Method and device for determining automatic driving state, equipment, medium and mobile equipment

Abstract

The invention belongs to the technical field of automatic driving, and provides an automatic driving state determination method, a related device thereof and mobile equipment, and the determination method comprises the steps: firstly obtaining the pure lag duration of a transverse and longitudinal actuator of the mobile equipment; secondly, obtaining a historical control sequence within pure lagging duration before the current moment based on the current moment; and finally, determining a first future automatic driving state at a target moment after the current moment based on the current automatic driving state and the actual control quantity of the historical control sequence. Therefore, according to the application, the first future automatic driving state of the mobile equipment at the target moment after the current moment can be determined by using the actual control quantity in the historical control sequence within the pure lag duration of the transverse and longitudinal controller at the current moment and the current automatic driving state; the technical problems of low response speed, poor control precision, poor stability and the like caused by the large lag problem of a transverse and longitudinal controller in the prior art can be solved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method for determining an autonomous driving state and a device, equipment, medium and mobile device. Background Art

[0002] Actuators are an important component of mobile devices with autonomous driving functions. Among them, the lateral and longitudinal actuators can control the driving system, braking system and steering system of the mobile device based on the autonomous driving status of the mobile device, thereby realizing automatic control of the mobile device's acceleration, braking and steering and other autonomous driving functions.

[0003] Since the lateral and longitudinal actuators are affected by lag links such as communication delay and calculation delay (for example, 300ms), there is a certain lag effect. If the relevant control instructions are executed in real time, there will be certain safety hazards in operations such as steering and braking.

[0004] In the related technology, a first-order lag link can be used to simulate a pure lag link to establish a prediction model. The prediction model can be combined with other pure mathematical algorithms such as the horizontal and vertical integrated evaluation function to calculate the control quantity corresponding to the autonomous driving state. The control quantity can be used to control the mobile device at future times to reduce the safety hazards caused by the lag effect.

[0005] However, since the first-order lag link cannot simulate the large lag problem of the lateral and longitudinal controllers, the large lag problem is the problem of large delay in the pure lag link. Therefore, when dealing with large lag problems, the output results of the prediction model are inaccurate. At the same time, the use of pure mathematical algorithms has high computational complexity and large amount of calculations, which will lead to slow response speed.

[0006] It can be seen that using the methods in the relevant technology to deal with the large lag problem of the lateral and longitudinal actuators will still have technical problems such as slow response speed, poor control accuracy, and poor stability. Summary of the invention

[0007] In order to overcome the problems existing in the related art, the present application provides a method for determining the driving state of a mobile device and a related device and mobile device, which can effectively solve or alleviate the large lag problem existing in the lateral and longitudinal actuators.

[0008] On one hand, the present application provides a method for determining an autonomous driving state, comprising:

[0009] Get the pure lag time of the horizontal and vertical actuators of the mobile device;

[0010] Based on the current moment, a historical control sequence within the pure lag time before the current moment is obtained; the historical control sequence includes an actual control amount for controlling the movement of the mobile device;

[0011] A first future autonomous driving state at a target time after the current time is determined based on the current autonomous driving state and the historical control sequence.

[0012] A second aspect of the present application provides a device for determining an automatic driving state, comprising:

[0013] A pure lag time acquisition module is used to obtain the pure lag time of the horizontal and vertical actuators of the mobile device;

[0014] A historical control sequence acquisition module, used to acquire a historical control sequence within the pure lag time before the current moment based on the current moment; the historical control sequence includes an actual control amount for controlling the movement of the mobile device;

[0015] A state determination module is used to determine a first future autonomous driving state at a target moment after the current moment based on the current autonomous driving state and the historical control sequence.

[0016] A third aspect of the present application provides a controller, including:

[0017] Processor; and

[0018] A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute a method for determining an autonomous driving state as described above.

[0019] A fourth aspect of the present application provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor executes a method for determining an autonomous driving state as described above.

[0020] A fifth aspect of the present application provides a mobile device, comprising the above-mentioned controller.

