Vehicle control method and device, vehicle and storage medium
By using the model predictive control (MPC) method in vehicle control, the amount of control of the vehicle is optimized, and the problem of poor vehicle running stability is solved, and the comfort and safety of rides are improved.
Patent Information
- Application Number
- CN202411367623.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-27
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-27
AI Technical Summary
The existing vehicle control methods lead to poor vehicle running stability and lower vehicle comfort and safety.
Based on the real state quantity and expected state quantity of the vehicle, a cost function is constructed. Through the model predictive control (MPC) method, the control quantity is optimized to ensure the smooth operation of the vehicle under constraints, including the change in speed and parameters.
Through the MPC method, the vehicle control volume is optimized, the rush speed is prevented, the vehicle's smooth operation is improved, and the ride comfort and safety is enhanced.
Smart Images

Figure CN119078841A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of vehicle technology, and in particular to a vehicle control method, a vehicle control device, a vehicle, and a storage medium. Background Art
[0002] At present, most of the vehicle control is based on PID (Proportional-Integral-Derivative) and other control algorithms. For example, in a braking scene, the vehicle will continue to decelerate until the final speed drops to zero and remains stationary. The actual speed of the vehicle can be controlled to follow the expected speed curve. However, the vehicle control method in the related art has poor stability in vehicle operation, resulting in low riding comfort and safety. Summary of the invention
[0003] The present disclosure provides a vehicle control method, device, vehicle, server, and computer-readable storage medium to at least solve the problem that the vehicle control method in the related art has poor vehicle running stability, resulting in low riding comfort and safety. The technical solution of the present disclosure is as follows:
[0004] According to a first aspect of an embodiment of the present disclosure, a vehicle control method is provided, comprising: obtaining a predicted state quantity sequence of the vehicle in a first time period based on the actual state quantity of the vehicle at a current moment, wherein each type of state quantity includes a speed and a first parameter of the vehicle; constructing a cost function of the vehicle based on the predicted state quantity sequence and an expected state quantity sequence of the vehicle in the first time period, wherein the independent variables of the cost function include a control quantity sequence of the vehicle in a second time period, and the control quantity of the vehicle includes a change in the first parameter; solving the cost function under the constraint of the control quantity to obtain the control quantity of the vehicle at the current moment, and controlling the vehicle based on the control quantity of the vehicle at the current moment.
[0005] According to a second aspect of an embodiment of the present disclosure, a vehicle control device is provided, comprising: an acquisition module, configured to obtain a predicted state quantity sequence of the vehicle in a first time period based on the actual state quantity of the vehicle at a current moment, wherein each type of state quantity includes a speed and a first parameter of the vehicle; a construction module, configured to construct a cost function of the vehicle based on the predicted state quantity sequence and an expected state quantity sequence of the vehicle in the first time period, wherein the independent variable of the cost function includes a control quantity sequence of the vehicle in a second time period, and the control quantity of the vehicle includes a change in the first parameter; a control module, configured to solve the cost function under the constraint of the control quantity, obtain the control quantity of the vehicle at the current moment, and control the vehicle based on the control quantity of the vehicle at the current moment.
[0006] According to a third aspect of an embodiment of the present disclosure, a vehicle is provided, comprising a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the steps of the method described in the first aspect of the embodiment of the present disclosure.
[0007] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the method described in the first aspect of the embodiment of the present disclosure are implemented.
[0008] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects: vehicle control can be implemented based on MPC, with the vehicle speed and the first parameter both used as state quantities, the change in the first parameter used as the control quantity, and the vehicle control quantity can be solved under the constraints of the control quantity (including the constraints of the change in the first parameter), thereby ensuring that the vehicle control quantity satisfies the constraints of the control quantity, preventing excessive jerkiness during driving, ensuring smooth operation of the vehicle, and improving ride comfort and safety.
[0009] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.
[0011] Figure 1 The figure is a flow chart of a method for controlling a vehicle according to an exemplary embodiment.
[0012] Figure 2 is a flowchart of a method for controlling a vehicle according to another exemplary embodiment.
[0013] Figure 3 is a flowchart of a method for controlling a vehicle according to another exemplary embodiment.
[0014] Figure 4 is a flowchart of a method for controlling a vehicle according to another exemplary embodiment.
[0015] Figure 5 is a schematic diagram showing an expected speed curve according to an exemplary embodiment.
[0016] Figure 6 It is a schematic diagram showing a method for controlling a vehicle according to an exemplary embodiment.
[0017] Figure 7 is a block diagram of a vehicle control device according to an exemplary embodiment.
[0018] Figure 8 is a block diagram of a vehicle according to an exemplary embodiment. DETAILED DESCRIPTION
[0019] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.
[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.
[0021] Figure 1 is a flow chart of a vehicle control method according to an exemplary embodiment. Figure 1 As shown, the vehicle control method of the embodiment of the present disclosure includes the following steps.
[0022] S101, based on the actual state quantity of the vehicle at the current moment, obtain a predicted state quantity sequence of the vehicle in a first time period, wherein each type of state quantity includes a speed and a first parameter of the vehicle.
[0023] It should be noted that the executor of the vehicle control method of the embodiment of the present disclosure is an electronic device, such as a vehicle-mounted terminal, a vehicle-mounted controller, etc. The vehicle control method of the embodiment of the present disclosure can be executed by the control device of the vehicle of the embodiment of the present disclosure, and the control device of the vehicle of the embodiment of the present disclosure can be configured in any electronic device to execute the vehicle control method of the embodiment of the present disclosure.
[0024] It should be noted that there are no excessive restrictions on the first parameter, for example, it may include parameters affecting the speed of the vehicle, such as the force applied to the vehicle, and / or the torque of the vehicle, and / or the acceleration of the vehicle. Among them, the force may include a driving force, a braking force, etc. The first time period refers to the time period after the current moment. The predicted state quantity sequence is composed of the predicted state quantities of the vehicle at multiple moments in the first time period. The real state quantity at each moment includes the real speed and the real first parameter of the vehicle, and the predicted state quantity at each moment includes the predicted speed and the predicted first parameter of the vehicle.
[0025] In one implementation, the real state quantity of the vehicle at the current moment includes the real speed of the vehicle at the current moment and the real first parameter of the vehicle at the previous moment before the current moment.
[0026] For example, the first parameter is the force F applied to the vehicle, the current moment is the kth moment, the moment before the current moment is the k-1th moment, and the real state x of the vehicle at the current moment (i.e. the kth moment) is k as follows:
[0027]
[0028] Among them, v k is the actual speed of the vehicle at the kth moment, F k-1 is the real force of the vehicle at the k-1th moment.
[0029] In one embodiment, the predicted state quantity of the vehicle at the next moment after the current moment includes the predicted speed of the vehicle at the next moment after the current moment and the predicted first parameter of the vehicle at the current moment.
[0030] For example, the current moment is the kth moment, the next moment after the current moment is the k+1th moment, and the predicted state x of the vehicle at the next moment after the current moment (i.e. the k+1th moment) is p,k+1 as follows:
[0031]
[0032] Among them, v p,k+1 is the predicted speed of the vehicle at the k+1th moment, F p,k is the predicted force of the vehicle at the kth moment.
