CN116185030A

CN116185030A - Vehicle control method and device, vehicle and storage medium

Info

Publication number: CN116185030A
Application number: CN202310162304.7A
Authority: CN
Inventors: 杨硕炜
Original assignee: Guangzhou Xiaopeng Autopilot Technology Co Ltd
Current assignee: Guangzhou Xiaopeng Autopilot Technology Co Ltd
Priority date: 2023-02-22
Filing date: 2023-02-22
Publication date: 2023-05-30

Abstract

The application discloses a control method and device of a vehicle, the vehicle and a storage medium, wherein the method comprises the following steps: acquiring a current planning path and a historical planning path; determining adaptive parameters based on the current planned path and the historical planned path, the adaptive parameters characterizing a deviation between the current planned path and the historical planned path; acquiring an actual state quantity; determining a planning control model based on the actual state quantity, the current planning path and the adaptive parameters; and controlling the vehicle longitudinally based on the planning control model. Because the self-adaptive parameters for describing the fluctuation degree of the planned path are added into the planning control model, when the planning control model is optimally solved, the self-adaptive parameters can carry out certain constraint on the determined control quantity, so that the influence of the large fluctuation of the planned path on the control quantity is reduced, the anti-interference capability of a control system of the vehicle on the fluctuation of the planned path is improved, and the longitudinal control of the vehicle is more stable.

Description

Vehicle control method and device, vehicle and storage medium

Technical Field

The present disclosure relates to the field of vehicle control technologies, and in particular, to a vehicle control method and apparatus, a vehicle, and a storage medium.

Background

With the popularization and development of intelligent driving technology, longitudinal tracking control of vehicles is becoming an important research point for research personnel. Specifically, in the case where the upstream motion planning (MotionPlanning, MP) module determines a planned path, the motion control (MotionControl, MC) module in the vehicle determines the control amount of the vehicle based on the planned path given by the MP module to achieve longitudinal tracking control of the vehicle.

In the prior art, the MP module updates the planned path in real time based on the current road condition information of the vehicle. For example, when a side vehicle suddenly changes lanes to drive into a lane of the own vehicle, the MP module may plan a planned path for rapid deceleration; for another example, when the vehicle in front drives away from the lane where the vehicle is located, the MP module may plan a more gentle planned path.

Therefore, once traffic participants such as other vehicles, pedestrians and reverse bikes suddenly appear on the lane, the planned path of the vehicle can greatly fluctuate, and further the control quantity determined by the MC module can also greatly change, so that the vehicle cannot realize stable longitudinal control in the running process.

Disclosure of Invention

The embodiment of the application provides a vehicle control method and device, a vehicle and a storage medium.

In a first aspect, some embodiments of the present application provide a method for controlling a vehicle. The method comprises the following steps: acquiring a current planning path and a historical planning path, wherein the current planning path represents a planning path determined by the vehicle at an actual position, the historical planning path represents a planning path determined by the vehicle at a historical position, and the moment when the vehicle runs to the historical position is earlier than the moment when the vehicle runs to the actual position; determining adaptive parameters based on the current planned path and the historical planned path, the adaptive parameters characterizing a deviation between the current planned path and the historical planned path; acquiring an actual state quantity, wherein the actual state quantity comprises at least one of the following: actual position, actual speed, and actual acceleration of the vehicle; determining a planning control model based on the actual state quantity, the current planning path and the adaptive parameters; and controlling the vehicle longitudinally based on the planning control model.

In a second aspect, some embodiments of the present application further provide a control device for a vehicle. The device comprises a first acquisition module, a first determination module, a second acquisition module, a second determination module and a control module. The first acquisition module is used for acquiring a current planning path and a historical planning path, wherein the current planning path represents a planning path determined by the fact that the vehicle is in an actual position, the historical planning path represents a planning path determined by the fact that the vehicle is in a historical position, and the time when the vehicle runs to the historical position is earlier than the time when the vehicle runs to the actual position. The first determination module is used for determining adaptive parameters based on the current planning path and the historical planning path, wherein the adaptive parameters represent deviation between the current planning path and the historical planning path. The second obtaining module is configured to obtain an actual state quantity, where the actual state quantity includes at least one of: actual position, actual speed and actual acceleration of the vehicle. The second determining module is used for determining a planning control model based on the actual state quantity, the current planning path and the adaptive parameters. The control module is used for longitudinally controlling the vehicle based on the planning control model.

In a third aspect, some embodiments of the present application further provide a vehicle, the vehicle comprising: one or more processors, memory, and one or more applications. Wherein one or more application programs are stored in the memory and configured to be executed by the one or more processors and configured to perform the method described above.

In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium having computer program instructions stored therein. Wherein the computer program instructions are callable by the processor to perform the method as described above.

In a fifth aspect, embodiments of the present application also provide a computer program product that, when executed, implements the above-described method.

The application provides a control method and device of a vehicle, the vehicle and a storage medium, wherein the control method describes the fluctuation degree of a planned path by acquiring deviation between a current planned path and a historical planned path, and further determines self-adaptive parameters based on the deviation. And finally, the vehicle determines a planning control model based on the current planning path, the self-adaptive parameters and the actual state quantity, and realizes longitudinal control of the vehicle based on the planning control model. Because the self-adaptive parameters for describing the fluctuation degree of the planned path are added into the planning control model, when the planning control model is optimally solved, the self-adaptive parameters can carry out certain constraint on the determined control quantity, so that the influence of the large fluctuation of the planned path on the control quantity is reduced, the anti-interference capability of a control system of the vehicle on the fluctuation of the planned path is improved, and the longitudinal control of the vehicle is more stable.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 shows a schematic structural diagram of a vehicle according to an embodiment of the present application.

Fig. 2 shows a flowchart of a control method of a vehicle according to a first embodiment of the present application.