[0021] The technical solution provided by this application may have the following beneficial effects:

[0022] The present application provides a method for determining an automatic driving state and its related apparatus and mobile device, the determination method first obtains the pure lag time of the lateral and longitudinal actuators of the mobile device; secondly, based on the current moment, obtains the historical control sequence within the pure lag time before the current moment; the historical control sequence includes the actual control amount for manipulating the driving of the mobile device; finally, based on the current automatic driving state and the actual control amount of the historical control sequence, the first future automatic driving state of the target moment after the current moment is determined. It can be seen that the present application can use the actual control amount in the historical control sequence within the pure lag time of the lateral and longitudinal controller at the current moment and the current automatic driving state to determine the first future automatic driving state of the mobile device at the target moment after the current moment, and can have high accuracy even when the delay of the pure lag link is large, and does not need to be combined with pure mathematical algorithms, and can solve the technical problems of slow response speed, poor control accuracy, poor stability, etc. caused by the large lag problem of the lateral and longitudinal controllers in the prior art.

[0023] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0025] Figure 1 It is a flow chart of a method for determining an autonomous driving state shown in an embodiment of the present application.

[0026] Figure 2 It is a schematic diagram of calculating the pure lag time of the horizontal and vertical actuators in the embodiment of the present application.

[0027] Figure 3 Schematic diagram of the principle of using the kinematic integral model to recursively infer the future autonomous driving state in an embodiment of the present application.

[0028] Figure 4 It is a structural schematic diagram of a device for determining an automatic driving state shown in an embodiment of the present application.

[0029] Figure 5 It is a schematic diagram of the structure of the controller shown in the embodiment of the present application. DETAILED DESCRIPTION

[0030] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0031] This application is mainly used in the field of autonomous driving technology and can be applied to mobile devices that use autonomous driving technology. The lateral and longitudinal actuators in mobile devices may cause transient response and stability to decrease due to irresistible hysteresis effects such as communication delay and calculation delay. The related technology can offset some of the effects of the hysteresis problem, but the effects of the large hysteresis problem cannot be solved.

[0032] Based on this, a method for determining the state of autonomous driving, an apparatus, a device, a medium and a mobile device provided in the embodiments of the present application can solve the problems of poor control accuracy, oscillating motion, poor stability and the like caused by large lag problems of the lateral and longitudinal controllers.

[0033] The following is a detailed description of the embodiments of the present application.

[0034] An embodiment of the present application provides a method for determining an autonomous driving state.

[0035] See also Figure 1 , Figure 1 It is a flow chart of a method for determining an autonomous driving state shown in an embodiment of the present application.

[0036] An embodiment of the present application provides a method for determining an autonomous driving state, including:

[0037] S100: Obtain pure lag time of the horizontal and vertical actuators of the mobile device.

[0038] In the embodiment of the present application, the transverse and longitudinal actuators have pure lag time such as communication delay and calculation delay, but the pure lag time of each transverse and longitudinal controller may be different. Therefore, the pure lag time of the transverse and longitudinal controllers can be obtained in advance through testing. Among them, the pure lag time of the transverse and longitudinal controllers can specifically include the transverse pure lag time of the transverse controller and the longitudinal pure lag time of the longitudinal controller.

[0039] For example, see Figure 2 , Figure 2It is a schematic diagram of calculating the pure hysteresis time of the horizontal and vertical actuators in the embodiment of the present application. Among them, the horizontal coordinate t on the horizontal axis represents the execution time, the vertical coordinate y on the vertical axis represents the size of the control amount, the solid line is the curve corresponding to the control amount, and the dotted line is the curve corresponding to the response amount. Taking the horizontal actuator as an example, when determining the horizontal pure hysteresis time of the horizontal actuator, the horizontal control amount and the horizontal response amount of the horizontal actuator within the test time can be obtained first, and then the time difference between the horizontal control amount and the horizontal response amount in the execution time is calculated as the horizontal pure hysteresis time of the horizontal actuator. Among them, the execution time corresponding to the horizontal response amount is the time when the mobile device actually takes effect when the horizontal control amount. The execution time corresponding to the horizontal control amount is the time when the control amount is generated. Similarly, the longitudinal pure hysteresis time of the longitudinal actuator can also be measured by this test method. It can be understood that the pure hysteresis time can also be calibrated by the manufacturer of the horizontal and vertical actuators based on the underlying functions of the horizontal and vertical controllers after testing on a specific mobile device. In the embodiment of the present application, as long as the calibrated pure hysteresis time can be obtained.

[0040] S200, based on the current moment, obtaining a historical control sequence within a pure lag time before the current moment; the historical control sequence includes an actual control amount for controlling the movement of the mobile device.