[0033] For example, the current time is the kth time, and the first time period is from the k+1th time to the k+Nth time. p The time period between moments, N p is the prediction time domain, that is, the number of prediction moments in the first time period, and the prediction state sequence X pk as follows:
[0034]
[0035] Among them, x p,k+2 to For related content, please refer to x p,k+1 The relevant content of is not repeated here, predicting the state sequence X pk 2N p A matrix with 1 row and 1 column.
[0036] In one embodiment, based on the real state quantity of the vehicle at the current moment, a predicted state quantity sequence of the vehicle in the first time period is obtained, including inputting the real state quantity of the vehicle at the current moment into a prediction model, and the prediction model outputs the predicted state quantity sequence. It should be noted that there are no excessive restrictions on the prediction model, for example, it may include a data-driven model, a mechanism model, etc. For example, the prediction model is constructed based on the law of dynamics (such as Newton's second law).
[0037] In some examples, the method also includes obtaining a sample state quantity of the vehicle at a sample moment and a sequence of sample state quantities of the vehicle in a first sample time period, inputting the sample state quantity of the vehicle at the sample moment into an initial model, outputting a third state quantity sequence of the vehicle in the first sample time period from the initial model, and training the initial model based on the sample state quantity sequence and the third state quantity sequence to obtain a prediction model.
[0038] It should be noted that the first sample time period refers to the time period after the sample time.
[0039] S102, constructing a cost function of the vehicle based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period, wherein the independent variables of the cost function include the control quantity sequence of the vehicle in the second time period, and the control quantity of the vehicle includes the change of the first parameter.
[0040] It should be noted that the expected state quantity sequence is composed of the expected state quantities of the vehicle at multiple moments in the first time period, and the expected state quantity at each moment includes the expected speed and expected first parameter of the vehicle. The second time period refers to the time period including the current moment and the remaining moments after the current moment. The control quantity sequence is composed of the control quantity of the vehicle at multiple moments in the second time period, and the control quantity at each moment includes the change in the first parameter. There are no excessive restrictions on the change in the first parameter, for example, it may include the change in the force applied to the vehicle (hereinafter referred to as the change in the force), and / or, the change in the torque of the vehicle, and / or, the change in the acceleration of the vehicle.
[0041] In one implementation, the expected state quantity of the vehicle at the next moment after the current moment includes the expected speed of the vehicle at the next moment after the current moment and the expected first parameter of the vehicle at the current moment.
[0042] For example, the current moment is the kth moment, the next moment after the current moment is the k+1th moment, and the expected state x of the vehicle at the next moment after the current moment (i.e. the k+1th moment) is r,k+1 as follows:
[0043]
[0044] Among them, v r,k+1is the expected speed of the vehicle at the k+1th moment, F r,k is the expected force of the vehicle at the kth moment.
[0045] For example, the current time is the kth time, and the first time period is from the k+1th time to the k+Nth time. p The time period between the moments, the expected state sequence X rk as follows:
[0046]
[0047] Among them, x r,k+2 to For related content, please refer to x r,k+1 The relevant content of is not repeated here. The expected state sequence X rk 2N p A matrix with 1 row and 1 column.
[0048] In one embodiment, the control amount of the vehicle at the current moment includes a deviation between a first parameter of the vehicle at the current moment and a first parameter of the vehicle at a moment before the current moment.
[0049] For example, the current moment is the kth moment, the previous moment is the k-1th moment, and the control amount u of the vehicle at the current moment is k =ΔF k =F p,k -F k-1 , where ΔF k is the change in the force acting on the vehicle at the kth moment, F p,k is the predicted force of the vehicle at the kth moment, F k-1 is the real force acting on the vehicle at the k-1th moment.
[0050] For example, the current time is the kth time, and the second time period is from the kth time to the k+Nth time. c The time period between moments, N c is the control time domain, that is, the number of control moments in the second time period, and the control quantity sequence U k as follows:
[0051]
[0052] Among them, u k+1 to For related content, please refer to u k The relevant content of k N c A matrix with 1 row and 1 column.
[0053] In the embodiments of the present disclosure, the cost function may adopt any cost function in MPC (Model Predictive Control), without too much limitation here, for example, it may include a quadratic programming expression, etc.
[0054] For example, the cost function J is as follows:
[0055]
[0056] Among them, (X pk -X rk ) T is (X pk -X rk ), For U k The transposed matrix of , Q is the state weight matrix, and R is the control weight matrix. Q and R are both symmetric positive definite matrices, and Q is 2N p Row 2N p Matrix of columns, R is N c Row N c Matrix of columns.
[0057] For example, the state weight matrix Q is as follows:
[0058]
[0059] Among them, q i is the weight corresponding to the i-th state quantity, i is no more than 2N p A positive integer, Q is a symmetric positive definite matrix and a diagonal matrix.
[0060] For example, the control weight matrix R is as follows:
[0061]
[0062] Among them, r j is the weight corresponding to the jth state quantity, j is not greater than N c A positive integer, R is a symmetric positive definite matrix and a diagonal matrix.
[0063] In one embodiment, the state quantity weight matrix in the cost function includes the weight corresponding to the vehicle speed and the weight corresponding to the first parameter, wherein the weight corresponding to the first parameter is smaller than the weight corresponding to the vehicle speed. Therefore, the weight corresponding to the first parameter is smaller than the weight corresponding to the vehicle speed, and compared with optimizing the first parameter, the vehicle speed is optimized more, so as to reduce the deviation between the actual speed of the vehicle and the expected speed, thereby improving the accuracy of vehicle speed control.
[0064] In some examples, the weight corresponding to the first parameter is zero, and the first parameter is not optimized. In particular, when the state quantity only includes the vehicle speed and the first parameter, only the vehicle speed is optimized to reduce the deviation between the actual speed of the vehicle and the expected speed, thereby improving the accuracy of vehicle speed control.
[0065] For example, X pk =A·x k +B·U k , you can Substitution The cost function J is obtained as follows:
[0066]
[0067] Among them, B T is the transposed matrix of B, X pk =A·x k +B·U k For the relevant contents, please refer to the following embodiments, which will not be repeated here.
[0068] In one embodiment, the method also includes obtaining an expected speed curve of the vehicle, intercepting a first curve segment within a first time period from the expected speed curve, obtaining an expected speed sequence of the vehicle in the first time period based on the curve segment within the first time period, generating an expected first parameter curve of the vehicle based on the expected speed curve, intercepting a second curve segment within the first time period from the expected first parameter curve, obtaining an expected first parameter sequence of the vehicle in the first time period based on the second curve segment within the first time period, and obtaining an expected state quantity sequence based on the expected speed sequence and the expected first parameter sequence.
[0069] S103, solving the cost function under the constraint condition of the control amount to obtain the control amount of the vehicle at the current moment, and controlling the vehicle based on the control amount of the vehicle at the current moment.
