Control method and equipment of adaptive cruise control system (ACC)
By calculating the lateral acceleration of the target vehicle and predicting its deflection, it is judged whether the target vehicle has cut into the own lane, which solves the problem of too long judgment time in the existing technology and improves the recognition speed and accuracy of the adaptive cruise control system ACC.
Patent Information
- Application Number
- CN202310890086.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-19
- Publication Date
- 2025-01-21
AI Technical Summary
The existing adaptive cruise control system ACC has been used to determine that the car ahead has been cut into this lane for too long, resulting in misidentification and bad experience, reducing product quality and customer satisfaction.
By receiving the first lateral offset dy of the target vehicle, calculating its lateral acceleration ay, and predicting the second lateral offset dycpredicted of the target vehicle after the time period tdx based on this acceleration, calculating the overlap rate between the target vehicle and the own vehicle, thereby judging Whether the target vehicle has any behavior of cutting into the lane where the own vehicle is located.
Significantly improves the speed and accuracy of the adaptive cruise control system ACC's recognition of target vehicle entry behaviors, improving product quality, customer satisfaction and system safety.
Smart Images
Figure CN119329520A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of adaptive cruise control systems (ACC), and more specifically, to a control method and device for an adaptive cruise control system (ACC), an advanced driver assistance system (ADAS), a computer-readable storage medium, and a computer program product. Background Art
[0002] As the main basic component of the advanced driver assistance system ADAS, the main purpose of the adaptive cruise control system ACC is to be able to select the moving vehicle in front of the vehicle as the primary target (also called the "target vehicle"), and to control the longitudinal motion state and following distance of the vehicle in real time and comfortably according to the motion state of the primary target.
[0003] One of the corresponding challenges is that the advanced driver assistance system ADAS products need to correctly process all targets detected by the sensors, including the three lanes in front of the vehicle. While being able to promptly and correctly identify the lane change behavior of the vehicle in front of the vehicle from other lanes (i.e., not the vehicle's lane) to ensure that the adaptive cruise control system ACC can comfortably control the safe distance from the vehicle in front, it is also necessary to reduce the misidentification of the lane change behavior of the target vehicle in front of the vehicle, prevent the adaptive cruise control system ACC from misbraking or misaccelerating, and thus reduce the customer's bad experience.
[0004] Currently, the adaptive cruise control system ACC takes too long to determine that the vehicle in front is cutting into the lane. Overall, the actual vehicle test results show that the adaptive cruise control system ACC can successfully identify the target vehicle's cutting behavior only when nearly half of the vehicle body enters the lane where the vehicle is located. Taking too long to determine that the vehicle in front is cutting into the lane will reduce the customer experience (for example, customers feel that the adaptive cruise control system ACC's target selection is slow). Moreover, this will also cause the longitudinal control of the adaptive cruise control system ACC to be delayed, reducing the product quality of the advanced driver assistance system ADAS. Summary of the invention
[0005] According to one aspect of the present application, a control method for an adaptive cruise control system ACC is provided, the method comprising: receiving a first lateral offset dy of a target vehicle; calculating a lateral acceleration ay of the target vehicle based on the first lateral offset dy; predicting a lateral acceleration ay of the target vehicle in a time period t based on the lateral acceleration ay dx After the second lateral displacement dyc predicted ; and according to the second lateral offset dyc predicted The overlap rate between the target vehicle and the host vehicle is calculated to determine whether the target vehicle has cut into the lane where the host vehicle is located.
[0006] As a supplement or replacement for the above solution, in the above method, receiving the first lateral offset dy of the target vehicle includes: receiving the current lateral offset value dy of the target vehicle in the coordinate system of the vehicle from the perception module per And the lateral offset value dy of the previous cycle perlast .
[0007] As a supplement or alternative to the above solution, in the above method, calculating the lateral acceleration ay of the target vehicle based on the first lateral offset dy includes: determining the current lateral speed vy of the target vehicle current and the lateral velocity vy of the previous cycle last ; and according to the current lateral speed vy current and the lateral velocity vy of the previous cycle last To calculate the lateral acceleration ay.
[0008] As a supplement or replacement for the above solution, in the above method, the time period t dx is associated with the variance of the first lateral offset dy.
[0009] As a supplement or replacement for the above solution, in the above method, the second lateral displacement dyc of the target vehicle after the time period tdx is predicted based on the lateral acceleration ay predicted The method comprises: predicting the target vehicle in the time period t based on the lateral acceleration ay dx The first lateral offset change dy predicted ; and based on the first lateral offset change dy predicted Calculate the second lateral offset dyc predicted .
[0010] As a supplement or replacement for the above solution, in the above method, the target vehicle is predicted in the time period t based on the lateral acceleration ay dx The first lateral offset change dy predicted Comprising: determining a first weight factor K according to the lateral acceleration ay ay At least according to the first weight factor K ay Determine the predicted lateral velocity vy of the target vehicle predicted ; and calculating the first lateral offset change dy according to the predicted lateral velocity predicted .
