(k-1) +aT

[0154] Among them, a is the actual acceleration of the vehicle, and the constraints of the actual acceleration a of the vehicle are as follows:

[0155] a=a sensor -g·sinθ

[0156] Among them, a sensor It is the acceleration value of the vehicle obtained by the vehicle sensor.

[0157] Steps S504 to S506 are executed according to the above constraints, that is, the slope angle of the ego vehicle object 402 and the actual speed and acceleration of the ego vehicle object 402 are obtained through iterative calculation of the Kalman filter.

[0158] Then, step S604 is executed to perform an extended Kalman filter calculation to obtain the relative slope of the target relative to the vehicle.

[0159] Specifically, execute Figure 7 Steps S702 to S710.

[0160] Wherein, step S702 is first executed to confirm the state quantity and observation quantity of the Kalman filter.

[0161] It should be noted that the present application uses the distance R between the target vehicle object and the self-vehicle object in the horizontal direction measured by the camera as vision , the relative speed RR between the target vehicle object and the self-vehicle object in the horizontal direction vision , the relative height of the target vehicle object relative to the self-vehicle object Height, the vertical speed of the target vehicle object V vertical , the vertical acceleration of the target vehicle object a vertical As the state matrix X in the (extended) Kalman filter, that is,

[0162]

[0163] The above R vision , R.R. vision And the distance R between the target vehicle object and the vehicle object obtained by the radar radar As the observation matrix Z of the extended Kalman filter, that is,

[0164]

[0165] Further, step S704 is executed to confirm the state transfer matrix and control matrix of the (extended) Kalman filter.

[0166] Specifically, there are the following constraints for each state quantity in the above state quantity matrix.

[0167] The distance R between the target and the vehicle at the current moment in the horizontal direction vision Constraints:

[0168]

[0169] The relative speed RR between the target and the vehicle at the current moment in the horizontal direction vision Constraints:

[0170] RR vision(k) =RR vision(k-1) +a vision(k-1) T

[0171] The current target vehicle object height. The current target height Height constraints:

[0172]

[0173] The vertical speed of the target vehicle V vertical There are the following constraints.

[0174] V vertical(k) =V vertical(k-1) +a vertical(k-1) T

[0175] It can be understood that the vertical acceleration a of the target vehicle object vertical ,have:

[0176] a vertical =a vertical

[0177] That is, a vertical Equal to itself, the above constraints are expressed according to the (expanded) Kalman state space expression X k =AX k-1 +B·a vision Determine the state transfer matrix A and the control matrix B.

[0178] Specifically, obtain the right side R of the equation in each of the above constraints respectively vision , RR vision 、Height、V vertical 、a vertical The coefficient of R vision For example, in R vision Among the constraints, there are Among them, R vision , RR vision 、Height、V vertical 、avertical The coefficients are 1, T, 0, 0, and 0 respectively. It is worth noting that in R vision The acceleration involved in the constraint condition is the longitudinal acceleration a of the target vehicle object measured by the camera. vision , rather than a vertical , so a vertical The corresponding coefficient is 0.

[0179] Similarly, we can get RR vision 、Height、V vertical 、a vertical In the constraints of R vision , RR vision 、Height、V vertical 、a vertical The corresponding coefficients are 0, 1, 0, 0, 0; 0, 0, 1, T, 0.5T respectively. 2 ;0,0,0,1,T;0,0,0,0,1.

[0180] Taking the above coefficients as the element values ​​in the state transfer matrix A, we can get:

[0181]

[0182] According to the spatial state expression X k =AX k-1 +B·a vision , determine a among the above constraints vision The corresponding coefficient, R vision For example, in R vision Among the constraints, there are where a vision The corresponding coefficient is 0.5T 2 , and similarly we can get RR vision 、Height、V vertical 、a vertical Among the constraints, a vision The coefficients corresponding to the terms are T, 0, 0, and 0 respectively.

[0183] Taking the above coefficients as the elements in the control matrix B, we can get:

[0184]

[0185] Further, step S706 is executed to calculate the observation transformation Jacobian matrix.

[0186] The method of calculating the observation transformation Jacobian matrix in step S706 has been described in detail in the explanations of the aforementioned steps S2040-1 to S2040-2. The specific process can be referred to the explanations of the aforementioned steps S2040-1 to S2040-2, and will not be repeated here.

[0187] Through the above step S706, the observation conversion Jacobian matrix H can be obtained, where:

[0188]

[0189] Afterwards, step S708 is executed to confirm the covariance matrix P of the initial state vector, the process covariance matrix Q and the observation covariance matrix R.