[0041] In the embodiment of the present application, a historical control sequence within the pure hysteresis time before the current moment can be obtained. The historical control sequence includes a plurality of actual control amounts used to control the mobile device before the current moment.

[0042] In the embodiment of the present application, the number of control quantities stored in the historical control sequence can be determined according to the sampling period of the control module and the pure lag time.

[0043] In the embodiment of the present application, the process of saving the historical control sequence includes the following steps.

[0044] S201, determining the number of control quantities in the historical control sequence based on the pure lag time;

[0045] S202, collecting actual control quantities of the lateral and longitudinal actuators for controlling the movement of the mobile device based on a sampling period of the control module;

[0046] S203, saving the actual control amount in the data structure until the number of actual control amounts in the data structure meets the number of control amounts.

[0047] In the embodiment of the present application, the number n of control quantities in the historical control sequence can be obtained by the formula Calculated. Among them, d t is the sampling period of the control module. The max() function is used to obtain the maximum value. τ1 is the lateral pure lag time of the lateral actuator, and τ2 is the longitudinal pure lag time of the longitudinal actuator.

[0048] It can be understood that if the number of historical control sequences is greater than the number n of control quantities, the first control quantity in the historical control sequence is deleted.

[0049] In the application, the historical control sequence U can be [u1, u2, u3...u n-1 ,u n ], the element u in the historical control sequence represents the command control amount, which contains the steering wheel angle information θ, in radians. a represents the command acceleration angle information, in meters per second squared.

[0050] like Figure 3 As shown, Figure 3 Schematic diagram of the structure of the historical control sequence in the embodiment of the present application.

[0051] It is understandable that when the embodiment of the present application is executed for the first time, if there are not enough control quantities in the historical control sequence, the subsequent calculation results may be inaccurate, and the subsequent operations may be performed only after the number of control quantities meets the aforementioned n. It is understandable that since the calculation process takes a very short time, usually within 1 second, the loss caused by this method can be ignored.

[0052] In the embodiment of the present application, the historical control sequence includes multiple actual control quantities of manipulating the mobile device before the current moment, based on which the automatic driving state at future moments after the current moment can be predicted.

[0053] S300. Determine a first future autonomous driving state at a target moment after the current moment based on the current autonomous driving state and the actual control amount of the historical control sequence.

[0054] In an embodiment of the present application, the first future autonomous driving state at a future moment, such as a target moment, can be predicted based on the current autonomous driving state of the mobile device and the actual control amount in the historical control sequence. The target moment may be the moment when the mobile device is controlled using the current control amount, which can be understood as the moment when the current control amount takes effect. It can be understood that the first future autonomous driving state includes the autonomous driving state corresponding to the lateral actuator and the autonomous driving state corresponding to the longitudinal actuator, which are used to perform lateral control and longitudinal control, respectively.

[0055] Predicting the first future autonomous driving state at a target moment after the current moment based on the current autonomous driving state and the historical control sequence may be inputting the current moment, the current autonomous driving state and the historical control sequence into a prediction model to obtain multiple future autonomous driving states output by the prediction model. The prediction model may be a machine learning model established based on a kinematic model, and the output is the autonomous driving state at multiple future moments including the target moment. Then, the pure lag time is added to the current moment to obtain the specific time of the target moment, and then the first future autonomous driving state is obtained from the autonomous driving states at multiple future moments.

[0056] Predicting a first future autonomous driving state at a target moment after the current moment based on the current autonomous driving state and the historical control sequence can also be achieved through the following steps.

[0057] S301, converting the historical control sequence into a kinematic model control sequence based on the speed at the current moment.

[0058] S302: Predict a first future autonomous driving state at a target time after the current time based on the current autonomous driving state, the kinematic model, and the kinematic model control sequence.

[0059] S303, wherein the target moment is used to represent the moment when the mobile device is manipulated using the control amount at the current moment; and the kinematic model control sequence is used to represent the posture of the mobile device at multiple future moments after the current moment.

[0060] In the embodiment of the present application, the first future autonomous driving state X3 at a future moment when the control amount at the current moment takes effect can be calculated based on the current autonomous driving state X1 and the historical control sequence U. The first future autonomous driving state may include the lateral first future autonomous driving state X3 corresponding to the lateral actuator. lat And the longitudinal first future autonomous driving state X corresponding to the longitudinal actuator lon .