[0011] As a supplement or replacement for the above solution, in the above method, the predicted lateral velocity vy predicted Determined according to the following formula:
[0012] vy predicted =(vy current-vy last )×K ay +vy last ,
[0013] Among them, vy current Indicates the current lateral speed of the target vehicle and vy last represents the lateral velocity of the previous cycle; and
[0014] The first lateral offset variation dy predicted Determined according to the following formula:
[0015] dy predicted =vy predicted ×t dx ,
[0016] Among them, vy predicted is the predicted lateral velocity, t dx for the time period.
[0017] As a supplement or replacement for the above solution, in the above method, based on the first lateral offset change dy predicted Calculate the second lateral offset dyc predicted Includes: Based on the third lateral offset dyc Tipl Calculate the expected third lateral displacement dyc Tiplpredicted , wherein the third lateral offset dyc Tipl represents the lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located, and the estimated third lateral offset dyc Tiplpredicted In the time period t dx Then the estimated lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located; based on the fourth lateral offset dyc Kap Calculate the expected fourth lateral displacement dyc Kappredicted , wherein the fourth lateral offset dyc Kap represents the lateral distance from the center line of the target vehicle to the front trajectory line of the vehicle based on the current steering, and the estimated fourth lateral offset dyc Kappredicted In the time period t ax Then the estimated lateral distance from the center line of the target vehicle to the front trajectory line of the vehicle; and the estimated third lateral offset dyc Tiplpredicted and the estimated fourth lateral offset dyc Kappredicted Fusion is performed to determine the second lateral offset dyc predicted .
[0018] As a supplement or alternative to the above solution, in the above method, the expected third lateral offset dyc Tiplpredicted Determine according to the following formula:
[0019] dyc Tiplpredicted =dy predicted +dyc Tipl ,
[0020] Among them, dy predicted represents the first lateral offset change, and dyc Tipl represents the third lateral offset;
[0021] The estimated fourth lateral displacement dyc Kappredicted Determine according to the following formula:
[0022] dyc Kappredicted =dy predicted +dyc Kap ,
[0023] Among them, dyc Kap represents the fourth lateral offset; and
[0024] The second lateral offset dyc predicted Determined according to the following formula:
[0025] dyc predicted =dyc Tiplpredicted +(dyc Kappredicted -dyc Tiplpredicted )×K dx ,
[0026] Among them, K dx is a second weighting factor, which is associated with the longitudinal distance dx between the host vehicle and the target vehicle.
[0027] As a supplement or alternative to the above solution, in the above method, according to the second lateral offset dyc predicted Calculating the overlap rate between the target vehicle and the vehicle includes:
[0028] The overlap ratio between the target vehicle and the vehicle is determined according to the following formula: predicted :
[0029] overlap predicted =1-dyc presicted ÷(0.5×(width ego +width obj )),
[0030] Among them, width ego Indicates the width of the vehicle, and width obj Indicates the width of the target vehicle.
[0031] As a supplement or replacement for the above solution, the above method may further include: by continuously accumulating the overlap rate overlap between the target vehicle and the vehicle predicted , calculate the overlap score overlap between the vehicle and the target vehicle score ; and according to the overlap score overlap between the vehicle and the target vehicle score Determine whether the target vehicle has cut into the lane where the host vehicle is located.
[0032] According to another aspect of the present application, a control device for an adaptive cruise control system ACC is provided, the device comprising: a receiving device for receiving a first lateral offset dy of a target vehicle; a first calculating device for calculating a lateral acceleration ay of the target vehicle based on the first lateral offset dy; a predicting device for predicting a lateral acceleration ay of the target vehicle in a time period t based on the lateral acceleration ay dx After the second lateral displacement dyc predicted and a second calculating means for calculating the value of the second lateral offset dyc predicted The overlap rate between the target vehicle and the host vehicle is calculated to determine whether the target vehicle has cut into the lane where the host vehicle is located.
[0033] As a supplement or replacement for the above solution, in the above device, the receiving device is configured to receive the current lateral offset value dy of the target vehicle in the coordinate system of the vehicle from the perception module. per And the lateral offset value dy of the previous cycle perlast .
[0034] As a supplement or replacement for the above solution, in the above device, the first calculation device includes: a first determination unit, for determining the current lateral speed vy of the target vehicle current and the lateral velocity vy of the previous cycle last ; and a first calculation unit for calculating the current lateral velocity vy according to the current and the lateral velocity vy of the previous cycle last To calculate the lateral acceleration ay.
[0035] As a supplement or replacement for the above solution, in the above device, the time period t dx is associated with the variance of the first lateral offset dy.
[0036] As a supplement or replacement for the above solution, in the above device, the prediction device includes: a second determination unit for predicting the target vehicle in the time period t based on the lateral acceleration ay dx The first lateral offset change dy predicted and a second calculation unit for calculating the value of the first lateral displacement change dy based on the first lateral displacement change dypredicted Calculate the second lateral offset dyc predicted .