Fig. 3 is a schematic flow chart of a control method of a vehicle according to a second embodiment of the present application.

Fig. 4 is a schematic flow chart of a control method of a vehicle according to a third embodiment of the present application.

Fig. 5 shows a block diagram of a control device of a vehicle according to an embodiment of the present application.

Fig. 6 shows a block diagram of a vehicle according to an embodiment of the present application.

Fig. 7 shows a block diagram of a computer readable storage medium according to an embodiment of the present application.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.

In order to better understand the solution of the present application, the following description will make clear and complete descriptions of the technical solution of the embodiment of the present application with reference to the accompanying drawings in the embodiment of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

For the purpose of facilitating detailed description of the present application, the following description will first describe an application environment in the embodiments of the present application with reference to the accompanying drawings. Referring to fig. 1, the control method of the Vehicle provided in the embodiment of the present application is applied to a Vehicle 100, and the Vehicle 100 refers to a Vehicle driven or towed by a power device for passengers or for transporting articles, which includes, but is not limited to, cars, sport utility vehicles (Suburban Utility Vehicle, SUV), utility vehicles (MPV), and the like. Specifically, vehicle 100 may include a center console 110 and an execution system 120.

The center console 110 is a control center of the vehicle 100, and is used for processing data information acquired by the vehicle 100 during traveling and generating control instructions for controlling the vehicle 100. In this embodiment, the center console 110 may include a planning control module, and the center console 110 may determine, based on the planning control module, a corresponding control amount and send the control amount to the execution system 120 when determining a current actual state quantity (i.e., at least one of an actual position, an actual velocity, and an actual acceleration), a current planned path, and an adaptive parameter. The execution system 120 operates based on the control amount to realize tracking control of the planned path, that is, longitudinal control of the vehicle 100. In some possible embodiments, the planning control module may also be disposed in a server communicatively connected to the vehicle 100, and when the central console 110 needs to determine the control amount, the current actual state amount of the vehicle 100, the current planned path and the adaptive parameters may be sent to the server in real time, and the control amount determined by the server based on the planning control module may be received. The server may be a server, a server cluster formed by a plurality of servers, or a cloud computing service center. In some possible embodiments, the server may be a backend server corresponding to the intelligent driving function in the center console 110. Specifically, the working process of the planning control module and the determining process of the adaptive parameters are described in detail in the following method embodiments.

In this embodiment, the center console 110 further includes a path planning module, which can calculate a planned path based on the obtained actual position of the vehicle and the target destination. The planning path comprises a plurality of planning state quantities, wherein each planning state quantity can comprise information such as planning positions, planning speeds, planning accelerations and the like. Specifically, a path planning algorithm may be provided in the path planning module, where the path planning algorithm may include a search algorithm (for example, dijkstra algorithm, a×algorithm, weighted a×algorithm, etc.), and this embodiment is not limited specifically. Similarly, the path planning module may be disposed in a server communicatively connected to the vehicle 100, and when the central console 110 needs to determine or update the planned path, the central console may send the actual position and the target destination of the vehicle to the server, and receive the planned path determined by the server based on the path planning module.

The execution system 120 is electrically connected to the center console 110, and is capable of operating based on the control amount output from the center console 110 to control the driving state of the vehicle 100. In this embodiment, the execution system 120 may receive the target acceleration control amount determined by the center console 110 based on the planning control model, and adjust the rotational speed of the wheels based on the target acceleration control amount to achieve acceleration or deceleration of the vehicle 100, that is, to achieve longitudinal control of the vehicle 100.

Referring to fig. 2, fig. 2 schematically illustrates a method for controlling a vehicle according to a first embodiment of the present application, and the method may include steps S210 to S250.

Step S210, a current planning path and a historical planning path are obtained.

In this embodiment, the current planned path represents a planned path determined by the vehicle at the actual position, and the history planned path represents a planned path determined by the vehicle at the history position, and the time when the vehicle travels to the history position is earlier than the time when the vehicle travels to the actual position.

As an implementation manner, the center console may acquire an actual position of the vehicle, and determine a current planned path of the vehicle based on a preset path planning algorithm. The current planned path may be a path corresponding to the vehicle traveling from the actual position to the target destination, or may be a path corresponding to the vehicle traveling at the actual position for a preset period of time (e.g., 10 seconds). Specifically, the center console may acquire the actual position of the vehicle based on a global positioning system (Global Positioning System, GPS), and the preset path planning algorithm may be Dijkstra algorithm, a-algorithm, weighted a-algorithm, or the like, which is not limited in this embodiment.

It should be noted that, the current planned path and the historical planned path are both planned paths determined by the vehicle in the current driving process, that is, the center console continuously updates the determined planned paths in the driving process of the vehicle, so that the latest determined planned track is determined as the current planned track, and the previously determined planned track is determined as the historical planned track. Illustratively, the current planned path may be a planned path determined by the central console during the ith round of iteration, and the historical planned path may be a planned path determined by the central console during the ith-1 round of iteration. Specifically, the history planning path may be stored in a memory corresponding to the central console, and the central console may obtain the history planning path by reading data in the memory.

Step S220, determining adaptive parameters based on the current planned path and the historical planned path.

In this embodiment, the adaptive parameter characterizes the deviation between the current planned path and the historical planned path. The current planning path is the planning path determined by the central console in the ith round of iteration process, the historical planning path is the planning path determined by the central console in the ith-1 round of iteration process, and the central console determines the control quantity corresponding to the longitudinal control in each round of iteration process, so that the real-time performance of the control quantity on the vehicle control is ensured, and the time interval between two adjacent rounds of iteration processes is smaller. Illustratively, the time interval may be less than or equal to 100ms. In this case, if the vehicle runs smoothly on the lane, little change occurs between the current planned path and the historical planned path, that is, the deviation of the two is small. If other vehicles suddenly appear in front of the vehicle, for example, the vehicles in the side lanes suddenly change to drive into the lanes corresponding to the vehicles, the center console can determine a current planning path with a rapid deceleration trend, that is, the planning path of the vehicle suddenly changes, and in this case, the deviation between the current planning path and the historical planning path is larger.