[0070] It should be noted that the constraint conditions of the control quantity include the constraint conditions of the change amount of the first parameter, and there are no excessive restrictions on the constraint conditions, such as boundary constraints (upper limit, lower limit), equality constraints, etc. The solution of the cost function can be achieved by using any cost function solution method in the relevant technology, and there are no excessive restrictions here. It can be understood that by setting the constraint conditions of the change amount of the first parameter (such as force, acceleration, torque), it is possible to prevent excessive jerkiness during driving, ensure the smooth operation of the vehicle, and improve the ride comfort and safety.
[0071] In one embodiment, the cost function is solved under the constraint of the control amount to obtain the control amount of the vehicle at the current moment, including solving the cost function under the constraint of the control amount and the constraint of the state amount to obtain the control amount of the vehicle at the current moment. Thus, the constraint of the control amount and the constraint of the state amount can be comprehensively considered, and the cost function can be solved to ensure that the control amount of the vehicle satisfies the constraint of the control amount, and ensure that the state amount of the vehicle satisfies the constraint of the state amount.
[0072] It should be noted that the constraints of the state quantity include the constraints of the vehicle speed and the constraints of the first parameter (such as force, acceleration, torque).
[0073] For example, in the vehicle braking scenario (such as single pedal braking), the constraints are shown in Table 1:
[0074] Table 1 Constraints
[0075]
[0076] As shown in Table 1, by setting The constraint condition can prevent excessive jerkiness during braking, ensure the smooth operation of the vehicle during braking, and improve the riding comfort and safety during braking. By setting the constraint condition of -5000≤F≤0, it can be ensured that the vehicle continues to decelerate during braking and the deceleration should not be too large. v0 is the initial speed of the vehicle. By setting the constraint condition of 0≤v≤ν0, negative speed can be avoided during braking, which may cause the vehicle to slip backward.
[0077] In one embodiment, the cost function is solved under the constraint of the control amount to obtain the control amount of the vehicle at the current moment, including optimizing the cost function under the constraint of the control amount and the constraint of the state amount to obtain the control amount sequence when the cost function is minimized as the final control amount sequence, and the first control amount of the final control amount sequence is used as the control amount of the vehicle at the current moment. Thus, the control amount sequence when the cost function is minimized can be solved by comprehensively considering the constraint of the control amount and the constraint of the state amount as the final control amount sequence to obtain the control amount of the vehicle at the current moment.
[0078] In one embodiment, the cost function is solved under the constraints of the control quantity to obtain the control quantity of the vehicle at the current moment, including when the cost function is a quadratic programming expression, the constraints of the control quantity, the constraints of the state quantity and the cost function are input into a quadratic programming solver, and the quadratic programming solver outputs a control quantity sequence.
[0079] The control method of the vehicle provided by the embodiment of the present disclosure obtains the predicted state quantity sequence of the vehicle in the first time period based on the real state quantity of the vehicle at the current moment, wherein each type of state quantity includes the speed of the vehicle and the first parameter, and constructs the cost function of the vehicle based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period, wherein the independent variable of the cost function includes the control quantity sequence of the vehicle in the second time period, and the control quantity of the vehicle includes the change of the first parameter, and solves the cost function under the constraint condition of the control quantity to obtain the control quantity of the vehicle at the current moment, and controls the vehicle based on the control quantity of the vehicle at the current moment. Thus, the vehicle control can be realized based on MPC, the speed of the vehicle and the first parameter are both used as the state quantity, the change of the first parameter is used as the control quantity, and the control quantity of the vehicle can be solved under the constraint condition of the control quantity (including the constraint condition of the change of the first parameter), which can ensure that the control quantity of the vehicle meets the constraint condition of the control quantity, and can prevent excessive jerkiness during driving, thereby ensuring the smooth operation of the vehicle and improving the ride comfort and safety.
[0080] Figure 2 is a flow chart of a vehicle control method according to another exemplary embodiment. Figure 2 As shown, the vehicle control method of the embodiment of the present disclosure includes the following steps.
[0081] S201, obtaining a first conversion matrix between the predicted state quantity sequence and the actual state quantity of the vehicle at the current moment.
[0082] In one embodiment, obtaining a first conversion matrix between a predicted state quantity sequence and a real state quantity of a vehicle at a current moment includes obtaining a third conversion matrix between a predicted state quantity of the vehicle at the next moment after the current moment and the real state quantity of the vehicle at the current moment, and obtaining a first conversion matrix based on the third conversion matrix and the prediction time domain. Thus, the third conversion matrix between the predicted state quantity of the vehicle at the next moment after the current moment and the real state quantity of the vehicle at the current moment can be obtained first, and the first conversion matrix can be obtained by comprehensively considering the third conversion matrix and the prediction time domain.
[0083] In some examples, a third conversion matrix between a predicted state quantity of a vehicle at the next moment after the current moment and an actual state quantity of the vehicle at the current moment is obtained, including constructing a continuous-time model between the rate of change of the vehicle's speed and a first parameter based on the law of dynamics, discretizing the continuous-time model to obtain a first model, replacing the predicted first parameter of the vehicle at the current moment in the first model with the sum of the actual first parameter of the vehicle at the previous moment and the change in the first parameter of the vehicle at the current moment to obtain a second model, and obtaining a third conversion matrix based on the second model.
[0084] For example, if the first parameter is the force F applied to the vehicle, the continuous-time model is as follows:
[0085]
[0086] in, is the rate of change of the vehicle's speed, and m is the vehicle's mass.
[0087] For example, the first model is as follows:
[0088]
[0089] Among them, Ts is the sampling period, which is in milliseconds.
[0090] For example, the F in the first model can be p,k , replaced by F k-1 +ΔF k , and the second model is obtained. The second model is as follows:
[0091]
[0092] The third transformation matrix First transformation matrix The first transformation matrix A is 2N p A matrix with 2 rows and 2 columns.
[0093] In one embodiment, obtaining a first conversion matrix between a predicted state quantity sequence and a real state quantity of the vehicle at the current moment includes obtaining a sample state quantity of the vehicle at a sample moment, and a sample state quantity sequence of the vehicle in a first sample time period, obtaining a sample conversion matrix between the sample state quantity sequence and the sample state quantity of the vehicle at the sample moment, and using the sample conversion matrix as the first conversion matrix. Thus, a sample conversion matrix between the sample state quantity sequence and the sample state quantity of the vehicle at the sample moment can be obtained, and the sample conversion matrix can be used as the first conversion matrix.
[0094] S202, obtaining a second conversion matrix between the predicted state quantity sequence and the control quantity sequence.