[0037] As a supplement or replacement for the above solution, in the above device, the second determination unit is configured to: determine the first weighting factor K according to the lateral acceleration ay ay At least according to the first weight factor K ay Determine the predicted lateral velocity vy of the target vehicle predicted ; and calculating the first lateral offset change dy according to the predicted lateral velocity predicted .
[0038] As a supplement or replacement for the above solution, in the above device, the predicted lateral velocity vy predicted Determined according to the following formula:
[0039] vy predicted =(vy current -vy last )×K ay +vy last ,
[0040] Among them, vy current Indicates the current lateral speed of the target vehicle and vy last represents the lateral velocity of the previous cycle; and
[0041] The first lateral offset variation dy p Redict d Determined according to the following formula:
[0042] dy predicted =vy predicted ×t dx ,
[0043] Among them, vy predicted is the predicted lateral velocity, t dx for the time period.
[0044] As a supplement or replacement for the above solution, in the above device, the second calculation unit is configured to: based on the third lateral offset dyc Tipl Calculate the expected third lateral displacement dyc Tiplpredicted , wherein the third lateral offset dyc Tipl represents the lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located, and the estimated third lateral offset dyc Tiplpredicted In the time period t dx Then the estimated lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located; based on the fourth lateral offset dyc KapCalculate the expected fourth lateral displacement dyc Kappredicted , wherein the fourth lateral offset dyc Kap represents the lateral distance from the center line of the target vehicle to the front trajectory line of the vehicle based on the current steering, and the estimated fourth lateral offset dyc Kappredicted In the time period t dx Then the estimated lateral distance from the center line of the target vehicle to the front trajectory line of the vehicle; and the estimated third lateral offset dyc Tiplpredicted and the estimated fourth lateral offset dyc Kappredicted Fusion is performed to determine the second lateral offset dyc predicted .
[0045] As a supplement or alternative to the above solution, in the above device, the expected third lateral offset dyc Tiplpredicted Determine according to the following formula:
[0046] dyc Tiplpredicted =dy predicted +dyc Tipl ,
[0047] Among them, dy predicted represents the first lateral offset change, and dyc Tipl represents the third lateral offset;
[0048] The estimated fourth lateral displacement dyc Kappredicted Determine according to the following formula:
[0049] dyc Kappredicted =dy predicted +dyc Kap ,
[0050] Among them, dyc Kap represents the fourth lateral offset; and
[0051] The second lateral offset dyc predicted Determined according to the following formula:
[0052] dyc predicted =dyc Tiplpredicted +(dyc Kappredicted -dyc Tiplpredicted )×K dx ,
[0053] Among them, K dx is a second weighting factor, which is associated with the longitudinal distance dx between the host vehicle and the target vehicle.
[0054] As a supplement or replacement for the above solution, in the above device, the second calculation device is configured to determine the overlap ratio overlap between the target vehicle and the host vehicle according to the following formula: predicted :
[0055] overlap presicted =1-dyc presicted ÷(0.5×(width ego +width obj )),
[0056] Among them, width ego Indicates the width of the vehicle, and width obj Indicates the width of the target vehicle.
[0057] As a supplement or replacement for the above solution, the above device may further include: a third calculation device for continuously accumulating the overlap rate overlap between the target vehicle and the vehicle presicted , calculate the overlap score overlap between the vehicle and the target vehicle score and a determination device for determining an overlap score overlap between the vehicle and the target vehicle score Determine whether the target vehicle has cut into the lane where the host vehicle is located.
[0058] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the medium includes instructions, and the instructions execute the above-mentioned method when executed.
[0059] According to another aspect of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method described above is implemented.
[0060] According to yet another aspect of the present application, an advanced driving assistance system (ADAS) is provided. The advanced driving assistance system (ADAS) includes the control device as described above.
[0061] The inventor of the present application realizes that the control scheme of the existing adaptive cruise control system ACC is heavily dependent on the detection quality of the lane line by the sensor, and the average time for judging the cut-in behavior is relatively long. As customers have higher and higher requirements for the performance of ADAS products, this performance is bound to fail to meet the standards of customers.
[0062] The control scheme of the adaptive cruise control system ACC of the embodiment of the present application designs a set of prediction algorithms based on the motion attributes and position information of the target vehicle to determine whether the target vehicle has a cut-in behavior. Specifically, the control scheme calculates the lateral acceleration ay of the target vehicle through the received first lateral offset dy of the target vehicle and predicts the target vehicle in time period t based on the lateral acceleration ay. dx After the second lateral displacement dyc predicted , and according to the second lateral offset dyc predicted The overlap rate between the target vehicle and the vehicle is calculated to determine whether the target vehicle has cut into the lane where the vehicle is located. Compared with the existing technology, this solution can greatly improve the selection performance of the adaptive cruise control system ACC or ADAS system for the target vehicle cutting in (greatly shorten the recognition time of the cutting-in behavior and improve the recognition accuracy), improve product quality, customer satisfaction and system safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] The above and other objects and advantages of the present application will become more fully apparent from the following detailed description in conjunction with the accompanying drawings, wherein the same or similar elements are represented by the same reference numerals.