The center console will determine the adaptive parameters based on the deviation between the current planned path and the historical planned path. Illustratively, the adaptive parameter may have a positive correlation with the deviation, that is, the larger the deviation is, the larger the value of the adaptive parameter is; conversely, the smaller the deviation, the smaller the value of the adaptive parameter. Specifically, the determination process of the adaptive parameters is explained in detail in the following embodiments.

In step S230, the actual state quantity is acquired.

In the present embodiment, the actual state quantity includes at least one of: actual position, actual speed and actual acceleration of the vehicle. As an embodiment, the center console may acquire one or more of an actual position, an actual speed, and an actual acceleration of the vehicle every a preset time period. The preset time length can be a default value in the center console, and can also be adjusted by a research and development personnel based on the longitudinal control precision of the vehicle. Specifically, the higher the longitudinal control accuracy is, the shorter the preset time period is, so that the number of times of acquiring the actual state quantity is increased, that is, the number of iterations of the longitudinal control is increased.

As an embodiment, the center console may acquire the actual position of the vehicle based on GPS, acquire the actual speed of the vehicle through an in-vehicle speed sensor (e.g., a magneto-electric speed sensor, a hall speed sensor, etc.), and acquire the actual acceleration of the vehicle through an in-vehicle acceleration sensor (e.g., a capacitive acceleration sensor, a strain acceleration sensor, etc.), which is not particularly limited in this embodiment.

Here, it should be noted that, since the current planned path of the vehicle in step S210 is determined based on the actual position of the vehicle. Therefore, step S230 may be performed earlier than step S210, or may be performed simultaneously with step S210.

Step S240, determining a planning control model based on the actual state quantity, the current planning path and the adaptive parameters.

In this embodiment, the planning control model may be an optimization model determined based on the actual state quantity, the current planning path, and the adaptive parameters. Thus, the planning control model relates not only to the current actual state quantities of the vehicle (i.e. the actual displacement, the actual speed and the actual acceleration), but also to the adaptive parameters describing the degree of fluctuation of the planned path. When the subsequent central console performs optimization solution on the planning control model, the self-adaptive parameters can perform certain constraint on the control quantity determined by the central console, so that the influence of larger fluctuation of the planning path on the control quantity is reduced, and the anti-interference capability of the central console is improved. Specifically, the determination process of the planning control model is described in detail in the following embodiments.

Step S250, longitudinal control is performed on the vehicle based on the planned control model.

In this embodiment, the center console may determine a control amount (for example, a target acceleration control amount) corresponding to the longitudinal control based on the planning control model, and send the control amount to an execution system of the vehicle, and the execution system works based on the control amount to implement the longitudinal control of the vehicle. For example, the execution system may receive a target acceleration control amount determined by the center console based on the planning control model, and adjust the rotational speed of the wheels based on the target acceleration control amount to achieve acceleration or deceleration of the vehicle, that is, to achieve longitudinal control of the vehicle.

The embodiment provides a control method of a vehicle, because the self-adaptive parameters for describing the fluctuation degree of a planned path are added in the planning control model, when the planning control model is optimally solved, the self-adaptive parameters can carry out certain constraint on the determined control quantity, so that the influence of larger fluctuation of the planned path on the control quantity is reduced, the anti-interference capability of a control system of the vehicle on the fluctuation of the planned path is improved, and the longitudinal control of the vehicle is more stable.

Referring to fig. 3, fig. 3 schematically illustrates a vehicle control method according to a second embodiment of the present application, in which a process of determining adaptive parameters is specifically described. The current planning path comprises N first planning state quantities, and each first planning state quantity comprises at least one of a first planning position, a first planning speed and a first planning acceleration. The historical planning path includes N second planning state quantities, each of which includes at least one of a second planning position, a second planning speed, and a second planning acceleration. Specifically, the method may include steps S310 to S360.

Step S310, a current planning path and a historical planning path are obtained.

Specifically, the specific implementation of step S310 may refer to the detailed description in step S210, which is not described herein.

Step S320, obtaining a difference between the first planning state quantity and the second planning state quantity.

In this embodiment, the first planning state quantity may include one or more parameters (for example, a first planning position, a first planning speed, a first planning acceleration, etc.), and the number of parameters included in the second planning state quantity is the same as the number of parameters included in the first state planning quantity, and the parameter attributes of the two parameters are the same. For example, in case the first planning state quantity comprises a first planning position and a first planning speed, the second planning state quantity likewise comprises a second planning position and a second planning speed. The center console determines a difference between the first planning state quantity and the second planning state quantity by calculating a difference between the same attribute parameters in the first planning state quantity and the second planning state quantity, and based on the difference.

In some embodiments, the center console may determine a difference between the first and second planning state amounts based on any one of the parameters of the first and second planning state amounts. For example, in case the first planning state quantity comprises a first planning position and the second planning state quantity comprises a second planning position, step S320 may comprise step S3210 and step S3220.

Step S3210 obtains a first difference between the first planned position and the second planned position.

In this embodiment, the current planned path includes N first planned positions, and the historical planned path includes N second planned positions. The center console calculates the distance between each first planning position and the corresponding second planning position, and determines the sum of N distances as a first difference value between the first planning position and the second planning position.

Here, the N first planning positions may be sequentially arranged according to the corresponding moments to form the first sequence. The N second planned positions may be sequentially arranged according to their corresponding moments in order to form a second sequence. Therefore, the "first planned position and its corresponding second planned position" means that when the number of the first planned position in the first sequence is k, the number of the second planned position corresponding to the first planned position in the second sequence is k.