[0190] Specifically, for the covariance matrix P of the initial state vector, let

[0191]

[0192] For the process covariance matrix Q, let

[0193]

[0194] For the observation covariance matrix R, let

[0195]

[0196] Then, the above step S710 is executed to perform iterative calculation according to the Kalman filter formula.

[0197] Specifically, the constraints of the (extended) Kalman filter are as follows.

[0198] State space expression:

[0199] X k =AX k-1 +B·a vision

[0200] Error state covariance matrix:

[0201] P k =AP k-1 A T +Q

[0202] Kalman gain:

[0203] K k =P k H T (HP k H T +R) ′

[0204] Error status update:

[0205]

[0206] Error state covariance matrix update:

[0207] P k =(IK k H)P k-1

[0208] Thus, the filtered RR is obtained vision 、Height、R vision , and calculate the relative slope β between the target vehicle object 404 and the vehicle object 402. The specific calculation formula is as follows:

[0209]

[0210] After the relative slope β is determined, step S608 is executed to calculate the actual distance of the target according to the relative slope. The specific calculation formula is as follows:

[0211]

[0212] The derivation process of the solution formula of the relative slope β and the actual distance D has been described above, and will not be repeated here. express Figure 3 The distance represented by the midline segment d, express Figure 3 The distance represented by the middle line segment c is the sum of the two equal to the distance between the vehicle object 302 and the target vehicle object 304. It should also be noted that due to factors such as the tire height and the rear length of the vehicle, and There will be a certain error between the sum and the absolute actual distance.

[0213] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0214] According to another aspect of the embodiment of the present application, a device for determining vehicle distance and slope for implementing the above-mentioned method for determining vehicle distance and slope is also provided. Figure 8 As shown, the device comprises:

[0215] The acquisition unit 802, when detecting a target vehicle object traveling on a target ramp, acquires a first motion parameter set matching the target vehicle object according to the image perception unit, acquires a second motion parameter set matching the target vehicle object according to the radar perception unit, and acquires a third motion parameter set matching the ego vehicle object;

[0216] An establishing unit 804 establishes a Kalman filter equation group between a plurality of state parameters and a plurality of observation parameters according to the first motion parameter set, the second motion parameter set, and the third motion parameter set, wherein the plurality of state parameters include a first state parameter and a second state parameter, the first state parameter is a vertical component of a velocity parameter of a target vehicle object, and the second state parameter is a horizontal component of a relative velocity parameter between target vehicle objects;

[0217] A filtering unit 806 performs Kalman filtering on the first state parameter to obtain a first target value according to the Kalman filter equation group, and performs Kalman filtering on the second state parameter to obtain a second target value;

[0218] The determination unit 808 determines a target vehicle distance between the ego vehicle object and the target vehicle object according to the first target value of the first state parameter and the second target value of the second state parameter, and the geometric position relationship between the target vehicle object on the current ramp and the ego vehicle object on the target ramp.

[0219] As an optional solution, the above-mentioned determination unit 808 includes: a vehicle distance determination module, which is used to determine the relative slope between the target ramp and the current ramp according to the first target value of the first state parameter and the second target value of the second state parameter; obtain a third target value after performing Kalman filtering on the third state parameter according to the Kalman filter equation group, wherein the multiple state parameters include the third state parameter, and the third state parameter is the object height difference between the target vehicle object and the own vehicle object; determine the target vehicle distance between the own vehicle object and the target vehicle object according to the relative slope, the third state parameter, and the first vehicle distance parameter in the first motion parameter set.

[0220] As an optional solution, the above-mentioned vehicle distance determination module is also used to: determine the sum of the second target value and the first reference value of the speed parameter of the target vehicle object as the second reference value, wherein the second reference value is used to indicate the horizontal component of the speed parameter of the target vehicle object; and determine the inverse tangent function value of the ratio between the first target value and the second reference value as the relative slope between the target ramp and the current ramp.

[0221] As an optional solution, the above-mentioned vehicle distance determination module is also used to: use the sine value of the relative slope as the third reference value, and use the tangent value of the relative slope as the fourth reference value; determine the ratio between the third target value and the third reference value as the first target vehicle distance, wherein the first target vehicle distance is the distance between the reference point and the target vehicle object, and the reference point is the connection point between the current ramp and the target ramp; determine the ratio between the third target value and the fourth reference value as the reference vehicle distance, wherein the reference vehicle distance is the horizontal distance between the reference point and the target vehicle object; determine the difference between the first vehicle distance of the first vehicle distance parameter and the reference vehicle distance as the second target vehicle distance, wherein the second target vehicle distance is the distance between the reference point and the self-vehicle object; and determine the target vehicle distance based on the first target vehicle distance and the second target vehicle distance.