[0061] In the embodiment of the present application, the future autonomous driving state at a future moment can be determined based on the kinematic model. To predict the future autonomous driving state at a future moment based on the kinematic model, it is necessary to convert the historical control sequence into a kinematic model control sequence based on the speed at the current moment.

[0062] The process of converting the historical control sequence into a kinematic model control sequence based on the speed at the current moment includes the following steps.

[0063] S3011. Obtain the speed at the current moment.

[0064] S3012. Extract the acceleration corresponding to each actual control variable in the historical control sequence to obtain a historical control acceleration sequence.

[0065] S3013: Obtain a kinematic model control sequence based on the speed at the current moment based on the steering wheel angle information in the historical control sequence and the historical control acceleration sequence.

[0066] In the application, taking the future autonomous driving state corresponding to the lateral actuator as an example, the future autonomous driving state of the mobile device at the future moment when the control amount at the current moment is used to control the mobile device will be calculated based on the lateral pure lag time of the lateral actuator.

[0067] The speed of the mobile device at the current moment can be obtained first. The speed, position and other related information of the mobile device can be directly obtained from the state determination module of the mobile device. The state determination module is a common module of the mobile device and will not be described in detail here.

[0068] In step 3012, the historical control sequence U[u1, u2, u3...u n-1 ,u n ] can extract the preset number M1 of control quantities. The preset number M1 can be calculated by the ratio of the lateral pure lag time to the sampling period. Extract the acceleration a corresponding to each control quantity in the historical control sequence U, and then obtain the historical control acceleration sequence [a1, a2, a3...a n1-1 , a n1 ], and is converted into a kinematic model control sequence [v1, v2, v3...v n-1 , v n1 ].

[0069] The conversion formula may include: Among them, i is the position of the element in the historical control acceleration sequence, and dt is the sampling period.

[0070] Then the front wheel angle is calculated based on the steering wheel angle information, and finally the kinematic model control sequence U′=[u1′,u2′,u3′...u n1-1 ′,u n1 ′]. Wherein, u′={v,δ}, v represents the speed of the mobile device, unit is m / s, δ represents the wheel angle, unit is radian / s, and the calculation formula of the wheel angle is: δ=θ / k steer Among them, k steer Indicates the transmission ratio of EPS.

[0071] In the application, the kinematic model can be used to obtain the first future autonomous driving state corresponding to each actuator by integral calculus recursion. Figure 3 , Figure 3The schematic diagram of the principle of using the kinematic integral model to recursively deduce the future autonomous driving state in the embodiment of the present application. Where X is the current autonomous driving state of the mobile device, and the kinematic model control sequence is used to calculate to obtain the first future autonomous driving state. For example, the kinematic integral model can calculate the first future autonomous driving state by the following formula.

[0072] v n+1 =v n +a n ·T; n is the current moment, n+1 is the next moment after the current moment, X is the horizontal coordinate of the position; y is the vertical coordinate of the position; v is the speed of the mobile device, in m / s; T is the control period, in s; is the heading, in radians; L is the wheelbase of the vehicle, K is the eps transmission ratio, is the lateral command eps control amount, in radians; a is the longitudinal command acceleration control amount, in m / s^2. In the application, for example, if the current speed v of the mobile device is 1m / s, the control cycle T is 0.05s, and the command acceleration a is 1m / s, then the speed at the next moment v1=v0+a0*T=1+1×0.05=1.05m / s. By analogy, the future speed in the final first future autonomous driving state can be obtained.

[0073] Similar to the lateral actuator, the determination process of the longitudinal first future autonomous driving state corresponding to the longitudinal actuator is basically the same as the process of the lateral first future autonomous driving state corresponding to the above lateral actuator. However, in application, since the longitudinal pure lag time of most longitudinal actuators is longer than the lateral pure lag time of the lateral actuator, in order to match M1, the preset number of control quantities based on prediction is M2. If the longitudinal first future autonomous driving state can be predicted more accurately and effectively, the M2-M1+1th element in the kinematic model control sequence corresponding to the longitudinal actuator is used as the first element to calculate the longitudinal first future autonomous driving state, so that it can match the lateral first future autonomous driving state corresponding to the lateral actuator and obtain the longitudinal first future autonomous driving state.