Step S3220, the first difference is determined as a difference between the first planning state quantity and the second planning state quantity.

In this embodiment, the center console determines the first difference value as a difference value between the first planning state quantity and the second planning state quantity.

Here, it should be noted that the above embodiment is merely exemplary, and the center console may also determine the second difference between the first planning speed and the second planning speed as the difference between the first planning state quantity and the second planning state quantity, or determine the third difference between the first planning acceleration and the second planning acceleration as the difference between the first planning state quantity and the second planning state quantity, which is not particularly limited in this embodiment.

In other embodiments, the center console may determine the difference between the first and second planning state amounts based on any two or all three parameters of the first and second planning state amounts. For example, in the case where the first planning state quantity includes a first planning position, a first planning speed, and a first planning acceleration, and the second planning state quantity includes a second planning position, a second planning speed, and a second planning acceleration, step S320 may include steps S3240 and S3270.

Step S3240, a first difference between the first planned position and the second planned position is obtained.

Specifically, the specific implementation of step S3240 may refer to the detailed description in step S3210, which is not described herein.

Step S3250, a second difference between the first planned speed and the second planned speed is obtained.

In this embodiment, the current planned path includes N first planned speeds, and the historical planned path includes N second planned speeds. The center console calculates the speed difference between each first planning speed and the corresponding second planning speed, and determines the sum of N speed differences as the second difference between the first planning speed and the second planning speed.

Here, the N first planning speeds may be sequentially arranged according to their corresponding moments to form the third sequence. The N second planning speeds may be sequentially arranged according to their corresponding moments in order to form a fourth sequence. Therefore, the "first planning speed and the corresponding second planning speed" means that when the number of the first planning speed in the third sequence is k, the number of the corresponding second planning speed in the fourth sequence is k.

Step S3260, a third difference between the first planned acceleration and the second planned acceleration is obtained.

In this embodiment, the current planned path includes N first planned accelerations, and the historical planned path includes N second planned accelerations. The center console calculates the acceleration difference between each first planning acceleration and the corresponding second planning acceleration, and determines the sum of N acceleration differences as a third difference between the first planning speed and the second planning speed.

Here, the N first planned accelerations may be sequentially arranged according to their corresponding moments to form a fifth sequence. The N second planned accelerations may be sequentially arranged in order according to their corresponding moments to form a sixth sequence. Therefore, the "first planned acceleration and the corresponding second planned acceleration" means that, when the number of the first planned acceleration in the fifth sequence is k, the number of the corresponding second planned acceleration in the sixth sequence is k.

Step S3270, determining the sum of the first difference, the second difference and the third difference as the difference between the first planning state quantity and the second planning state quantity.

In this embodiment, the center console determines the sum of the first difference value, the second difference value, and the third difference value as a difference value between the first planning state quantity and the second planning state quantity.

Here, the above-described embodiment is merely exemplary, and the center console may determine the sum of any two of the first difference value, the second difference value, and the third difference value as the difference value between the first planning state quantity and the second planning state quantity. For example, a sum of the first difference and the second difference is determined as a difference between the first planning state quantity and the second planning state quantity; or determining the sum of the second difference value and the third difference value as the difference value between the first planning state quantity and the second planning state quantity; the sum of the first difference and the third difference is determined as the difference between the first planning state quantity and the second planning state quantity, which is not particularly limited in this embodiment.

In some possible embodiments, step S320 further comprises step S3200, prior to step S3210 and step S3240.

In step S3200, idle computing resources of the vehicle are acquired.

In this embodiment, the free computing resources may refer to the available memory space in the processor. The central console can acquire idle computing resources of the vehicle by acquiring current working parameters of the processor.

In the subsequent step, the center console performs steps S3240 to S3270 in the case where the idle computing resource is greater than or equal to the specified value. That is, under the condition that the idle computing resources are sufficient, the center console comprehensively considers a plurality of items in the first difference value, the second difference value and the third difference value, so that the difference value between the determined first planning state quantity and the determined second planning state quantity can more accurately reflect the deviation of the planning path, and therefore, the adaptive parameters determined subsequently can be more reasonable. Otherwise, if the idle computing resource is smaller than the specified value, the center console performs steps S3210 to S3220. Specifically, the specified value may be a default value in the center console, or may be adjusted by a developer based on the actual running situation of the vehicle, which is not particularly limited in this embodiment.

Step S330, determining an adaptive parameter based on a difference between the first planning state quantity and the second planning state quantity.

In this embodiment, the adaptive parameter and the difference value have a positive correlation, that is, the larger the difference value between the first planning state quantity and the second planning state quantity is, the larger the adaptive parameter is; conversely, the smaller the difference between the first and second planning state amounts, the smaller the adaptive parameter.

As an embodiment, the central console may have a mapping relationship between the difference between the first planning state quantity and the second planning state quantity and the adaptive parameter stored in advance, and the mapping relationship may be summarized by a developer based on a large amount of experimental data. And under the condition that the central console determines the difference value between the first planning state quantity and the second planning state quantity, the self-adaptive parameter can be determined based on the mapping relation. Specifically, the mapping relationship may be embodied by a mapping table or a mapping function, which is not specifically limited in this embodiment.

In step S340, the actual state quantity is acquired.

Specifically, the specific implementation of step S340 may refer to the detailed description in step S230, which is not described herein.

Step S350, determining a planning control model based on the actual state quantity, the current planning path and the adaptive parameters.

Step S360, longitudinal control is performed on the vehicle based on the planned control model.

The specific implementation of step S350 and step S360 is explained in detail in the following embodiments.