[0095] In one embodiment, obtaining a second conversion matrix between a predicted state quantity sequence and a control quantity sequence includes obtaining a third conversion matrix between the predicted state quantity of the vehicle at the next moment of the current moment and the actual state quantity of the vehicle at the current moment, obtaining a fourth conversion matrix between the predicted state quantity of the vehicle at the next moment and the control quantity sequence, and obtaining a second conversion matrix based on the third conversion matrix, the fourth conversion matrix, the prediction time domain, and the control time domain. Thus, the third conversion matrix between the predicted state quantity of the vehicle at the next moment of the current moment and the actual state quantity of the vehicle at the current moment can be obtained first, and the fourth conversion matrix between the predicted state quantity of the vehicle at the next moment and the control quantity sequence can be obtained, and the second conversion matrix can be obtained by comprehensively considering the third conversion matrix, the fourth conversion matrix, the prediction time domain, and the control time domain.
[0096] In some examples, a fourth transformation matrix between a predicted state quantity of a vehicle at the next moment and a control quantity sequence is obtained, including constructing a continuous-time model between the rate of change of the vehicle's speed and a first parameter based on the law of dynamics, discretizing the continuous-time model to obtain a first model, replacing the predicted first parameter of the vehicle at the current moment in the first model with the sum of the actual first parameter of the vehicle at the previous moment and the change in the first parameter of the vehicle at the current moment to obtain a second model, and obtaining a fourth transformation matrix based on the second model.
[0097] For example, the second model is as follows:
[0098]
[0099] Fourth transformation matrix
[0100] The second transformation matrix B is as follows:
[0101]
[0102] Among them, the second transformation matrix B is 2N p Row N c Matrix of columns.
[0103] In one embodiment, obtaining a second conversion matrix between a predicted state quantity sequence and a control quantity sequence includes obtaining a sample state quantity sequence of a vehicle in a first sample time period, and a sample control quantity sequence of a vehicle in a second sample time period, obtaining a sample conversion matrix between the sample state quantity sequence and the sample control quantity sequence, and using the sample conversion matrix as the second conversion matrix. Thus, a sample conversion matrix between the sample state quantity sequence and the sample control quantity sequence can be obtained, and the sample conversion matrix can be used as the second conversion matrix.
[0104] It should be noted that the second sample time period refers to a time period including the sample moment and the remaining moments after the sample moment.
[0105] S203, based on the first conversion matrix, the second conversion matrix and the actual state quantity of the vehicle at the current moment, a predicted state quantity sequence is obtained, wherein the predicted state quantity sequence is related to the control quantity sequence.
[0106] In this embodiment, the predicted state quantity sequence is related to the control quantity sequence, that is, the predicted state quantity sequence can be represented by the control quantity sequence.
[0107] In one embodiment, a predicted state quantity sequence is obtained based on a first conversion matrix, a second conversion matrix and the actual state quantity of the vehicle at the current moment, including converting the actual state quantity of the vehicle at the current moment based on the first conversion matrix to obtain a first state quantity sequence, and obtaining a second state quantity sequence based on the second conversion matrix, wherein the second state quantity sequence is related to the control quantity sequence, and the first state quantity sequence and the second state quantity sequence are summed to obtain a predicted state quantity sequence.
[0108] For example, predicting the state sequence X pk The acquisition process is as follows:
[0109] X pk =A·x k +B·U k
[0110] Among them, A·x k is the first state sequence, B·U k is the second state sequence.
[0111] S204, constructing a cost function of the vehicle based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period, wherein the independent variables of the cost function include the control quantity sequence of the vehicle in the second time period, and the control quantity of the vehicle includes the change of the first parameter.
[0112] S205, solving the cost function under the constraint condition of the control amount to obtain the control amount of the vehicle at the current moment, and controlling the vehicle based on the control amount of the vehicle at the current moment.
[0113] The relevant contents of steps S204-S205 can be found in the above embodiment and will not be repeated here.
[0114] The control method of the vehicle provided by the embodiment of the present disclosure obtains a first conversion matrix between the predicted state quantity sequence and the state quantity of the vehicle at the current moment. A second conversion matrix between the predicted state quantity sequence and the control quantity sequence is obtained, and the predicted state quantity sequence is obtained based on the first conversion matrix, the second conversion matrix and the state quantity of the vehicle at the current moment, wherein the predicted state quantity sequence is related to the control quantity sequence. Thus, the predicted state quantity sequence can be obtained by comprehensively considering the first conversion matrix, the second conversion matrix and the state quantity of the vehicle at the current moment.
[0115] Figure 3 is a flow chart of a vehicle control method according to another exemplary embodiment. Figure 3 As shown, the vehicle control method of the embodiment of the present disclosure includes the following steps.
[0116] S301, based on the actual state quantity of the vehicle at the current moment, obtain a predicted state quantity sequence of the vehicle in a first time period, wherein each type of state quantity includes a speed and a first parameter of the vehicle.
[0117] S302, constructing a cost function of the vehicle based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period, wherein the independent variables of the cost function include the control quantity sequence of the vehicle in the second time period, and the control quantity of the vehicle includes the change of the first parameter.
[0118] S303, solving the cost function under the constraint condition of the control amount to obtain the control amount of the vehicle at the current moment.
[0119] The relevant contents of steps S301 - S303 can be found in the above embodiment and will not be described again here.
[0120] S304, obtaining a first sum of a real first parameter of the vehicle at a moment before the current moment and a change in the first parameter of the vehicle at the current moment.
[0121] S305: Obtain a target first parameter of the vehicle at the current moment based on the first sum.
[0122] It should be noted that the first sum is the predicted first parameter of the vehicle at the current moment.
[0123] For example, the first parameter is the force F exerted on the vehicle, F p,k =F k-1 +ΔF k .
[0124] In one implementation, obtaining the target first parameter of the vehicle at the current moment based on the first sum includes using the first sum as the target first parameter of the vehicle at the current moment.
[0125] In one embodiment, obtaining the target first parameter of the vehicle at the current moment based on the first sum includes obtaining a compensation amount of the first parameter based on the environment in which the vehicle is located at the current moment, obtaining a second sum of the first sum and the compensation amount as the target first parameter of the vehicle at the current moment. Thus, the compensation amount of the first parameter can be obtained taking into account the environment in which the vehicle is located at the current moment, obtaining the second sum of the first sum and the compensation amount as the target first parameter of the vehicle at the current moment, which can reduce the impact of environmental factors on vehicle performance and improve the control accuracy of the vehicle.
[0126] It should be noted that there are no excessive restrictions on the compensation amount, for example, it may include road resistance compensation (such as wind resistance compensation, ice and snow coverage compensation), slope compensation, temperature compensation, etc. The relevant content of obtaining the compensation amount of the first parameter can be implemented by using any compensation amount obtaining method in the relevant technology, and no excessive restrictions are made here.
[0127] In some examples, the compensation amount of the first parameter is obtained based on the environment in which the vehicle is currently located, including obtaining the road resistance compensation amount based on at least one of the road parameters, wind speed, and wind direction in which the vehicle is currently located. The road parameters may include road type, friction coefficient, road surface material, road surface flatness, whether it is covered with ice and snow, whether it is slippery, etc.
[0128] In some examples, a compensation amount of the first parameter is obtained based on the environment in which the vehicle is currently located, including obtaining a slope compensation amount based on the slope of the road on which the vehicle is currently located.
[0129] S306: Control the vehicle based on the target first parameter of the vehicle at the current moment.