[0074] It can be seen that in the embodiment of the present application, the first future autonomous driving state X3 can be obtained by using the historical control sequence U within the pure lag period and the current autonomous driving state X1 at the current moment. There is no need to consider whether the pure lag period is too long to use the first-order lag link simulation. Moreover, since the adopted algorithm does not involve complex pure mathematical algorithms, the calculation efficiency is greatly improved.

[0075] In order to further improve the accuracy of the future autonomous driving state of the mobile device at the future moment, in the embodiment of the present application, the first future autonomous driving state can be further corrected.

[0076] Based on the above embodiment, the embodiment of the present application also includes step 400 and step 500.

[0077] S400. Obtaining a historical automatic driving state sequence within a pure lag time before the current moment based on the current moment; the historical automatic driving state sequence includes a predicted future automatic driving state.

[0078] S500. Correct the first future autonomous driving state at the target moment according to the historical autonomous driving state sequence to obtain a second future autonomous driving state.

[0079] Among them, correcting the first future autonomous driving state at the target moment according to the historical autonomous driving state to obtain the second future autonomous driving state includes the following steps.

[0080] S401. Extracting a target state from a historical automatic driving state sequence based on pure lag duration.

[0081] S402: Taking the difference between the current automatic driving state and the target state as a deviation value.

[0082] S403. Correct the first future autonomous driving state at the target time based on the deviation value to obtain a second future autonomous driving state.

[0083] In this embodiment, it is also necessary to apply the historical automatic driving state sequence. The historical automatic driving state sequence X includes the future automatic driving state predicted in each sampling period before the current moment. In the application, X can be [s1, s2, s3...s n-1 ,s n ], where n is the number of historical autonomous driving state sequences to be recorded. s is the state information of the mobile device, which may include, for example, the global position information x, y, speed v and heading of the mobile device.

[0084] It is understandable that after the first future autonomous driving state predicted in the aforementioned step 300 is generated, it will be saved in the historical autonomous driving state sequence X as a basis for correcting the autonomous driving state at a future moment.

[0085] In this embodiment, the maximum number of future autonomous driving states in the historical autonomous driving state sequence X can be related to the pure lag time, or the formula can be used. Calculated. Among them, d t is the sampling period of the control module. The max() function is used to obtain the maximum value. τ1 is the lateral pure lag time of the lateral actuator, and τ2 is the longitudinal pure lag time of the longitudinal actuator.

[0086] In this embodiment, taking the lateral actuator as an example, the target state in the historical autonomous driving state sequence X is extracted, and the target state is the future autonomous driving state s with a distance τ1 from the current moment i , and the difference between X2 and the current autonomous driving state X1 is taken as the deviation value ΔX, and the formula is ΔX=X1-X2, and then the first future autonomous driving state is corrected to the second future autonomous driving state X4 corresponding to the lateral actuator. It can be understood that the second future autonomous driving state may also include the second future autonomous driving state corresponding to the lateral actuator and the second future autonomous driving state corresponding to the longitudinal actuator.

[0087] By correcting, the second future autonomous driving state can be made more accurate and more consistent with the actual autonomous driving state of the mobile device. Therefore, the second future autonomous driving state can be used as a real-time state for subsequent design and calculation of the lateral and longitudinal control algorithms of the control system.

[0088] Based on this, in this embodiment, it also includes:

[0089] The second future autonomous driving state is sent to the autonomous driving control system so that the autonomous driving system executes the lateral and longitudinal control algorithms as a lag-free system.

[0090] The lateral and longitudinal control algorithms involved in the second future autonomous driving state in this embodiment can be used as real-time control algorithms. For example, before using the embodiment of this application, the autonomous driving mobile device needs to turn on the curve, but due to the large lag problem, the currently generated control amount will not be actually executed until after the delay. If the second future autonomous driving state in the embodiment of this application is used, the delay will be offset, and the mobile device can be controlled as a real-time control amount, and there will be no overshoot (the control amount is adjusted too much after the delayed execution) and other phenomena. Compared with pure mathematical algorithms, it is simpler and more efficient, and can increase the control accuracy of the mobile device, improve stability, and solve the occurrence of phenomena such as oscillating dragon drawing.

[0091] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a device for determining the driving state of a mobile device, a medium, and corresponding embodiments of the mobile device.

[0092] Figure 4 It is a structural schematic diagram of a device for generating a predicted trajectory shown in an embodiment of the present application.