The present embodiment provides a control method of a vehicle, and in the present embodiment, a determination process of adaptive parameters is described in detail. Because the self-adaptive parameters for describing the fluctuation degree of the planned path are added into the planning control model, when the planning control model is optimally solved, the self-adaptive parameters can carry out certain constraint on the determined control quantity, so that the influence of the large fluctuation of the planned path on the control quantity is reduced, the anti-interference capability of a control system of the vehicle on the fluctuation of the planned path is improved, and the longitudinal control of the vehicle is more stable.

Referring to fig. 4, fig. 4 schematically illustrates a control method of a vehicle according to a third embodiment of the present application, in which a planning control model and a longitudinal control process of the vehicle are described in detail. The current planning path comprises N first planning state quantities and N corresponding planning acceleration control quantities, N predicted accelerations included in the control sequence are sequentially arranged according to corresponding moments, and the planning control model is characterized by a cost function. Specifically, the method may include steps S410 to S490.

Step S410, a current planned path and a historical planned path are obtained.

Step S420, determining adaptive parameters based on the current planned path and the historical planned path.

In step S430, the actual state quantity is acquired.

Specifically, the specific implementation manner of step S410 to step S430 may refer to the detailed descriptions in step S210 to step S230, and will not be described in detail herein.

In step S440, a control sequence is acquired.

The control sequence includes N predicted acceleration control amounts. The N predicted acceleration control amounts represent the acceleration control amounts predicted by the center console after the vehicle runs at different moments under the current position. Specifically, the N predicted acceleration control amounts are sequentially arranged in order according to their corresponding timings. As an embodiment, the center console may determine a default value as an initial value of the control sequence. The central console may also use the control sequence determined in the historical iteration process as the control sequence in the present round of iteration process, and the determination mode of the control sequence in this embodiment is not specifically limited.

In step S450, N-1 predicted state quantities are determined based on the control sequence and the actual state quantities.

In this embodiment, the center console may determine N-1 predicted state amounts based on a preset vehicle dynamics model. The vehicle dynamics model may be stored in the center console in advance, and specifically, the vehicle dynamics model is shown below.

x _k+1 ＝Ax _k +Bu _k +c。

Wherein x is _k Represents the kth predicted state quantity, x when k is equal to 1 ₁ The actual state quantity is obtained for the central console. In particular, the method comprises the steps of,

where s represents the kth predicted position and v represents the kth predictionSpeed, a, represents the kth predicted acceleration. When k is equal to 1, s is the actual position, v is the actual speed, and a is the actual acceleration. u (u) _k The kth predicted acceleration control amount, that is, the input amount is represented. X is x _k+1 Represents the k+1th predicted state quantity. A and B are respectively a state matrix and an input matrix with known parameters, c is a disturbance matrix used for representing the interference of external noise on the predicted state quantity, and the disturbance matrix c can be measured.

Here, the determination of the predicted state quantity will be described with the value of N being 3. At this time, 3 predicted acceleration control amounts, i.e., u, are included in the control sequence ₁ ，u ₂ And u ₃ . Due to x ₁ Is a known quantity, i.e. the actual state quantity, and therefore the central console needs to determine 2 predicted state quantities (x ₂ And x ₃ ) This can be expressed by the following formula.

x ₂ ＝Ax ₁ +Bu ₁ +c；

x ₃ ＝Ax ₂ +Bu ₂ +c＝A(Ax ₁ +Bu ₁ +c)+Bu ₂ +c。

Thus, at x ₁ Where each of A, B and c is known, 2 predicted state quantities (x ₂ And x ₃ ) The representation may be by a control sequence.

Step S460, a planning control model is determined based on the actual state quantity, the N-1 predicted state quantities, the N first planning state quantities, the N planning acceleration control quantities, the control sequence and the adaptive parameters.

In this embodiment, the planning control model is represented by a cost function. Specifically, step S460 may include steps S4610 to S4660.

In step S4610, a first plan item is determined based on the actual state quantity, the N-1 predicted state quantities, and the N first plan state quantities.

As an embodiment, the central console may first determine the actual state quantity and the first errors between the N-1 predicted state quantities and the corresponding N first planned state quantities. And determining a product between the first error and the first scale factor as a first programming term. Specifically, the calculation formula corresponding to the first plan term is as follows.

Wherein J is ₁ For the first programming term, ref _k For the kth first planning state quantity, x when k is equal to 1 _k Is the actual state quantity; when k is greater than 1, x _k Is the kth predicted state quantity. That is, ref _k -x _k Is the first error between the actual state quantity and the N-1 predicted state quantities and the corresponding N first planned state quantities. Q is a first scale factor, wherein Q can be characterized in a matrix form, and the values of Q are all larger than 0, namely positive correlation is formed between the first planning term and the first error. Specifically, Q may be a default parameter, or may be adjusted by a developer based on the actual driving situation of the vehicle.

Step S4620, determining a second programming item based on the N programming acceleration control amounts and the control sequence.

As an embodiment, the center console may first determine a second error between the N planned acceleration control amounts and the corresponding N predicted acceleration control amounts in the control sequence. And determining a product between the second error and the second scaling factor as a second programming term. Specifically, the calculation formula corresponding to the second planning term is as follows.

Wherein J is ₂ For the second planning term, u _r To plan the acceleration control quantity, u _k The acceleration control amount is predicted for the kth. That is, u _r -u _k And a second error between the N planned acceleration control amounts and the corresponding N predicted acceleration control amounts in the control sequence. R is a second scale factor, wherein R can be characterized in a matrix form, and the values of R are all larger than 0, namely, positive correlation is formed between the second planning term and the second error. Specifically, R may be a default parameter, alsoThe adjustment may be made by the developer based on the actual driving situation of the vehicle.

Step S4630, determining a third programming term based on the difference between the predicted accelerations adjacent at any two times in the control sequence.