[0130] In one embodiment, when the first parameter includes the force applied to the vehicle, the vehicle is controlled based on the target first parameter of the vehicle at the current moment, including obtaining the ratio between the target force of the vehicle at the current moment and the tire dynamic radius of the vehicle at the current moment as the target torque of the vehicle at the current moment, and controlling the vehicle based on the target torque of the vehicle at the current moment. Thus, when the first parameter includes the force applied to the vehicle, the target torque of the vehicle at the current moment can be obtained based on the target force of the vehicle at the current moment to control the vehicle.
[0131] In one embodiment, when the first parameter includes the torque of the vehicle, controlling the vehicle based on the target first parameter of the vehicle at the current moment includes controlling the vehicle based on the target torque of the vehicle at the current moment.
[0132] In one embodiment, when the first parameter includes the acceleration of the vehicle, the vehicle is controlled based on the target first parameter of the vehicle at the current moment, including obtaining the product of the target acceleration of the vehicle at the current moment and the mass of the vehicle as the target force of the vehicle at the current moment, obtaining the ratio between the target force of the vehicle at the current moment and the tire dynamic radius of the vehicle at the current moment as the target torque of the vehicle at the current moment, and controlling the vehicle based on the target torque of the vehicle at the current moment. Thus, when the first parameter includes the acceleration of the vehicle, the target force of the vehicle at the current moment can be obtained based on the target acceleration of the vehicle at the current moment, and the target torque of the vehicle at the current moment can be obtained based on the target force of the vehicle at the current moment, so as to control the vehicle.
[0133] The vehicle control method provided by the embodiment of the present disclosure obtains the real first parameter of the vehicle at the previous moment of the current moment, and the first sum of the change amount of the first parameter of the vehicle at the current moment, obtains the target first parameter of the vehicle at the current moment based on the first sum, and controls the vehicle based on the target first parameter of the vehicle at the current moment. Thus, the real first parameter of the vehicle at the previous moment of the current moment, and the first sum of the change amount of the first parameter of the vehicle at the current moment can be obtained, and the target first parameter of the vehicle at the current moment can be obtained based on the first sum to control the vehicle.
[0134] Figure 4 is a flow chart of a vehicle control method according to another exemplary embodiment. Figure 4 As shown, the vehicle control method of the embodiment of the present disclosure includes the following steps.
[0135] S401, based on the actual state quantity of the vehicle at the current moment, obtain a predicted state quantity sequence of the vehicle in a first time period, wherein each type of state quantity includes a speed and a first parameter of the vehicle.
[0136] The relevant contents of step S401 can be found in the above embodiment and will not be described again here.
[0137] S402, based on the actual state quantity of the vehicle at the previous moment before the current moment and the control quantity of the vehicle at the previous moment, obtain the predicted state quantity of the vehicle at the current moment.
[0138] For example, the first parameter is the force F applied to the vehicle, the current moment is the kth moment, the previous moment is the k-1th moment, and the real state x of the vehicle at the previous moment (i.e., the k-1th moment) is k-1 as follows:
[0139]
[0140] Among them, v k-1 is the actual speed of the vehicle at the k-1th moment, F k-2 is the real force acting on the vehicle at the k-2th moment.
[0141] For example, the current moment is the kth moment, and the predicted state x of the vehicle at the current moment (i.e. the kth moment) is p,k as follows:
[0142]
[0143] Among them, v p,k is the predicted speed of the vehicle at the kth moment, F p,k-1 is the predicted force of the vehicle at the k-1th moment.
[0144] For example, the current moment is the kth moment, the previous moment is the k-1th moment, and the control amount u of the vehicle at the previous moment is k-1 =ΔF k-1 =F p,k-1 -F k-2 , where ΔF k-1 is the change in the force acting on the vehicle at the k-1th moment, F p,k-1 is the predicted force of the vehicle at the k-1th moment, F k-2 is the real force acting on the vehicle at the k-2th moment.
[0145] In one embodiment, based on the actual state quantity of the vehicle at the previous moment before the current moment, and the control quantity of the vehicle at the previous moment, the predicted state quantity of the vehicle at the current moment is obtained, including inputting the actual state quantity of the vehicle at the previous moment before the current moment, and the control quantity of the vehicle at the previous moment into the prediction model, and the prediction model outputs the predicted state quantity of the vehicle at the current moment.
[0146] In some examples, the method also includes obtaining a sample state quantity of the vehicle at a sample moment and a sample control quantity of the vehicle at the sample moment, inputting the sample state quantity of the vehicle at the sample moment and the sample control quantity of the vehicle at the sample moment into an initial model, outputting a predicted state quantity of the vehicle at the next moment after the sample moment from the initial model, training the initial model based on the predicted state quantity of the vehicle at the next moment after the sample moment and the sample state quantity of the vehicle at the next moment after the sample moment, and obtaining a prediction model.
[0147] In one embodiment, based on the real state quantity of the vehicle at the previous moment before the current moment and the control quantity of the vehicle at the previous moment, the predicted state quantity of the vehicle at the current moment is obtained, including obtaining the predicted state quantity of the vehicle at the current moment and a fifth conversion matrix between the real state quantity of the vehicle at the previous moment before the current moment, based on the fifth conversion matrix, converting the real state quantity of the vehicle at the previous moment before the current moment to obtain a first state quantity, obtaining the predicted state quantity of the vehicle at the current moment and a sixth conversion matrix between the control quantity of the vehicle at the previous moment, based on the sixth conversion matrix, converting the control quantity of the vehicle at the previous moment to obtain a second state quantity, and obtaining the predicted state quantity of the vehicle at the current moment based on the first state quantity and the second state quantity.
[0148] For example, the third model is as follows:
[0149]
[0150] The third model F p,k-1 , replaced by F k-2 +ΔF k-1 , and the fourth model is obtained. The fourth model is as follows:
[0151]
[0152] The fifth transformation matrix is consistent with the third transformation matrix, both of which are
[0153] The sixth conversion matrix is consistent with the fourth conversion matrix, both of which are
[0154] For example, the predicted state x of the vehicle at the current moment p,k The acquisition process is as follows:
[0155] x p,k =A d ·x k-1 +B d ·u k-1
[0156] Among them, A d ·x k-1 is the first state quantity, B d ·u k-1 is the second state quantity.
[0157] It should be noted that, the relevant contents of the third model can refer to the relevant contents of the first model in the above embodiment, the relevant contents of the fourth model can refer to the relevant contents of the second model in the above embodiment, the relevant contents of the fifth conversion matrix can refer to the relevant contents of the third conversion matrix, and the relevant contents of the sixth conversion matrix can refer to the relevant contents of the fourth conversion matrix, which will not be repeated here.
[0158] S403, obtaining the error between the actual state of the vehicle at the current moment and the predicted state of the vehicle at the current moment.
[0159] For example, the error e = x k -x p,k .
[0160] S404, constructing a cost function based on the predicted state quantity sequence, the expected state quantity sequence and the error quantity.