[0093] See also Figure 4 The driving state determination device 400 of the mobile device disclosed in the embodiment of the present application includes:

[0094] The pure lag time acquisition module 1 is used to obtain the pure lag time of the horizontal and vertical actuators of the mobile device.

[0095] The historical control sequence acquisition module 2 is used to obtain the historical control sequence within the pure lag time before the current moment based on the current moment; the historical control sequence includes the actual control of manipulating the driving of the mobile device.

[0096] The state determination module 3 is used to determine the first future autonomous driving state at a target moment after the current moment based on the current autonomous driving state and the actual control amount of the historical control sequence.

[0097] Also includes:

[0098] A correction module is used to obtain a historical automatic driving state sequence within the pure lag time before the current moment based on the current moment; the historical automatic driving state sequence includes a predicted future automatic driving state.

[0099] The first future autonomous driving state at the target moment is corrected according to the historical autonomous driving state sequence to obtain a second future autonomous driving state.

[0100] In some embodiments, the state determination module includes:

[0101] A conversion unit is used to convert the historical control sequence into a kinematic model control sequence based on the speed at the current moment.

[0102] A prediction unit is used to predict a first future autonomous driving state at a target moment after the current moment based on a current autonomous driving state, a kinematic model, and a control sequence of the kinematic model.

[0103] Among them, the target moment is used to represent the moment when the mobile device is manipulated using the control amount at the current moment; the kinematic model control sequence is used to represent the posture of the mobile device at multiple future moments after the current moment.

[0104] In some embodiments, the prediction unit is specifically configured to:

[0105] Get the current speed;

[0106] Extracting the acceleration corresponding to each actual control variable in the historical control sequence to obtain a historical control acceleration sequence;

[0107] A kinematic model control sequence based on the speed at the current moment is obtained based on each steering wheel angle information in the historical control sequence and the historical control acceleration sequence.

[0108] In some embodiments, the conversion unit is specifically configured to:

[0109] Get the current speed;

[0110] The speed and the historical control sequence are input into a sequence conversion model to obtain a kinematic model control sequence based on the speed at the current moment.

[0111] In some embodiments, the correction module is specifically used to:

[0112] Extracting a target state in the historical automatic driving state sequence based on the pure lag duration;

[0113] Taking the difference between the current automatic driving state and the target state as a deviation value;

[0114] The first future autonomous driving state at the target moment is corrected based on the deviation value to obtain a second future autonomous driving state.

[0115] It also includes a sending module for sending the second future autonomous driving state to the autonomous driving control system so that the autonomous driving system executes the lateral and longitudinal control algorithm as a lag-free system.

[0116] In some embodiments, the process of saving the historical control sequence includes:

[0117] Determining the number of control quantities in the historical control sequence based on the pure lag time;

[0118] Based on the sampling period of the control module, actual control variables of the lateral and longitudinal actuators for controlling the movement of the mobile device are collected;

[0119] The actual control amount is saved in a data structure until the number of the actual control amounts in the data structure meets the number of control amounts.

[0120] Corresponding to the method embodiment, using the device in the embodiment of the present application, the actual control quantity in the historical control sequence within the pure lag time of the lateral and longitudinal controllers at the current moment and the current autonomous driving state can be used to determine the first future autonomous driving state of the mobile device at the target moment after the current moment. Even when the delay in the pure lag link is large, it can also have high accuracy and does not need to be combined with pure mathematical algorithms. It can solve the technical problems of slow response speed, poor control accuracy, poor stability, etc. caused by the large lag problem of the lateral and longitudinal controllers in the prior art.

[0121] Figure 5 It is a schematic diagram of the structure of the controller shown in the embodiment of the present application.

[0122] See also Figure 5 , the controller 1000 includes a memory 1010 and a processor 1020 .

[0123] The processor 1020 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0124] The memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0125] The memory 1010 stores executable codes, and when the executable codes are processed by the processor 1020 , the processor 1020 can execute part or all of the methods described above.

[0126] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0127] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing the following method steps:

[0128] Inputting the perception data and map data of the target obstacle obtained at the current moment into the neural network model, and obtaining the predicted points of the target obstacle at at least two different future moments output by the neural network model; wherein each of the future moments corresponds to at least one predicted point;

[0129] Based on the perception data, respectively binding each of the prediction points to an associated lane of each of the prediction points in the map data, so that the prediction points have map semantic information;

[0130] Based on the map semantic information, respectively determining a lane relationship between each predicted point and a target lane where the target obstacle is located;

[0131] Based on the constraint conditions corresponding to the lane relationship, the predicted trajectory of the target obstacle is generated using the predicted points.