As an embodiment, the center console may determine, as the third planning term, a product between a difference between the predicted accelerations adjacent to any two times in the control sequence and the second scaling factor. Specifically, the calculation formula corresponding to the third plan term is as follows.

Wherein J is ₃ For the third planning term, deltau _k For controlling the difference between adjacent predicted accelerations at any two moments in the sequence, i.e. Deltau _k ＝u _k+1 -u _k . R is a second scale factor, wherein R can be characterized by a matrix form, and the values of R are all larger than 0, namely, the third programming term and Deltau _k The two are positively correlated.

Step S4640, determining the actual state quantity and the ratio between the N-1 predicted state quantities and the adaptive parameters as a fourth planning term.

Specifically, a calculation formula corresponding to the fourth plan term is shown below.

/>

Wherein J is ₄ For the fourth programming term, γ is the adaptive parameter, x when k equals 1 _k Is the actual state quantity; when k is greater than 1, x _k Is the kth predicted state quantity.

In step S4650, the product of the difference between the actual state quantity and the state quantity adjacent to any two times of the N-1 predicted state quantities and the adaptive parameter is determined as the fifth planning term.

Specifically, the calculation formula corresponding to the fifth plan term is as follows.

J ₅ ＝γd ^T d。

Wherein J is ₅ For the fifth programming term, γ is the adaptive parameter, d is the difference between the actual state quantity and the state quantity adjacent to any two times of the N-1 predicted state quantities, i.e., d=x _k+1 -x _k 。

Step S4660 determines a sum of the first plan term, the second plan term, the third plan term, the fourth plan term, and the fifth plan term as a plan control model.

In this embodiment, the planning control model is characterized by a cost function. And the center console determines the sum of the first planning item, the second planning item, the third planning item, the fourth planning item and the fifth planning item as a cost function under the condition that the first planning item, the second planning item, the third planning item, the fourth planning item and the fifth planning item are determined. Specifically, a calculation formula corresponding to the cost function is as follows.

s.t.x _k+1 ＝Ax _k +Bu _k +c，

x _lb ≤x _k ≤x _ub ，u _lb ≤u _k ≤u _ub ，Δu _lb ≤Δu _k ≤Δu _ub ，0≤γ≤γ _ub 。

Wherein J represents a cost function value corresponding to the cost function, x _lb And x _ub Respectively x _k Lower and upper values of u _lb And u _ub U respectively _k Lower and upper values of Deltau, deltau _lb And Deltau _ub Respectively Deltau _l Lower and upper values of 0 and gamma _ub The lower value and the upper value of gamma are respectively the lower value and the upper value of gamma.

And step S470, optimizing and solving the control sequence and the self-adaptive parameters in the planning control model, and determining the target control sequence and the target self-adaptive parameters.

In this embodiment, the central console may perform optimization solution on the control sequence based on a preset iterative optimization algorithm, so as to determine the target control sequence and the target adaptive parameter. Specifically, the iterative optimization algorithm may be newton method, gradient descent algorithm, or the like, which is not particularly limited in this embodiment.

In step S480, when the target adaptive parameter is less than or equal to the first preset value and the cost function value corresponding to the cost function is less than or equal to the second preset value, the first value in the target control sequence is determined as the target acceleration control amount.

In this embodiment, the center console determines the first value in the target control sequence as the target acceleration control amount when the target adaptive parameter is less than or equal to the first preset value and the cost function value corresponding to the cost function is less than or equal to the second preset value. The first preset value and the second preset value may be default values in the center console, or may be adjusted by a developer based on the optimization accuracy of the control sequence, specifically, the higher the optimization accuracy of the control sequence is, the smaller the first preset value and the second preset value are, which is not limited in this embodiment.

Otherwise, if the target adaptive parameter is greater than the first preset value or the cost function value corresponding to the cost function is greater than the second preset value, the center console repeatedly executes step S470.

In step S490, the vehicle is longitudinally controlled based on the target acceleration control amount.

In this embodiment, the center console may transmit the target acceleration control amount to the execution system of the vehicle, and the execution system operates based on the target acceleration control amount to realize longitudinal control of the vehicle.

The present embodiment provides a control method of a vehicle, in which a planning control model and a longitudinal control process of the vehicle are described in detail. Because the self-adaptive parameters for describing the fluctuation degree of the planned path are added into the planning control model, when the planning control model is optimally solved, the self-adaptive parameters can carry out certain constraint on the determined control quantity, so that the influence of the large fluctuation of the planned path on the control quantity is reduced, the anti-interference capability of a control system of the vehicle on the fluctuation of the planned path is improved, and the longitudinal control of the vehicle is more stable.

Referring to fig. 5, fig. 5 schematically illustrates a control device 500 for a vehicle according to an embodiment of the present application. The control device 500 of the vehicle includes a first acquisition module 510, a first determination module 520, a second acquisition module 530, a second determination module 540, and a control module 550. The first obtaining module 510 is configured to obtain a current planned path and a historical planned path, where the current planned path represents a planned path determined by the vehicle at an actual position, and the historical planned path represents a planned path determined by the vehicle at a historical position, and a time when the vehicle travels to the historical position is earlier than a time when the vehicle travels to the actual position. The first determining module 520 is configured to determine an adaptive parameter based on the current planned path and the historical planned path, the adaptive parameter characterizing a deviation between the current planned path and the historical planned path. The second obtaining module 530 is configured to obtain an actual state quantity, where the actual state quantity includes at least one of the following: actual position, actual speed and actual acceleration of the vehicle. The second determining module 540 is configured to determine a planning control model based on the actual state quantity, the current planning path, and the adaptive parameter. The control module 550 is configured to control the vehicle longitudinally based on the planned control model.

In some embodiments, the current planned path includes N first planned state amounts and the historical planned path includes N second planned state amounts. The first determining module 520 is further configured to obtain a difference between the first planning state quantity and the second planning state quantity; determining an adaptive parameter based on a difference between the first and second planning state quantities; wherein the adaptive parameter and the difference value are in positive correlation.