[0064] Figure 1 A schematic flow chart of a control method of an adaptive cruise control system ACC according to an embodiment of the present application is shown;
[0065] Figure 2 A schematic diagram showing the structure of a control device of an adaptive cruise control system ACC according to an embodiment of the present application is shown;
[0066] Figure 3 According to one embodiment of the present application, the first weight factor K ay Schematic diagram of the relationship between the lateral acceleration ay of the target vehicle;
[0067] Figure 4 According to an embodiment of the present application, the time period t dx Schematic diagram of the relationship between the variance ObjVarDy of the first lateral offset dy of the target vehicle;
[0068] Figure 5 According to one embodiment of the present application, the second weight factor K dx A schematic diagram of the relationship between and the longitudinal distance dx; and
[0069] Figure 6 A control scenario schematic diagram of an adaptive cruise control system ACC according to an embodiment of the present application is shown. DETAILED DESCRIPTION
[0070] Hereinafter, a control scheme of an adaptive cruise control system ACC according to various exemplary embodiments of the present application will be described in detail with reference to the accompanying drawings.
[0071] Figure 1 FIG. 1 is a flow chart showing a control method 1000 of an adaptive cruise control system ACC according to an embodiment of the present application. Figure 1 As shown, the control method 1000 includes:
[0072] In step S110, a first lateral offset dy of the target vehicle is received;
[0073] In step S120, a lateral acceleration ay of the target vehicle is calculated based on the first lateral offset dy;
[0074] In step S130, the target vehicle is predicted to be in a time period t based on the lateral acceleration ay. dx After the second lateral displacement dyc predicted ;as well as
[0075] In step S140, according to the second lateral offset dyc predicted The overlap rate between the target vehicle and the host vehicle is calculated to determine whether the target vehicle has cut into the lane where the host vehicle is located.
[0076] In the context of this application, the term "adaptive cruise control system ACC" is also referred to as an adaptive cruise control function, which sends instructions to the actuator according to the driving status (e.g., distance and speed) of the target vehicle in front and the vehicle itself, thereby deciding whether to accelerate or decelerate, or exit cruise. In some embodiments, when there is a risk of collision, the adaptive cruise control system ACC will prompt the driver and take active braking intervention. Moreover, when the distance to the vehicle in front is too small, the adaptive cruise control system ACC can appropriately brake the wheels by cooperating with the anti-lock braking system, etc., so as to always maintain a safe distance from the vehicle in front. In general, the adaptive cruise control system ACC can reduce the driver's driving fatigue to a certain extent.
[0077] In step S110, a first lateral offset dy of a target vehicle is received. Here, the term "target vehicle" refers to a vehicle identified or detected by an adaptive cruise control system ACC. The target vehicle may be located in front of the vehicle, including directly in front of the vehicle, in front of the side, etc.
[0078] The term "first lateral offset dy" refers to the lateral offset value of the target vehicle in the coordinate system of the ego vehicle. For example, when the target vehicle is located on the left side of the ego vehicle, the first lateral offset dy is positive, and when the target vehicle is located on the right side of the ego vehicle, the first lateral offset dy is negative. In one embodiment, step S110 includes: receiving the current lateral offset value dy of the target vehicle in the coordinate system of the ego vehicle from the perception module per And the lateral offset value dy of the previous cycle perlast That is, the “first lateral offset dy” is obtained from the perception module and includes the current (periodic) lateral offset value dy per And the lateral offset value dy of the previous cycle perlast .
[0079] In one or more embodiments, the lateral acceleration ay can be calculated based on the second derivative of the first lateral displacement dy of the target vehicle detected by the perception module PER with respect to time. Specifically, in step S120, the lateral acceleration ay of the target vehicle is calculated based on the first lateral displacement dy. In one embodiment, step S120 includes: determining the current lateral velocity vy of the target vehicle current and the lateral velocity vy of the previous cycle last ; and according to the current lateral speed vy current and the lateral velocity vy of the previous cycle last To calculate the lateral acceleration ay.
[0080] For example, the current (periodic) lateral velocity vy current Based on the current lateral offset value dy per And the lateral offset value dy of the previous cycle perlast Determine according to the following equation:
[0081] vy current =(dy per -dy perlast )÷cycletime,
[0082] Among them, dy per is the current lateral offset value, dy perlast It is the lateral offset value of the previous cycle, and cycletime represents the cycle time.
[0083] Similarly, the lateral velocity vy in the previous cycle last Based on the lateral offset value dy of the previous cycle perlast And the lateral offset value of the previous cycle is used to determine.
[0084] In one embodiment, the lateral acceleration ay can be determined according to the following equation:
[0085] ay=(vy current -vy last )÷cycletime.
[0086] In step S130, the target vehicle is predicted to be in a time period t based on the lateral acceleration ay. dx After the second lateral displacement dyc predicted Here, time period t dx Used to indicate the duration to be predicted.