[0222] As an optional solution, the above-mentioned establishment unit 804 includes: a reference establishment module, which is used to establish a first Kalman filter equation group according to a first state parameter and a fourth state parameter, wherein the fourth state parameter is a vertical component of an acceleration parameter of a target vehicle object, and the first Kalman filter equation group is used to indicate that a current state value of the first state parameter is determined according to a historical state value of the first state parameter and a historical state value of the fourth state parameter; establish a second Kalman filter equation group according to a second state parameter and a first acceleration parameter, wherein the first motion parameter set includes a first acceleration parameter, and the second Kalman filter equation group is used to indicate that a current state value of the second state parameter is determined according to a historical state value of the second state parameter and a historical state value of the first acceleration parameter; and establish a second Kalman filter equation group according to a third state parameter. , the first state parameter and the fourth state parameter establish a third Kalman filter equation group, wherein the third state parameter is the object height difference between the target vehicle object and the self-vehicle object, and the third Kalman filter equation group is used to indicate that the current state value of the third state parameter is determined according to the historical state value of the third state parameter, the historical state value of the first state parameter, and the historical state value of the fourth state parameter; the fourth Kalman filter equation group is established according to the fifth state parameter, the second state parameter and the first acceleration parameter, wherein the fifth state parameter is the first distance parameter in the first motion parameter set, and the fourth Kalman filter equation group is used to indicate that the current state value of the fifth state parameter is determined according to the historical state value of the fifth state parameter, the historical state value of the second state parameter, and the historical state value of the first acceleration parameter.

[0223] As an optional solution, the above-mentioned vehicle distance and slope determination device also includes: a measurement matrix establishment module, which is used to determine a state quantity matrix used to characterize the Kalman filter equation group based on the first state parameter, the second state parameter, the third state parameter, the fourth state parameter and the fifth state parameter; determine the fifth state parameter as the first observation parameter among multiple observation parameters, determine the second state parameter as the second observation parameter among multiple observation parameters, and determine the second distance parameter in the second motion parameter set as the third observation parameter among multiple observation parameters; determine the observation quantity matrix used to characterize the Kalman filter equation group based on the first observation parameter, the second observation parameter and the third observation parameter.

[0224] As an optional scheme, the above-mentioned establishment unit 804 also includes: a partial derivative reference module, which is used to determine the numerical relationship between the first observation parameter, the third observation parameter and the third state parameter; determine the partial derivative results of the state parameters associated with each observation parameter in the observation matrix according to the numerical relationship, and obtain the observation transformation Jacobian matrix.

[0225] As an optional solution, the above-mentioned vehicle distance and slope determination device further includes: an adjustment unit, which is used to dynamically determine a fourth target value of the speed parameter of the own vehicle object according to the target vehicle distance, the preset vehicle distance threshold and the first reference value of the speed parameter of the own vehicle object through the following formula:

[0226]

[0227] Wherein, V1 is the fourth target value, V2 is the first reference value of the speed parameter of the vehicle object, d1 is the preset vehicle distance threshold, d2 is the target vehicle distance, K i is a variable coefficient.

[0228] The specific implementation example can refer to the example shown in the above-mentioned method for determining the vehicle distance and the slope, which will not be repeated here in this example.

[0229] Among them, the memory 902 can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for determining the vehicle distance and slope in the embodiment of the present invention. The processor 904 executes various functional applications and data processing by running the software programs and modules stored in the memory 902, that is, realizing the above-mentioned method for determining the vehicle distance and slope. The memory 902 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 902 may further include a memory remotely arranged relative to the processor 904, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 902 can be specifically, but not limited to, used to store file information such as target logical files. As an example, such as Fig. 9 As shown, the memory 902 may include, but is not limited to, the acquisition unit 802, the establishment unit 804, the filtering unit 806, and the determination unit 808 in the above-mentioned vehicle distance and slope determination device. In addition, it may also include, but is not limited to, other module units in the above-mentioned vehicle distance and slope determination device, which will not be repeated in this example.

[0230] Optionally, the transmission device 906 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 906 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 906 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0231] In addition, the electronic device mentioned above further includes: a display 908, and a connection bus 910, which is used to connect various module components in the electronic device mentioned above.

[0232] According to one aspect of the present application, a computer program product is provided, the computer program product comprising a computer program / instruction, the computer program / instruction comprising a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit, various functions provided by the embodiments of the present application are executed.

[0233] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0234] It should be noted that the computer system of the electronic device is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0235] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit, various functions defined in the system of the present application are executed.