In some embodiments, each first programmed state quantity includes a first programmed position, a first programmed speed, a first programmed acceleration; each second planning state quantity includes a second planning position, a second planning speed, and a second planning acceleration. The first determining module 520 is further configured to obtain a first difference between the first planned position and the second planned position; acquiring a second difference between the first planning speed and the second planning speed; acquiring a third difference between the first planned acceleration and the second planned acceleration; and determining the sum of the first difference value, the second difference value and the third difference value as a difference value between the first planning state quantity and the second planning state quantity.

In some embodiments, the current planned path includes N first planned state amounts and corresponding N planned acceleration control amounts. The second determining module 540 is further configured to obtain a control sequence, where the control sequence includes N predicted acceleration control amounts; determining N-1 predicted state quantities based on the control sequence and the actual state quantities; a planning control model is determined based on the actual state quantity, the N-1 predicted state quantities, the N first planning state quantities, the N planning acceleration control quantities, the control sequence, and the adaptive parameters.

In some embodiments, the second determining module 540 is further configured to determine the first planning term based on the actual state quantity, the N-1 predicted state quantities, and the N first planning state quantities; determining a second planning term based on the N planning acceleration control amounts and the control sequences; determining a third planning term based on the difference between the predicted accelerations adjacent to any two moments in the control sequence; determining the ratio between the actual state quantity and N-1 predicted state quantities and the adaptive parameters as a fourth planning term; determining the product of the difference between the actual state quantity and the state quantity adjacent to any two moments in the N-1 predicted state quantities and the adaptive parameter as a fifth planning term; and determining the sum of the first planning item, the second planning item, the third planning item, the fourth planning item and the fifth planning item as a planning control model.

In some embodiments, the second determining module 540 is further configured to determine the actual state quantity and a first error between the N-1 predicted state quantities and the corresponding N first planned state quantities; determining a product between the first error and the first scale factor as a first plan term; determining a second error between the N planned acceleration control amounts and the corresponding N predicted acceleration control amounts in the control sequence; determining a product between the second error and the second scaling factor as a second planning term; and determining the product between the difference between the predicted accelerations adjacent to any two moments in the control sequence and the second scaling factor as a third programming term.

In some embodiments, the N predicted accelerations included in the control sequence are sequentially arranged according to the corresponding moments, the planning control model is characterized by a cost function, and the control module 550 is further configured to perform optimization solution on the control sequence and the adaptive parameters in the planning control model, and determine a target control sequence and a target adaptive parameter; determining a first value in a target control sequence as a target acceleration control amount under the condition that the target adaptive parameter is smaller than or equal to a first preset value and the cost function value corresponding to the cost function is smaller than or equal to a second preset value; the vehicle is longitudinally controlled based on the target acceleration control amount.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus and modules described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.

In several embodiments provided herein, the coupling of the modules to each other may be electrical, mechanical, or other.

In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules.

The present embodiment provides a control device of a vehicle, which describes a planned path fluctuation degree by acquiring a deviation between a current planned path and a historical planned path, and further determines an adaptive parameter based on the deviation. And finally, the vehicle determines a planning control model based on the current planning path, the self-adaptive parameters and the actual state quantity, and realizes longitudinal control of the vehicle based on the planning control model. Because the self-adaptive parameters for describing the fluctuation degree of the planned path are added into the planning control model, when the planning control model is optimally solved, the self-adaptive parameters can carry out certain constraint on the determined control quantity, so that the influence of the large fluctuation of the planned path on the control quantity is reduced, the anti-interference capability of a control system of the vehicle on the fluctuation of the planned path is improved, and the longitudinal control of the vehicle is more stable.

Referring to fig. 6, fig. 6 schematically illustrates that the embodiment of the present application further provides a vehicle 600, the vehicle 600 comprising: one or more processors 610, memory 620, and one or more applications. Wherein one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more application programs configured to perform the methods described in the above embodiments.

Processor 610 may include one or more processing cores. The processor 610 connects various parts within the overall battery management system using various interfaces and lines, performs various functions of the battery management system and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 620, and invoking data stored in the memory 620. Alternatively, the processor 610 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 610 may integrate one or a combination of several of a central processor 610 (Central Processing Unit, CPU), an image processor 610 (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 610 and may be implemented solely by a single communication chip.

The Memory 620 may include a random access Memory 620 (Random Access Memory, RAM) or a Read-Only Memory 620 (ROM). Memory 620 may be used to store instructions, programs, code sets, or instruction sets. The memory 620 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like. The storage data area may also store data created by the electronic device map in use (e.g., phonebook, audiovisual data, chat log data), and the like.

Referring to fig. 7, fig. 7 schematically illustrates that the present embodiment further provides a computer readable storage medium 700, where the computer readable storage medium 700 stores computer program instructions 710, and the computer program instructions 710 may be invoked by a processor to perform the method described in the above embodiment.

The computer readable storage medium 700 may be, for example, a flash Memory, an Electrically Erasable Programmable Read Only Memory (EEPROM), an electrically programmable Read Only Memory (Electrical Programmable Read Only Memory, EPROM), a hard disk, or a Read-Only Memory (ROM). Optionally, the computer readable storage medium comprises a Non-volatile computer readable storage medium (Non-transitory Computer-readable Storage Medium). The computer readable storage medium 700 has storage space for computer program instructions 710 that perform any of the method steps described above. The computer program instructions 710 may be read from or written to one or more computer program products.

The foregoing description is not intended to limit the preferred embodiments of the present application, but is not intended to limit the scope of the present application, and any such modifications, equivalents and adaptations of the embodiments described above in accordance with the principles of the present application should and are intended to be within the scope of the present application, as long as they do not depart from the scope of the present application.