[0087] In one or more embodiments, the time period t dx is associated with the variance of the first lateral offset dy, that is, an adjustable value. dx It can be obtained by linear interpolation based on the variance of the first lateral offset dy.
[0088] Figure 4 According to an embodiment of the present application, the time period t dx Schematic diagram of the relationship between the variance ObjVarDy of the first lateral offset dy of the target vehicle. Figure 4 As shown, when the variance ObjVarDy is less than 40, time period t dx The value can be 1, and as the variance ObjVarDy gradually increases (for example, from 40 to 70), the time period t dx Gradually approaches 0. In other words, if the variance is too large, it means that the perception module is not stable and the quality of the lateral distance detection of the current target is not high. In this case, it is beneficial to try not to make too many predictions on dy at present, which can improve the accuracy of the prediction.
[0089] In one embodiment, step S130 includes: predicting the target vehicle in the time period t based on the lateral acceleration ay dx The first lateral offset change dy predicted ; and based on the first lateral offset change dy predicted Calculate the second lateral offset dyc predicted .
[0090] Wherein, based on the lateral acceleration ay, the target vehicle is predicted to be in the time period t dx The first lateral offset change dy predicted Comprising: determining a first weight factor K according to the lateral acceleration ay ay At least according to the first weight factor K ay Determine the predicted lateral velocity vy of the target vehicle predicted ; and calculating the first lateral offset change dy according to the predicted lateral velocity predicted.
[0091] In one or more embodiments, the first weight factor K ay It can be obtained by linear interpolation of the lateral acceleration ay of the target vehicle. Figure 3 According to one embodiment of the present application, the first weight factor K ay Schematic diagram of the relationship between the lateral acceleration ay of the target vehicle. Figure 3 As shown, when the lateral acceleration ay is less than 5.0, the first weighting factor K ay The value can be 1; however, when the lateral acceleration ay increases further (for example, gradually increases from 5.0 to 10.0), the first weight factor K ay It gradually decreases (e.g., approaches 0.1). Of course, those skilled in the art will understand that Figure 3 The first weight factor K given ay The schematic diagram of the relationship between the lateral acceleration ay of the target vehicle is only an embodiment, and various adjustments or changes can be made as needed, and should not be regarded as limiting the scope of protection of the present application.
[0092] In determining the first weight factor K ay After that, the predicted lateral velocity vy predicted In one embodiment, it can be determined according to the following formula:
[0093] vy predicted =(vy current -vy last )×K ay +vy last ,
[0094] Among them, vy current Indicates the current lateral speed of the target vehicle and vy last Indicates the lateral velocity of the previous cycle.
[0095] Next, the first lateral offset variation dy predicted It can be further determined according to the following formula:
[0096] dy predicted =vy predicted ×t dx ,
[0097] Among them, vy predicted To predict the lateral velocity, t dx The predicted duration.
[0098] In one embodiment, based on the first lateral offset variation dy predicted Calculate the second lateral offset dyc predicted Includes: Based on the third lateral offset dyc TiplCalculate the expected third lateral displacement dyc Tiplpredicted , wherein the third lateral offset dyc Tipl represents the lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located, and the estimated third lateral offset dyc Tiplpredicted In the time period t dx Then the estimated lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located; based on the fourth lateral offset dyc Kap Calculate the expected fourth lateral displacement dyc Kappredicted , wherein the fourth lateral offset dyc Kap represents the lateral distance from the center line of the target vehicle to the front trajectory line of the vehicle based on the current steering, and the estimated fourth lateral offset dyc Kappredicted In the time period t dx Then the estimated lateral distance from the center line of the target vehicle to the front trajectory line of the vehicle; and the estimated third lateral offset dyc Tiplpredicted and the estimated fourth lateral offset dyc Kappredicted Fusion is performed to determine the second lateral offset dyc predicted Here, the first lateral offset change dy predicted (based on the derivation and prediction of the first lateral offset dy) is used to calculate the lateral distance from the center line of the future target vehicle to the front trajectory of the vehicle.
[0099] Figure 6 FIG. 2 shows a control scenario schematic diagram of an adaptive cruise control system ACC according to an embodiment of the present application. Figure 6 As shown, the vehicle 632 is traveling in lane 610, and the target vehicle 634 is traveling in front of the right side of the vehicle 632 and is in another lane 620. Figure 6 The third lateral offset dyc Tipl The fourth lateral offset dyc is represented by the reference numeral 652, which is the lateral distance from the center line 644 of the target vehicle 634 to the center line 642 of the lane where the host vehicle 632 is located. Kap Indicated by reference numeral 654, it is the lateral distance from the center line 644 of the target vehicle 634 to the front trajectory line 646 of the host vehicle 632 based on the current turn.
[0100] In one embodiment, the expected third lateral offset dyc Tiplpredicted Determine according to the following formula:
[0101] dyc Tiplpredicted =dy predicted +dyc Tipl ,
[0102] Among them, dypredicted represents the first lateral offset change, and dyc Tipl Indicates the third lateral offset.