[0161] In one embodiment, a cost function is constructed based on a predicted state quantity sequence, an expected state quantity sequence and an error quantity, including obtaining the product of the error quantity and a feedback coefficient matrix as an error matrix, correcting the predicted state quantity sequence based on the error matrix to obtain a corrected state quantity sequence, and constructing a cost function based on the corrected state quantity sequence and the expected state quantity sequence. Thus, an error matrix can be obtained based on the error quantity and the feedback coefficient matrix to correct the predicted state quantity sequence to obtain a corrected state quantity sequence, thereby constructing a cost function.
[0162] In some examples, based on the error matrix, the predicted state quantity sequence is corrected to obtain the corrected state quantity sequence, including summing the predicted state quantity sequence and the error matrix to obtain the corrected state quantity sequence.
[0163] For example, the cost function J is as follows:
[0164]
[0165] E=e·H
[0166] Among them, E is the error matrix, H is the feedback coefficient matrix, (X pk +E) is the correction state sequence, E and H are both 2N p A matrix with 1 row and 1 column, (X pk +EX rk ) T is (X pk +EX rk ) is the transposed matrix of .
[0167] For example, X pk =A·x k +B·U k , X pk =A·x k +B·U k Substitute J = (X pk +E-Xrk)TQ(Xpk+E-Xrk)+UkTRUk, the cost function J is as follows:
[0168]
[0169] In one embodiment, a cost function is constructed based on the predicted state quantity sequence, the expected state quantity sequence and the error quantity, including correcting the predicted state quantity sequence based on the error quantity to obtain a corrected state quantity sequence, and constructing the cost function based on the corrected state quantity sequence and the expected state quantity sequence. Thus, the predicted state quantity sequence can be corrected taking into account the error quantity to obtain a corrected state quantity sequence, and then the cost function can be constructed.
[0170] In some examples, based on the error amount, the predicted state quantity sequence is corrected to obtain the corrected state quantity sequence, including obtaining the sum of the s-th predicted state quantity in the predicted state quantity sequence and the error amount as the s-th corrected state quantity in the corrected state quantity sequence, where s is not greater than the predicted time domain N p A positive integer.
[0171] In some examples, based on the error amount, the predicted state quantity sequence is corrected to obtain the corrected state quantity sequence, including obtaining the product of the error amount and the set coefficient as the correction amount, obtaining the sum of the s-th predicted state quantity in the predicted state quantity sequence and the correction amount as the s-th corrected state quantity in the corrected state quantity sequence. It should be noted that there are no excessive restrictions on the set coefficient, for example, it may include 0.5, 0.8, etc.
[0172] S405, solving the cost function under the constraint condition of the control amount to obtain the control amount of the vehicle at the current moment, and controlling the vehicle based on the control amount of the vehicle at the current moment.
[0173] The relevant contents of step S405 can be found in the above embodiment and will not be described again here.
[0174] The control method of the vehicle provided by the embodiment of the present disclosure obtains the predicted state quantity of the vehicle at the current moment based on the real state quantity of the vehicle at the previous moment and the control quantity of the vehicle at the previous moment, obtains the error between the real state quantity of the vehicle at the current moment and the predicted state quantity of the vehicle at the current moment, and constructs a cost function based on the predicted state quantity sequence, the expected state quantity sequence and the error quantity. Thus, the predicted state quantity of the vehicle at the previous moment and the control quantity of the vehicle at the previous moment can be comprehensively considered to obtain the predicted state quantity of the vehicle at the current moment, obtain the error between the real state quantity of the vehicle at the current moment and the predicted state quantity, and comprehensively consider the predicted state quantity sequence, the expected state quantity sequence and the error quantity to construct a cost function, and add feedback correction, which can avoid the problem that the inaccurate predicted state quantity sequence affects the solution of the control quantity, improve the accuracy of the solution of the control quantity, and make the control of the vehicle have a strong ability to resist disturbance and overcome system uncertainty.
[0175] Based on any of the above embodiments, taking the vehicle braking (such as single pedal braking) scenario as an example, the following can be obtained: Figure 5 In the expected speed curve shown, t0 is the moment when the vehicle starts to brake, that is, the initial moment, and v0 is the speed of the vehicle at moment t0, that is, the initial speed.
[0176] like Figure 6 As shown, based on the expected speed curve, the expected state sequence X is obtained. rk .
[0177] At the k-1th moment, obtain the control value u of the vehicle at the k-1th moment output by the quadratic programming solver k-1 , and at the k-1th moment based on u k-1 Control the vehicle.
[0178] The actual state x of the vehicle at the k-1th moment k-1 , and u k-1 Input to the prediction model, and the prediction model outputs the predicted state x of the vehicle at the current moment p,k .
[0179] At the kth moment, obtain the real state x of the vehicle at the kth moment k , error e = x k -x p,k , x k Input to the prediction model, and the prediction model outputs the predicted state quantity sequence X pk , the error e and X pk Input to the feedback corrector, which outputs the correction state sequence X pmodk , based on X pmodk With X rk Construct a cost function and input the cost function into the quadratic programming solver, which outputs the control value u of the vehicle at the kth moment. k , and at the kth moment based on u k Control the vehicle.
[0180] Figure 7 is a block diagram of a vehicle control device according to an exemplary embodiment. Figure 7 The vehicle control device 100 of the embodiment of the present disclosure includes: an acquisition module 110, a construction module 120 and a control module 130.
[0181] The acquisition module 110 is configured to obtain a predicted state quantity sequence of the vehicle in a first time period based on the actual state quantity of the vehicle at a current moment, wherein each type of state quantity includes a speed and a first parameter of the vehicle;
[0182] A construction module 120 is configured to construct a cost function of the vehicle based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period, wherein the independent variable of the cost function includes a control quantity sequence of the vehicle in the second time period, and the control quantity of the vehicle includes a change in the first parameter;
[0183] The control module 130 is configured to solve the cost function under the constraint condition of the control amount, obtain the control amount of the vehicle at the current moment, and control the vehicle based on the control amount of the vehicle at the current moment.
[0184] In one embodiment of the present disclosure, the acquisition module 110 is further configured to: acquire a first conversion matrix between the predicted state quantity sequence and the actual state quantity of the vehicle at the current moment; acquire a second conversion matrix between the predicted state quantity sequence and the control quantity sequence; obtain the predicted state quantity sequence based on the first conversion matrix, the second conversion matrix and the actual state quantity of the vehicle at the current moment, wherein the predicted state quantity sequence is related to the control quantity sequence.
[0185] In one embodiment of the present disclosure, the acquisition module 110 is further configured to: obtain a third conversion matrix between the predicted state quantity of the vehicle at the next moment after the current moment and the actual state quantity of the vehicle at the current moment; and obtain the first conversion matrix based on the third conversion matrix and the predicted time domain.
[0186] In one embodiment of the present disclosure, the acquisition module 110 is further configured to: obtain a third conversion matrix between the predicted state quantity of the vehicle at the next moment after the current moment and the actual state quantity of the vehicle at the current moment; obtain a fourth conversion matrix between the predicted state quantity of the vehicle at the next moment and the control quantity sequence; and obtain the second conversion matrix based on the third conversion matrix, the fourth conversion matrix, the prediction time domain and the control time domain.