[0132] The step of respectively binding each of the prediction points to a lane of each of the prediction points in the map data comprises:

[0133] Determine, based on the position information in the perception data, the associated lanes with an associated relationship within the selected range of each prediction point in the map data;

[0134] A correspondence between each of the predicted points and the associated lane is established respectively, and the correspondence is used to represent map semantic information.

[0135] The generating a predicted trajectory of the target obstacle using the predicted points based on the constraint conditions corresponding to the lane relationship includes:

[0136] According to the time sequence of the future time, at least two adjacent target points at adjacent time are determined in sequence from the predicted points that meet the constraint conditions;

[0137] Determining a curve connection algorithm based on map semantic information of the neighboring target points;

[0138] Connect at least two of the adjacent target points in sequence based on the curve connection algorithm to obtain a target point curve;

[0139] The target point curves are connected to generate a predicted trajectory of the target obstacle.

[0140] The method of determining a curve connection algorithm based on map semantic information of the neighboring target points includes:

[0141] If the two adjacent target points are in the same associated lane and / or the associated lane of the adjacent target point at the next future moment is the successor lane of the associated lane of the adjacent target point at the previous future moment, then the curve connection algorithm is determined to be a lane curvature generation algorithm; the lane curvature generation algorithm can make the generated target point curve conform to the lane curvature of the associated lane.

[0142] The method of determining a curve connection algorithm based on map semantic information of the neighboring target points includes:

[0143] If the two adjacent target points are in adjacent associated lanes, the curve connection algorithm is determined to be a polynomial curve generation algorithm; the polynomial curve generation algorithm can make the generated target point curve conform to the vehicle kinematics.

[0144] After determining the lane relationship between each prediction point and the target lane where the target obstacle is located, the method further includes:

[0145] Based on the constraint conditions corresponding to the road relationship, the target point probability of each predicted point is determined respectively.

[0146] The step of sequentially determining at least two adjacent target points at adjacent moments from the predicted points that meet the constraint conditions includes:

[0147] At least two adjacent target points at adjacent moments are determined in sequence from the predicted points according to each of the target point probabilities.

[0148] The step of sequentially determining at least two adjacent target points at adjacent moments from the predicted points according to each of the target point probabilities comprises:

[0149] Selecting a target point with the highest target point probability among the predicted points at the first future moment as the first target point;

[0150] A destination point with the highest probability of being a target point among the predicted points at a second future moment is selected as a second target point; wherein the second future moment and the first future moment are adjacent moments.

[0151] The step of sequentially determining at least two adjacent target points at adjacent moments from the predicted points according to each of the target point probabilities comprises:

[0152] Selecting the target point with the highest target point probability among the predicted points at the third future moment as the third target point;

[0153] The target point whose target point probability is not the largest among the predicted points at a fourth future moment is selected as the fourth target point; wherein the fourth future moment and the third future moment are adjacent moments.

[0154] The present application also discloses a mobile device, which includes but is not limited to a vehicle with six autonomous driving technology levels, L0-L5, as defined by the Society of Automotive Engineers International (SAE International) or the Chinese national standard "Automotive Driving Automation Classification", for example, a vehicle device or a robot device having the following functions:

[0155] (1) Passenger-carrying function, such as family cars and buses;

[0156] (2) Cargo-carrying functions, such as ordinary trucks, van trucks, trailer trucks, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, trucks with special structures, etc.;

[0157] (3) Tool functions, such as logistics delivery vehicles, automated guided vehicles (AGVs), patrol cars, cranes, hoists, excavators, bulldozers, forklifts, road rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor scrubbers, water sprinklers, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.;

[0158] (4) Entertainment functions, such as entertainment vehicles, amusement park self-driving devices, balance vehicles, etc.;

[0159] (5) Special rescue functions, such as fire trucks, ambulances, power repair vehicles, engineering rescue vehicles, etc.

[0160] This application does not strictly limit the types of mobile devices, and will not be exhaustively listed here.