[0103] In one embodiment, the expected fourth lateral offset dyc Kappredicted Determine according to the following formula:
[0104] dyc Kappredicted =dy predicted +dyc Kap ,
[0105] Among them, dyc Kap Indicates the fourth lateral offset.
[0106] In one embodiment, the second lateral offset dyc predicted The estimated third lateral offset dyc is calculated according to the following formula: Tiplpredicted and the estimated fourth lateral displacement dyc Kappredicted To perform the fusion:
[0107] dyc predicted =dyc Tiplpredicted +(dyc Kappredicted -dyc Tiplpredicted )×K dx ,
[0108] Among them, K dx is a second weighting factor, which is associated with the longitudinal distance dx between the host vehicle and the target vehicle.
[0109] Figure 5 According to one embodiment of the present application, the second weight factor K dx Schematic diagram of the relationship between and the longitudinal distance dx. Figure 5 As shown, when the longitudinal distance dx is less than 40.0, the second weight factor K dx The value can be 1; however, when the longitudinal distance dx further increases (for example, gradually increases from 40.0 to 80.0), the longitudinal distance dx gradually decreases (for example, approaches 0). Of course, those skilled in the art can understand that Figure 5 The second weight factor K given dx The schematic diagram of the relationship with the longitudinal distance dx is only an embodiment, and various adjustments or changes can be made as needed, and should not be regarded as limiting the scope of protection of the present application.
[0110] The second lateral displacement dyc is calculated predicted Then, as described in step S140, according to the second lateral offset dyc predictedTo calculate the overlap rate between the target vehicle and the host vehicle, so as to determine whether the target vehicle has cut into the lane where the host vehicle is located. In one embodiment, step S140 includes:
[0111] The overlap ratio between the target vehicle and the vehicle is determined according to the following formula: predicted :
[0112] overlap presicted =1-dyc presicted ÷(0.5×(width ego +width obj )),
[0113] Among them, width ego Indicates the width of the vehicle, and width obj Indicates the width of the target vehicle.
[0114] although Figure 1 As not shown in the figure, the method 1000 may further include: by continuously accumulating the overlap rate overlap between the target vehicle and the vehicle predicted , calculate the overlap score overlap between the vehicle and the target vehicle score ; and according to the overlap score overlap between the vehicle and the target vehicle score Determine whether the target vehicle has cut into the lane where the vehicle is located. In other words, by continuously accumulating the historical overlap rate overlap predicted , that is, to obtain the final overlap score overlap score , and use the overlap score overlap score To determine whether the target vehicle has a tendency to cut into the lane where the vehicle is located.
[0115] In addition, it is easy for a person skilled in the art to understand that the control method 1000 of the adaptive cruise control system ACC provided in the above one or more embodiments of the present application can be implemented by a computer program. For example, the computer program is included in a computer program product, and when the computer program is executed by a processor, the control method 1000 of the adaptive cruise control system ACC of one or more embodiments of the present application is implemented. For another example, when a computer-readable storage medium (such as a USB flash drive) storing the computer program is connected to a computer, the control method 1000 of the adaptive cruise control system ACC of one or more embodiments of the present application can be executed by running the computer program.
[0116] refer to Figure 2 , Figure 2 FIG. 2 shows a schematic diagram of the structure of a control device 2000 of an adaptive cruise control system ACC according to an embodiment of the present application. Figure 2As shown, the control device 2000 includes: a receiving device 210, a first calculating device 220, a predicting device 230 and a second calculating device 240. The receiving device 210 is used to receive a first lateral displacement dy of a target vehicle; the first calculating device 220 is used to calculate a lateral acceleration ay of the target vehicle based on the first lateral displacement dy; the predicting device 230 is used to predict the lateral acceleration ay of the target vehicle in a time period t based on the lateral acceleration ay. dx After the second lateral displacement dyc predicted and a second calculating device 240 for calculating the second lateral offset dyc predicted The overlap rate between the target vehicle and the host vehicle is calculated to determine whether the target vehicle has cut into the lane where the host vehicle is located.
[0117] In one embodiment, the receiving device 210 is configured to receive the current lateral offset value dy of the target vehicle in the coordinate system of the host vehicle from the perception module. per And the lateral offset value dy of the previous cycle perlast .
[0118] In one embodiment, although Figure 2 As not shown in the figure, the first calculation device 220 may include: a first determination unit for determining the current lateral speed vy of the target vehicle current and the lateral velocity vy of the previous cycle last ; and a first calculation unit for calculating the current lateral velocity vy according to the current and the lateral velocity vy of the previous cycle last To calculate the lateral acceleration ay.
[0119] In one embodiment, although Figure 2 As not shown in the figure, the prediction device 230 may include: a second determination unit for predicting the target vehicle in the time period t based on the lateral acceleration ay dx The first lateral offset change dy predicted and a second calculation unit for calculating the value of the first lateral displacement change dy based on the first lateral displacement change dy predicted Calculate the second lateral offset dyc predicted .