[0187] In one embodiment of the present disclosure, the acquisition module 110 is further configured to: based on the first conversion matrix, convert the actual state quantity of the vehicle at the current moment to obtain a first state quantity sequence; based on the second conversion matrix, obtain a second state quantity sequence, wherein the second state quantity sequence is related to the control quantity sequence; and sum the first state quantity sequence and the second state quantity sequence to obtain the predicted state quantity sequence.
[0188] In one embodiment of the present disclosure, the state quantity weight matrix in the cost function includes a weight corresponding to the speed of the vehicle and a weight corresponding to the first parameter, wherein the weight corresponding to the first parameter is smaller than the weight corresponding to the speed of the vehicle.
[0189] In one embodiment of the present disclosure, the weight corresponding to the first parameter is zero.
[0190] In one embodiment of the present disclosure, the control module 130 is further configured to: obtain a first sum of a real first parameter of the vehicle at the previous moment and a change in the first parameter of the vehicle at the current moment; obtain a target first parameter of the vehicle at the current moment based on the first sum; and control the vehicle based on the target first parameter of the vehicle at the current moment.
[0191] In one embodiment of the present disclosure, the control module 130 is further configured to: obtain a compensation amount of the first parameter based on the environment in which the vehicle is located at the current moment; obtain a second sum of the first sum and the compensation amount as the target first parameter of the vehicle at the current moment.
[0192] In one embodiment of the present disclosure, when the first parameter includes the force applied to the vehicle, the control module 130 is further configured to: obtain the ratio of the target force of the vehicle at the current moment to the dynamic radius of the tire of the vehicle at the current moment as the target torque of the vehicle at the current moment; and control the vehicle based on the target torque of the vehicle at the current moment.
[0193] In one embodiment of the present disclosure, the construction module 120 is further configured to: obtain the predicted state quantity of the vehicle at the current moment based on the actual state quantity of the vehicle at the previous moment and the control quantity of the vehicle at the previous moment; obtain the error quantity between the actual state quantity of the vehicle at the current moment and the predicted state quantity of the vehicle at the current moment; and construct the cost function based on the predicted state quantity sequence, the expected state quantity sequence and the error quantity.
[0194] In one embodiment of the present disclosure, the construction module 120 is further configured to: obtain the product of the error amount and the feedback coefficient matrix as an error matrix; based on the error matrix, correct the predicted state quantity sequence to obtain a corrected state quantity sequence; based on the corrected state quantity sequence and the expected state quantity sequence, construct the cost function.
[0195] In one embodiment of the present disclosure, the control module 130 is further configured to: optimize the cost function under the constraints of the control quantity and the state quantity, and obtain a control quantity sequence when the cost function is minimized as a final control quantity sequence; and use the first control quantity of the final control quantity sequence as the control quantity of the vehicle at the current moment.
[0196] In one embodiment of the present disclosure, the first parameter includes a force applied to the vehicle and / or a torque of the vehicle.
[0197] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0198] The control device of the vehicle provided by the embodiment of the present disclosure obtains the predicted state quantity sequence of the vehicle in the first time period based on the real state quantity of the vehicle at the current moment, wherein each type of state quantity includes the speed of the vehicle and the first parameter, and constructs the cost function of the vehicle based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period, wherein the independent variable of the cost function includes the control quantity sequence of the vehicle in the second time period, and the control quantity of the vehicle includes the change of the first parameter, and solves the cost function under the constraint condition of the control quantity to obtain the control quantity of the vehicle at the current moment, and controls the vehicle based on the control quantity of the vehicle at the current moment. Thus, the vehicle control can be realized based on MPC, the speed of the vehicle and the first parameter are both used as the state quantity, the change of the first parameter is used as the control quantity, and the control quantity of the vehicle can be solved under the constraint condition of the control quantity (including the constraint condition of the change of the first parameter), which can ensure that the control quantity of the vehicle meets the constraint condition of the control quantity, prevent excessive jerkiness during driving, ensure the smooth operation of the vehicle, and improve the ride comfort and safety.
[0199] Figure 8 2 is a block diagram of a vehicle according to an exemplary embodiment. For example, vehicle 200 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. Vehicle 200 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.
[0200] Reference Figure 8, the vehicle 200 may include various subsystems, such as an infotainment system 210, a perception system 220, a decision control system 230, a drive system 240, and a computing platform 250. The vehicle 200 may also include more or fewer subsystems, and each subsystem may include multiple components. In addition, each subsystem and each component of the vehicle 200 may be interconnected by wire or wireless means.
[0201] In some embodiments, the infotainment system 210 may include a communication system, an entertainment system, and a navigation system, among others.
[0202] The perception system 220 may include several sensors for sensing information about the environment around the vehicle 200. For example, the perception system 220 may include a global positioning system (the global positioning system may be a GPS system, or a Beidou system or other positioning systems), an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera.
[0203] The decision control system 230 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.
[0204] The drive system 240 may include components that provide power movement for the vehicle 200. In one embodiment, the drive system 240 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of an internal combustion engine, an electric motor, and an air compression engine. The engine can convert energy provided by the energy source into mechanical energy.
[0205] Some or all functions of the vehicle 200 are controlled by a computing platform 250. The computing platform 250 may include at least one processor 251 and a memory 252, and the processor 251 may execute instructions 253 stored in the memory 252.
[0206] The processor 251 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System on Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.
[0207] The memory 252 may be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0208] In addition to instructions 253 , memory 252 may also store data, such as road maps, route information, and data such as the location, direction, and speed of the vehicle. The data stored in memory 252 may be used by computing platform 250 .
[0209] In the embodiment of the present disclosure, the processor 251 can execute instructions 253 to implement all or part of the steps of the vehicle control method provided by the present disclosure.
[0210] The vehicle of the disclosed embodiment obtains a predicted state quantity sequence of the vehicle in the first time period based on the real state quantity of the vehicle at the current moment, wherein each type of state quantity includes the speed of the vehicle and the first parameter, and constructs a cost function of the vehicle based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period, wherein the independent variable of the cost function includes the control quantity sequence of the vehicle in the second time period, and the control quantity of the vehicle includes the change of the first parameter, and solves the cost function under the constraint of the control quantity to obtain the control quantity of the vehicle at the current moment, and controls the vehicle based on the control quantity of the vehicle at the current moment. Thus, the vehicle control can be realized based on MPC, the speed of the vehicle and the first parameter are both used as the state quantity, the change of the first parameter is used as the control quantity, and the control quantity of the vehicle can be solved under the constraint of the control quantity (including the constraint of the change of the first parameter), which can ensure that the control quantity of the vehicle meets the constraint of the control quantity, prevent excessive jerkiness during driving, ensure the smooth operation of the vehicle, and improve the ride comfort and safety.