[0236] According to one aspect of the present application, a computer-readable storage medium is provided, and a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0237] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0238] S1, when a target vehicle object traveling on a target ramp is detected, a first motion parameter set matching the target vehicle object is obtained according to an image perception unit, a second motion parameter set matching the target vehicle object is obtained according to a radar perception unit, and a third motion parameter set matching the self-vehicle object is obtained.

[0239] S2, establishing a Kalman filter equation group between multiple state parameters and multiple observation parameters according to the first motion parameter set, the second motion parameter set and the third motion parameter set, wherein the multiple state parameters include a first state parameter and a second state parameter, the first state parameter is a vertical component of a velocity parameter of the target vehicle object, and the second state parameter is a horizontal component of a relative velocity parameter between the target vehicle objects;

[0240] S3, according to the Kalman filter equation group, performing Kalman filtering on the first state parameter to obtain a first target value, and performing Kalman filtering on the second state parameter to obtain a second target value;

[0241] S4, determining a relative relationship between a target vehicle object located on the current ramp and an ego vehicle object located on the target ramp and a target vehicle distance according to a first target value of the first state parameter and a second target value of the second state parameter.

[0242] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the electronic device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0243] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0244] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers or network devices, etc.) to execute all or part of the steps of the methods of each embodiment of the present application.

[0245] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0246] In the several embodiments provided in the present application, it should be understood that the disclosed user equipment can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0247] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0248] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0249] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining vehicle distance and slope, characterized in that: include: When a target vehicle object traveling on a target ramp is detected, a first motion parameter set matching the target vehicle object is obtained according to an image sensing unit, a second motion parameter set matching the target vehicle object is obtained according to a radar sensing unit, and a third motion parameter set matching the ego vehicle object is obtained; According to the first motion parameter set, the second motion parameter set and the third motion parameter set, a Kalman filter equation group between multiple state parameters and multiple observation parameters is established, wherein the multiple state parameters include a first state parameter and a second state parameter, the first state parameter is a vertical component of a velocity parameter of the target vehicle object, and the second state parameter is a horizontal component of a relative velocity parameter between the target vehicle objects; According to the Kalman filter equation group, performing Kalman filtering on the first state parameter to obtain a first target value, and performing Kalman filtering on the second state parameter to obtain a second target value; The relative slope and target vehicle distance between the target vehicle object located on the current ramp and the self-vehicle object located on the target ramp are determined according to the first target value of the first state parameter and the second target value of the second state parameter.

2. The method according to claim 1, characterized in that: The step of determining the relative slope and target vehicle distance between the target vehicle object located on the current ramp and the self-vehicle object located on the target ramp according to the first target value and the second target value includes: determining the relative slope according to the first target value of the first state parameter and the second target value of the second state parameter; Obtaining a third target value after performing Kalman filtering on a third state parameter according to the Kalman filter equation group, wherein the plurality of state parameters include a third state parameter, and the third state parameter is an object height difference between the target vehicle object and the self-vehicle object; The target vehicle distance between the ego-vehicle object and the target vehicle object is determined according to the relative slope, the third state parameter, and the first vehicle distance parameter in the first motion parameter set.

3. The method according to claim 2, characterized in that The determining, according to the first target value and the second target value, a relative slope between the target ramp and the current ramp comprises: Determine a sum of the second target value and a first reference value of the speed parameter of the ego vehicle object as a second reference value, wherein the second reference value is used to indicate a horizontal component of the speed parameter of the target vehicle object; An inverse tangent function value of the ratio between the first target value and the second reference value is determined as a relative slope between the target slope and the current slope.

4. The method according to claim 2, characterized in that: Determining the target vehicle distance between the self-vehicle object and the target vehicle object according to the relative slope, the third state parameter, and the first vehicle distance parameter in the first motion parameter set includes: Using the sine value of the relative slope as a third reference value, and using the tangent value of the relative slope as a fourth reference value; Determine a ratio between the third target value and the third reference value as a first target vehicle distance, wherein the first target vehicle distance is a distance between a reference point and the target vehicle object, and the reference point is a connection point between the current ramp and the target ramp; Determine a ratio between the third target value and the fourth reference value as a reference vehicle distance, wherein the reference vehicle distance is a horizontal distance between the reference point and the target vehicle object; Determine a difference between a first vehicle distance of the first vehicle distance parameter and the reference vehicle distance as a second target vehicle distance, wherein the second target vehicle distance is a distance between a reference point and the self-vehicle object; The target vehicle distance is determined according to the first target vehicle distance and the second target vehicle distance.