[0120] For example, the second determination unit may be configured to: determine the first weighting factor K according to the lateral acceleration ay ay At least according to the first weight factor K ay Determine the predicted lateral velocity vy of the target vehicle predicted ; and calculating the first lateral offset change dy according to the predicted lateral velocity predicted .
[0121] For another example, the second calculation unit may be configured to: based on the third lateral offset dyc Tipl Calculate the expected third lateral displacement dyc Tiplpredicted , wherein the third lateral offset dyc Tip1 represents the lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located, and the estimated third lateral offset dyc Tiplpredicted In the time period t dx Then the estimated lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located; based on the fourth lateral offset dyc Kap Calculate the expected fourth lateral displacement dyc Kappredicted , wherein the fourth lateral offset dyc Kap represents the lateral distance from the center line of the target vehicle to the front trajectory line of the vehicle based on the current steering, and the estimated fourth lateral offset dyc Kappredicted In the time period t dx Then the estimated lateral distance from the center line of the target vehicle to the front trajectory line of the vehicle; and the estimated third lateral offset dyc Tiplpredicted and the estimated fourth lateral offset dyc Kappredicted Fusion is performed to determine the second lateral offset dyc predicted .
[0122] In one embodiment, the second calculation device 240 is configured to determine the overlap ratio overlap between the target vehicle and the host vehicle according to the following formula: predicted :
[0123] overlap presicted =1-dyc predicted ÷(0.5×(width ego +width obj )),
[0124] Among them, width ego Indicates the width of the vehicle, and width obj Indicates the width of the target vehicle.
[0125] In one or more embodiments, the control device 2000 may further include: Figure 2 (not shown): a third calculating device for continuously accumulating the overlap rate overlap between the target vehicle and the vehicle presicted , calculate the overlap score overlap between the vehicle and the target vehicle score and a determination device for determining an overlap score overlap between the vehicle and the target vehicle scoreDetermine whether the target vehicle has cut into the lane where the host vehicle is located.
[0126] The control device 2000 of one or more of the above embodiments can be integrated into various types of automatic driving systems or assisted driving systems, including but not limited to advanced driving assistance systems ADAS. In one or more embodiments, the above control device 2000 is suitable for integration in a vehicle with an advanced driving assistance system ADAS. Here, the "Advanced Driving Assistance System" (ADAS) uses a variety of sensors (millimeter wave radar, lidar, single / binocular cameras and satellite navigation) installed on the vehicle to sense the surrounding environment at any time during the driving process of the car, collect data, identify, detect and track static and dynamic objects, and combine navigation map data to perform systematic calculations and analysis, so as to make the driver aware of possible dangers in advance and effectively increase the comfort and safety of car driving.
[0127] In summary, the control scheme of the adaptive cruise control system ACC of the embodiment of the present application designs a set of prediction algorithms based on the motion attributes and position information of the target vehicle to determine whether the target vehicle has a cut-in behavior. Specifically, the control scheme calculates the lateral acceleration ay of the target vehicle through the received first lateral offset dy of the target vehicle and predicts the target vehicle in time period t based on the lateral acceleration ay. dx After the second lateral displacement dyc predicted , and according to the second lateral offset dyc predicted The overlap rate between the target vehicle and the vehicle is calculated to determine whether the target vehicle has cut into the lane where the vehicle is located. Compared with the existing technology, this solution can greatly improve the selection performance of the adaptive cruise control system ACC or ADAS system for the target vehicle cutting in (greatly shorten the recognition time of the cutting-in behavior and improve the recognition accuracy), improve product quality, customer satisfaction and system safety.
[0128] The above examples mainly illustrate the control scheme of the adaptive cruise control system ACC of the embodiment of the present application. Although only some of the implementation methods of the present application are described, it should be understood by those skilled in the art that the present application can be implemented in many other forms without departing from its subject matter and scope. Therefore, the examples and implementation methods shown are regarded as illustrative rather than restrictive, and the present application may cover various modifications and substitutions without departing from the spirit and scope of the present application as defined in the claims.
Claims
1. A control method for an adaptive cruise control system ACC, characterized in that: The method comprises: Receiving a first lateral offset dy of the target vehicle; Calculating a lateral acceleration ay of the target vehicle based on the first lateral offset dy; Predict the target vehicle in time period t based on the lateral acceleration ay dx After the second lateral displacement dyc predicted ;as well as According to the second lateral offset dyc predicted The overlap rate between the target vehicle and the host vehicle is calculated to determine whether the target vehicle has cut into the lane where the host vehicle is located.
2. The method of claim 1, wherein: Receiving a first lateral offset dy of the target vehicle includes: Receive the current lateral offset value dy of the target vehicle in the coordinate system of the vehicle from the perception module per And the lateral offset value dy of the previous cycle perlast .