Claims

1. A control method of a vehicle, characterized by comprising:

acquiring a current planning path and a historical planning path, wherein the current planning path represents a planning path determined by a vehicle at an actual position, the historical planning path represents a planning path determined by the vehicle at a historical position, and the moment when the vehicle runs to the historical position is earlier than the moment when the vehicle runs to the actual position;

determining an adaptive parameter based on the current planned path and the historical planned path, the adaptive parameter characterizing a deviation between the current planned path and the historical planned path;

Acquiring an actual state quantity, wherein the actual state quantity comprises at least one of the following: the actual position, the actual speed and the actual acceleration of the vehicle;

determining a planning control model based on the actual state quantity, the current planning path and the adaptive parameter;

and controlling the vehicle longitudinally based on the planning control model.

2. The method of claim 1, wherein the current planned path includes N first planned state amounts and the historical planned path includes N second planned state amounts; the determining adaptive parameters based on the current planned path and the historical planned path includes:

acquiring a difference value between the first planning state quantity and the second planning state quantity;

determining the adaptive parameter based on a difference between the first and second planning state quantities; wherein the adaptive parameter and the difference value are in positive correlation.

3. The method of claim 2, wherein each of the first programmed state quantities includes a first programmed position, a first programmed speed, a first programmed acceleration; each of the second planning state quantities includes a second planning position, a second planning speed, and a second planning acceleration, and the obtaining the difference between the first planning state quantity and the second planning state quantity includes:

Acquiring a first difference between the first planning position and the second planning position;

acquiring a second difference between the first planning speed and the second planning speed;

acquiring a third difference between the first planned acceleration and the second planned acceleration;

and determining the sum of the first difference value, the second difference value and the third difference value as a difference value between the first planning state quantity and the second planning state quantity.

4. A method according to any one of claims 1 to 3, wherein the current planned path comprises N first planned state amounts and corresponding N planned acceleration control amounts; the determining a planning control model based on the actual state quantity, the current planning path and the adaptive parameter includes:

acquiring a control sequence, wherein the control sequence comprises N predicted acceleration control amounts;

determining N-1 predicted state quantities based on the control sequence and the actual state quantities;

and determining the planning control model based on the actual state quantity, N-1 predicted state quantities, N first planning state quantities, N planning acceleration control quantities, the control sequence and the adaptive parameters.

5. The method of claim 4, wherein the determining the planning control model based on the actual state quantity, N-1 of the predicted state quantities, N of the first planning state quantities, N of the planning acceleration control quantities, the control sequence, and the adaptive parameter comprises:

determining a first planning term based on the actual state quantity, N-1 predicted state quantities and N first planning state quantities;

determining a second planning term based on the N planned acceleration control amounts and the control sequence;

determining a third planning term based on the difference between the predicted accelerations adjacent to any two moments in the control sequence;

determining the actual state quantity and the ratio between N-1 predicted state quantities and the adaptive parameters as a fourth planning item;

determining the product of the difference between the actual state quantity and the state quantity adjacent to any two moments in the N-1 predicted state quantities and the adaptive parameter as a fifth planning term;

and determining the sum of the first planning item, the second planning item, the third planning item, the fourth planning item and the fifth planning item as the planning control model.

6. The method of claim 5, wherein the determining a first plan term based on the actual state quantity, N-1 of the predicted state quantities, and N of the first plan state quantities comprises:

determining first errors between the actual state quantity and N-1 predicted state quantities and corresponding N first planning state quantities;

determining a product between the first error and a first scale factor as the first plan term;

said determining a second programming term based on said N programming acceleration control amounts and said control sequence, comprising:

determining second errors between the N planned acceleration control amounts and the N predicted acceleration control amounts corresponding to the control sequence;

determining a product between the second error and a second scaling factor as the second plan term;

the determining a third planning term based on the difference between the predicted accelerations adjacent to any two moments in the control sequence includes:

and determining the product of the difference between the predicted accelerations adjacent to any two moments in the control sequence and the second scale factor as the third planning term.

7. The method of claim 4, wherein the control sequence includes N predicted accelerations sequentially ordered in their corresponding moments, the planning control model is characterized by a cost function, and the longitudinally controlling the vehicle based on the planning control model comprises:

Carrying out optimization solution on the control sequence and the self-adaptive parameters in the planning control model, and determining a target control sequence and target self-adaptive parameters;

determining a first value in the target control sequence as a target acceleration control amount under the condition that the target adaptive parameter is smaller than or equal to a first preset value and the cost function value corresponding to the cost function is smaller than or equal to a second preset value;

and controlling the vehicle longitudinally based on the target acceleration control amount.

8. A control device of a vehicle, characterized by comprising:

the vehicle comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a current planning path and a historical planning path, the current planning path represents a planning path determined by a vehicle in an actual position, the historical planning path represents a planning path determined by the vehicle in a historical position, and the moment when the vehicle runs to the historical position is earlier than the moment when the vehicle runs to the actual position;

a first determining module configured to determine an adaptive parameter based on the current planned path and the historical planned path, the adaptive parameter characterizing a deviation between the current planned path and the historical planned path;

The second acquisition module is used for acquiring the actual state quantity, and the actual state quantity comprises at least one of the following: the actual position, the actual speed and the actual acceleration of the vehicle;

the second determining module is used for determining a planning control model based on the actual state quantity, the current planning path and the self-adaptive parameter;

and the control module is used for longitudinally controlling the vehicle based on the planning control model.

9. A vehicle, characterized by comprising:

one or more processors;

a memory;

one or more applications, wherein one or more of the applications are stored in the memory and configured to be executed by one or more of the processors and configured to perform the method of any of claims 1-7.

10. A computer readable storage medium having stored therein computer program instructions which are callable by a processor to perform the method according to any one of claims 1-7.