5. The method according to claim 1, characterized in that: The establishing of a Kalman filter equation group between a plurality of state parameters and a plurality of observation parameters according to the first motion parameter set, the second motion parameter set and the third motion parameter set comprises: Establishing a first Kalman filter state equation according to the first state parameter and the fourth state parameter, wherein the fourth state parameter is a vertical component of an acceleration parameter of the target vehicle object, and the first Kalman filter state equation is used to indicate that a current state value of the first state parameter is determined according to a historical state value of the first state parameter and a historical state value of the fourth state parameter; Establishing a second Kalman filter state equation according to the second state parameter and the first acceleration parameter, wherein the first motion parameter set includes the first acceleration parameter, and the second Kalman filter state equation is used to indicate that a current state value of the second state parameter is determined according to a historical state value of the second state parameter and a historical state value of the first acceleration parameter; A third Kalman filter state equation is established according to a third state parameter, the first state parameter and the fourth state parameter, wherein the third state parameter is an object height difference between the target vehicle object and the self-vehicle object, and the third Kalman filter state equation is used to indicate that a current state value of the third state parameter is determined according to a historical state value of the third state parameter, a historical state value of the first state parameter and a historical state value of the fourth state parameter; A fourth Kalman filter state equation is established based on the fifth state parameter, the second state parameter and the first acceleration parameter, wherein the fifth state parameter is the first distance parameter in the first motion parameter set, and the fourth Kalman filter state equation is used to indicate that the current state value of the fifth state parameter is determined based on the historical state value of the fifth state parameter, the historical state value of the second state parameter and the historical state value of the first acceleration parameter.

6. The method according to claim 5, characterized in that Before establishing a Kalman filter equation group between a plurality of state parameters and a plurality of observation parameters according to the first motion parameter set, the second motion parameter set and the third motion parameter set, the method further includes: Determine a state quantity matrix for characterizing the Kalman filter equation group according to the first state parameter, the second state parameter, the third state parameter, the fourth state parameter and the fifth state parameter; Determine the fifth state parameter as a first observation parameter among the plurality of observation parameters, determine the second state parameter as a second observation parameter among the plurality of observation parameters, and determine the second distance parameter in the second motion parameter set as a third observation parameter among the plurality of observation parameters; An observation matrix for characterizing the Kalman filter equation group is determined according to the first observation parameter, the second observation parameter and the third observation parameter.

7. The method according to claim 6, characterized in that The establishing of a Kalman filter equation group between a plurality of state parameters and a plurality of observation parameters according to the first motion parameter set, the second motion parameter set and the third motion parameter set comprises: Determining a numerical relationship between the first observation parameter, the third observation parameter and the third state parameter; The partial derivative results of the state parameters associated with each observation parameter in the observation quantity matrix are determined according to the numerical relationship to obtain an observation conversion Jacobian matrix.

8. The method according to any one of claims 1 to 7, characterized in that After determining the target vehicle distance between the ego vehicle object and the target vehicle object according to the first target value of the first state parameter and the second target value of the second state parameter, and the geometric position relationship between the target vehicle object located on the current ramp and the ego vehicle object located on the target ramp, the method further includes: According to the target vehicle distance, the preset vehicle distance threshold and the first reference value of the speed parameter of the ego vehicle object, the fourth target value of the speed parameter of the ego vehicle object is dynamically determined by the following formula: Wherein, V1 is the fourth target value, V2 is the first reference value of the speed parameter of the vehicle object, d1 is the preset vehicle distance threshold, d2 is the target vehicle distance, K i is a variable coefficient.

9. A device for determining vehicle distance and slope, characterized in that: include: an acquisition unit, when detecting a target vehicle object traveling on a target ramp, acquiring a first motion parameter set matching the target vehicle object according to the image perception unit, acquiring a second motion parameter set matching the target vehicle object according to the radar perception unit, and acquiring a third motion parameter set matching the self-vehicle object; An establishing unit is configured to establish a Kalman filter equation group between a plurality of state parameters and a plurality of observation parameters according to the first motion parameter set, the second motion parameter set and the third motion parameter set, wherein the plurality of state parameters include a first state parameter and a second state parameter, the first state parameter is a vertical component of a velocity parameter of the target vehicle object, and the second state parameter is a horizontal component of a relative velocity parameter between the target vehicle objects; a filtering unit, which performs Kalman filtering on the first state parameter according to the Kalman filter equation group to obtain a first target value, and performs Kalman filtering on the second state parameter to obtain a second target value; A determination unit is provided, based on the first target value of the first state parameter and the second target value of the second state parameter, and a relative slope and a target vehicle distance between the target vehicle object located on the current slope and the self-vehicle object located on the target slope.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 8 when executed by an electronic device.

11. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 8 through the computer program.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images