3. The method of claim 2, wherein: Calculating the lateral acceleration ay of the target vehicle based on the first lateral offset dy includes: Determine the current lateral velocity vy of the target vehicle current and the lateral velocity vy of the previous cycle last ;as well as According to the current lateral speed vy current and the lateral velocity vy of the previous cycle last To calculate the lateral acceleration ay.
4. The method of claim 1, wherein: The time period t dx is associated with the variance of the first lateral offset dy.
5. The method of claim 1, wherein: Predict the target vehicle in time period t based on the lateral acceleration ay dx After the second lateral displacement dyc predicted include: Predict the target vehicle in the time period t based on the lateral acceleration ay dx The first lateral offset change dy predicted ;as well as Based on the first lateral offset change dy predicted Calculate the second lateral offset dyc predicted .
6. The method of claim 5, wherein: Predict the target vehicle in the time period t based on the lateral acceleration ay dx The first lateral offset change dy predicted include: Determine the first weighting factor K according to the lateral acceleration ay ay ; At least according to the first weight factor K ay Determine the predicted lateral velocity vy of the target vehicle predicted ;as well as Calculate the first lateral offset change dy according to the predicted lateral velocity predicted .
7. The method of claim 6, wherein: The predicted lateral velocity vy predicted Determined according to the following formula: vy predicted =(vy current -vy last )×K ay +vy last , Among them, vy current Indicates the current lateral speed of the target vehicle and vy last represents the lateral velocity of the previous cycle; and The first lateral offset variation dy predicted Determined according to the following formula: dy predicted =vy predicted ×t dx , Among them, vy predicted is the predicted lateral velocity, t dx for the time period.
8. The method of claim 5, wherein: Based on the first lateral offset change dy predicted Calculate the second lateral offset dyc predicted include: Based on the third lateral offset dyc Tipl Calculate the expected third lateral displacement dyc Tiplpredicted , wherein the third lateral offset dyc Tipl represents the lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located, and the estimated third lateral offset dyc Tiplpredicted In the time period t dx Then the estimated lateral distance from the center line of the target vehicle to the center line of the lane where the vehicle is located; Based on the fourth lateral offset dyc Kap Calculate the expected fourth lateral displacement dyc Kappredicted , wherein the fourth lateral offset dyc Kap represents the lateral distance from the center line of the target vehicle to the front trajectory line of the vehicle based on the current steering, and the estimated fourth lateral offset dyc Kappredicted In the time period t dx Then the estimated lateral distance from the center line of the target vehicle to the front trajectory line of the host vehicle; and The estimated third lateral offset dyc Tiplpredicted and the estimated fourth lateral offset dyc Kappredicted Fusion is performed to determine the second lateral offset dyc predicted .
9. The method of claim 8, wherein: The estimated third lateral displacement dyc Tiplpredicted Determine according to the following formula: dyke Tiplpredicted =your predicted + dyke Tipl , Among them, dy predicted represents the first lateral offset change, and dyc Tipl represents the third lateral offset; The estimated fourth lateral displacement dyc Kappredicted Determine according to the following formula: dyke Kappredicted =your predicted + dyke Kap , Among them, dyc Kap represents the fourth lateral offset; and The second lateral offset dyc predicted Determined according to the following formula: dyke predicted =duck Tiplpredicted + (dyk Kappredicted - dyke Tiplpredicted ) × K dx , Among them, K dx is a second weighting factor, which is associated with the longitudinal distance dx between the host vehicle and the target vehicle.
10. The method of claim 1, wherein: According to the second lateral offset dyc predicted Calculating the overlap rate between the target vehicle and the vehicle includes: The overlap ratio between the target vehicle and the vehicle is determined according to the following formula: predicted : overlap presicted =1-dyc predicted ÷(0.5×(width ego +width obj )), Among them, width ego Indicates the width of the vehicle, and width obj Indicates the width of the target vehicle.
11. The method of claim 1 , further comprising: By continuously accumulating the overlap rate between the target vehicle and the vehicle predicted , calculate the overlap score overlap between the vehicle and the target vehicle score ; as well as According to the overlap score overlap between the vehicle and the target vehicle score Determine whether the target vehicle has cut into the lane where the host vehicle is located.
12. A computer-readable storage medium, characterized in that: The medium includes instructions which, when executed, perform the method of any one of claims 1 to 11.
13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.
14. A control device for an adaptive cruise control system ACC, characterized in that: The device comprises: A receiving device, for receiving a first lateral displacement dy of the target vehicle; a first calculation device, configured to calculate a lateral acceleration ay of the target vehicle based on the first lateral offset dy; Prediction device, used for predicting the target vehicle in time period t based on the lateral acceleration ay dx After the second lateral displacement dyc predicted ;as well as a second calculating device for calculating the displacement according to the second lateral displacement dyc predicted The overlap rate between the target vehicle and the host vehicle is calculated to determine whether the target vehicle has cut into the lane where the host vehicle is located.
15. An advanced driver assistance system ADAS, characterized in that: The advanced driver assistance system ADAS includes the control device as claimed in claim 14 .