[0161] The scheme of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For the part that is not described in detail in a certain embodiment, refer to the relevant description of other embodiments. Those skilled in the art should also know that the actions and modules involved in the description are not necessarily required for the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in order, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0162] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0163] Alternatively, the present application can also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0164] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the application herein may be implemented as electronic hardware, computer software, or combinations of both.

[0165] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, a program segment or a code, and the part of the module, the program segment or the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or the flow chart, and the combination of the square boxes in the block diagram and / or the flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0166] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0167] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0168] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for determining an automatic driving state, characterized in that: include: Get the pure lag time of the horizontal and vertical actuators of the mobile device; Based on the current moment, a historical control sequence within the pure lag time before the current moment is obtained; the historical control sequence includes an actual control amount for controlling the movement of the mobile device; A first future autonomous driving state at a target time after the current time is determined based on the current autonomous driving state and the actual control amount of the historical control sequence.

2. The method according to claim 1, characterized in that Also includes: Based on the current moment, a historical automatic driving state sequence within the pure lag time before the current moment is obtained; the historical automatic driving state sequence includes a predicted future automatic driving state; The first future autonomous driving state at the target moment is corrected according to the historical autonomous driving state sequence to obtain a second future autonomous driving state.

3. The method according to claim 1, characterized in that: Determining a first future autonomous driving state at a target moment after the current moment based on the current autonomous driving state and the actual control amount of the historical control sequence includes: Converting the historical control sequence into a kinematic model control sequence based on the velocity at the current moment; predicting a first future autonomous driving state at a target time after the current time based on the current autonomous driving state, the kinematic model, and the kinematic model control sequence; Among them, the target moment is used to represent the moment when the mobile device is manipulated using the control amount at the current moment; the kinematic model control sequence is used to represent the posture of the mobile device at multiple future moments after the current moment.

4. The method according to claim 3, characterized in that The converting the historical control sequence into a kinematic model control sequence based on the speed at the current moment comprises: Get the current speed; Extracting the acceleration corresponding to each actual control variable in the historical control sequence to obtain a historical control acceleration sequence; A kinematic model control sequence based on the speed at the current moment is obtained based on each steering wheel angle information in the historical control sequence and the historical control acceleration sequence.

5. The method according to claim 3, characterized in that: The converting the historical control sequence into a kinematic model control sequence based on the speed at the current moment comprises: Get the current speed; The speed and the historical control sequence are input into a sequence conversion model to obtain a kinematic model control sequence based on the speed at the current moment.

6. The method according to claim 2, characterized in that The step of correcting the first future autonomous driving state at the target moment according to the historical autonomous driving state sequence to obtain a second future autonomous driving state includes: Extracting a target state in the historical automatic driving state sequence based on the pure lag duration; Taking the difference between the current automatic driving state and the target state as a deviation value; The first future autonomous driving state at the target moment is corrected based on the deviation value to obtain a second future autonomous driving state.

7. The method according to claim 2, characterized in that Also includes: The second future autonomous driving state is sent to the autonomous driving control system so that the autonomous driving system executes the lateral and longitudinal control algorithms as a lag-free system.

8. The method according to claim 1, characterized in that The process of saving the historical control sequence includes: Determining the number of control quantities in the historical control sequence based on the pure lag time; Based on the sampling period of the control module, actual control variables of the lateral and longitudinal actuators for controlling the movement of the mobile device are collected; The actual control amount is saved in a data structure until the number of the actual control amounts in the data structure meets the number of control amounts.

9. A device for determining an automatic driving state, characterized in that: include: A pure lag time acquisition module is used to obtain the pure lag time of the horizontal and vertical actuators of the mobile device; A historical control sequence acquisition module, used to acquire a historical control sequence within the pure lag time before the current moment based on the current moment; the historical control sequence includes an actual control amount for controlling the movement of the mobile device; A state determination module is used to determine a first future autonomous driving state at a target moment after the current moment based on the current autonomous driving state and the actual control amount of the historical control sequence.

10. A controller, characterized in that: include: processor; and a memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method for determining the automatic driving state as described in any one of claims 1 to 8.

11. A non-transitory machine-readable storage medium, characterized in that: An executable code is stored thereon, and when the executable code is executed by a processor of an electronic device, the processor executes a method for determining an autonomous driving state as described in any one of claims 1-8.

12. A mobile device, characterized in that: Comprising the controller as claimed in claim 10.

Images