[0211] In order to implement the above embodiments, the present disclosure further proposes a server, comprising a processor; a memory for storing processor executable instructions; wherein the processor is configured to implement the steps of the vehicle control method provided by the present disclosure.
[0212] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the vehicle control method provided by the present disclosure are implemented.
[0213] Alternatively, the computer readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, or the like.
[0214] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.
[0215] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. A vehicle control method, characterized in that: include: Based on the real state quantity of the vehicle at the current moment, a predicted state quantity sequence of the vehicle in a first time period is obtained, wherein each type of state quantity includes the speed and the first parameter of the vehicle; Based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period, constructing a cost function of the vehicle, wherein the independent variable of the cost function includes a control quantity sequence of the vehicle in the second time period, and the control quantity of the vehicle includes a change in the first parameter; The cost function is solved under the constraint condition of the control amount to obtain the control amount of the vehicle at the current moment, and the vehicle is controlled based on the control amount of the vehicle at the current moment.
2. The method according to claim 1, characterized in that The step of obtaining a predicted state quantity sequence of the vehicle in a first time period based on the actual state quantity of the vehicle at the current moment includes: Obtaining a first conversion matrix between the predicted state quantity sequence and the actual state quantity of the vehicle at the current moment; Acquire a second conversion matrix between the predicted state quantity sequence and the control quantity sequence; Based on the first conversion matrix, the second conversion matrix and the actual state quantity of the vehicle at the current moment, the predicted state quantity sequence is obtained, wherein the predicted state quantity sequence is related to the control quantity sequence.
3. The method according to claim 2, characterized in that The step of obtaining a first conversion matrix between the predicted state quantity sequence and the actual state quantity of the vehicle at the current moment includes: Obtaining a third conversion matrix between a predicted state quantity of the vehicle at the next moment after the current moment and an actual state quantity of the vehicle at the current moment; The first conversion matrix is obtained based on the third conversion matrix and the prediction time domain.
4. The method according to claim 2, characterized in that: The obtaining of a second conversion matrix between the predicted state quantity sequence and the control quantity sequence comprises: Obtaining a third conversion matrix between a predicted state quantity of the vehicle at the next moment after the current moment and an actual state quantity of the vehicle at the current moment; Obtaining a fourth conversion matrix between the predicted state quantity of the vehicle at the next moment and the control quantity sequence; The second conversion matrix is obtained based on the third conversion matrix, the fourth conversion matrix, the prediction time domain and the control time domain.
5. The method according to claim 2, characterized in that: The step of obtaining the predicted state quantity sequence based on the first conversion matrix, the second conversion matrix and the real state quantity of the vehicle at the current moment includes: Based on the first conversion matrix, converting the real state quantity of the vehicle at the current moment to obtain a first state quantity sequence; Obtaining a second state quantity sequence based on the second conversion matrix, wherein the second state quantity sequence is related to the control quantity sequence; The first state quantity sequence and the second state quantity sequence are summed to obtain the predicted state quantity sequence.
6. The method according to claim 1, characterized in that The state quantity weight matrix in the cost function includes a weight corresponding to the speed of the vehicle and a weight corresponding to the first parameter, wherein the weight corresponding to the first parameter is smaller than the weight corresponding to the speed of the vehicle.
7. The method according to claim 6, characterized in that The weight corresponding to the first parameter is zero.
8. The method according to claim 1, characterized in that The controlling the vehicle based on the control amount of the vehicle at the current moment includes: Obtaining a first sum of a real first parameter of the vehicle at a moment before the current moment and a change in the first parameter of the vehicle at the current moment; Obtaining a target first parameter of the vehicle at the current moment based on the first sum; The vehicle is controlled based on a target first parameter of the vehicle at a current moment.
9. The method according to claim 8, characterized in that The obtaining of a target first parameter of the vehicle at the current moment based on the first sum value includes: Obtaining a compensation amount of the first parameter based on the environment in which the vehicle is located at a current moment; The first sum value and the second sum value of the compensation amount are obtained as a target first parameter of the vehicle at the current moment.
10. The method according to claim 8, characterized in that In a case where the first parameter includes a force applied to the vehicle, controlling the vehicle based on a target first parameter of the vehicle at a current moment includes: Obtaining a ratio between a target force of the vehicle at a current moment and a tire dynamic radius of the vehicle at a current moment as a target torque of the vehicle at a current moment; The vehicle is controlled based on the target torque of the vehicle at a current moment.
11. The method according to any one of claims 1 to 10, characterized in that The constructing a cost function of the vehicle based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period includes: Based on the actual state quantity of the vehicle at the previous moment before the current moment and the control quantity of the vehicle at the previous moment, a predicted state quantity of the vehicle at the current moment is obtained; Obtaining an error between a real state quantity of the vehicle at the current moment and a predicted state quantity of the vehicle at the current moment; The cost function is constructed based on the predicted state quantity sequence, the expected state quantity sequence and the error quantity.
12. The method according to claim 11, characterized in that The cost function is constructed based on the predicted state quantity sequence, the expected state quantity sequence and the error quantity, including: Obtaining the product of the error amount and the feedback coefficient matrix as an error matrix; Based on the error matrix, the predicted state quantity sequence is corrected to obtain a corrected state quantity sequence; The cost function is constructed based on the corrected state quantity sequence and the desired state quantity sequence.
13. The method according to claim 1, characterized in that Solving the cost function under the constraint of the control amount to obtain the control amount of the vehicle at the current moment includes: Under the constraint conditions of the control quantity and the constraint conditions of the state quantity, the cost function is optimized to obtain a control quantity sequence when the cost function is minimized as a final control quantity sequence; The first control quantity of the final control quantity sequence is used as the control quantity of the vehicle at the current moment.
14. The method according to any one of claims 1 to 10, characterized in that The first parameter includes a force applied to the vehicle and / or a torque of the vehicle.
15. A vehicle control device, characterized in that: include: An acquisition module is configured to obtain a predicted state quantity sequence of the vehicle in a first time period based on the real state quantity of the vehicle at a current moment, wherein each type of state quantity includes a speed and a first parameter of the vehicle; A construction module is configured to construct a cost function of the vehicle based on the predicted state quantity sequence and the expected state quantity sequence of the vehicle in the first time period, wherein the independent variable of the cost function includes a control quantity sequence of the vehicle in the second time period, and the control quantity of the vehicle includes a change in the first parameter; The control module is configured to solve the cost function under the constraint condition of the control amount, obtain the control amount of the vehicle at the current moment, and control the vehicle based on the control amount of the vehicle at the current moment.
16. A vehicle, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: Implement the steps of the method according to any one of claims 1 to 14.
17. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method described in any one of claims 1 to 14 are implemented.
Citation Information
Patent Citations
Method and apparatus to provide necessary output torque reserve by selection of hybrid range state and input speed for a hybrid powertrain system
CN101513874A
Vehicle control method and device, storage medium, electronic equipment and vehicle
CN112947492A
Learning based controller for autonomous driving
CN113495559A
Rolling horizon state estimator
CN114126944A
Adaptive control of autonomous or semi-autonomous vehicles
CN114945885A
