Planning result generation method, device and electronic equipment

Abstract

Disclosed are a planning result generation method, a planning result generation device, and an electronic device. The planning result generation method comprises: generating a prediction result with a first time length as a period by a prediction unit running at a first frequency; acquiring the prediction result with a second time length as a period by a planning unit running at a second frequency; and generating a planning result based on the prediction result within the second time length by the planning unit when the first frequency meets a preset condition. In this way, the generation process of the planning result is improved, and the safety of using the planning result is improved.

Description

Technical Field

[0001] The present application relates to the field of automatic planning, and more specifically, to a planning result generating method, a planning result generating device and an electronic device. Background Art

[0002] In many fields such as autonomous driving, it is necessary to automatically plan the behavior of the controlled object, for example, planning the driving path and control actions of an autonomous vehicle.

[0003] Since the real world is a highly dynamic and interactive scene, in order to make planning more reliable, it is necessary to predict the environment based on current and historical perception results. In addition, because the real world is dynamic, the automatic planning system must run at a high enough frequency to ensure the safety of the planned behavior. For example, in a high-speed autonomous driving scenario, the operating frequency of the autonomous driving system needs to be very high.

[0004] However, since the prediction results are usually obtained through prediction algorithms based on deep reinforcement learning, they are constrained by hardware conditions and the computing power cannot meet the requirements of the prediction algorithms, resulting in the prediction results not necessarily being obtained at the set high operating frequency.

[0005] Therefore, it is desirable to provide an improved planning result generation scheme so as to generate planning results using prediction results obtained at different frequencies. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a planning result generation method, a planning result generation device and an electronic device, which can generate a planning result in a second time length different from the first time length of the prediction unit generating the prediction result by asynchronous operation, thereby improving the generation process of the planning result and improving the security of the use of the planning result.

[0007] According to one aspect of the present application, a planning result generating method is provided, comprising: generating prediction results with a first time length as a period by a prediction unit operating at a first frequency; acquiring the prediction results with a second time length as a period by a planning unit operating at a second frequency; and, when the first frequency meets a preset condition, generating a planning result based on the prediction results within the second time length by the planning unit.

[0008] According to another aspect of the present application, a planning result generating device is provided, comprising: a result generating unit, for generating a prediction result with a first time length as a period by a prediction unit running at a first frequency; a result acquiring unit, for acquiring the prediction result with a second time length as a period by a planning unit running at a second frequency; and a planning generating unit, for generating a planning result by the planning unit based on the prediction result within the second time length acquired by the result acquiring unit when the first frequency meets a preset condition.

[0009] According to another aspect of the present application, an electronic device is provided, comprising: a processor; and a memory, in which computer program instructions are stored, and when the computer program instructions are executed by the processor, the processor executes the planning result generation method as described above.

[0010] According to another aspect of the present application, a computer-readable medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the planning result generation method as described above.

[0011] The planning result generation method, planning result generation device and electronic device provided by the present application can obtain the generated prediction result in a second time length different from the first time length for the prediction unit to generate the prediction result by asynchronous operation, and generate the planning result based on the obtained prediction result. In this way, the prediction unit and the planning unit can be asynchronously operated to ensure the efficient operation of the planning unit based on the prediction result, thereby improving the generation process of the planning result and improving the security of the use of the planning result. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0013] Figure 1 The figure illustrates a flow chart of a method for generating planning results according to an embodiment of the present application.

[0014] Figure 2 The flowchart illustrates an example of a process of determining a preset condition in a planning result generating method according to an embodiment of the present application.

[0015] Figure 3 The flowchart illustrates an example of a process of generating a planning result in a planning result generating method according to an embodiment of the present application.

[0016] Figure 4 A schematic diagram of an operation example of a planning result generating method according to an embodiment of the present application is illustrated.

[0017] Figure 5 The figure illustrates a block diagram of a planning result generating device according to an embodiment of the present application.

[0018] Figure 6 A block diagram illustrating an example of a condition determination unit of a planning result generating device according to an embodiment of the present application is illustrated.

[0019] Figure 7 A block diagram of an example of a planning generation unit of a planning result generation device according to an embodiment of the present application is illustrated.

[0020] Figure 8 A block diagram of an electronic device according to an embodiment of the present application is illustrated. DETAILED DESCRIPTION

[0021] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0022] Application Overview

[0023] As described above, in a scheme of obtaining planning results based on prediction results in a synchronous manner, if planning results are to be obtained at a higher frequency, it is necessary to use a computing device with more powerful computing power, or to use a lighter prediction algorithm or prediction model.

[0024] However, using more powerful computing devices will increase costs, with limited room for improvement and low cost-performance ratio. Lighter prediction algorithms or prediction models have poor prediction effects and their accuracy cannot meet subsequent needs.

[0025] In addition, for machine vision scenarios such as autonomous driving, planning results can be obtained at a higher frequency by shortening the prediction and planning field of view, but this will result in the shortened prediction field of view being unable to meet subsequent needs in terms of time length.

[0026] Based on the above technical problems, the basic concept of the present application is to adopt prediction units and planning units with different operating frequencies. Through the asynchronous operation of the prediction unit and the planning unit, the planning unit obtains the prediction result in a second time length different from the first time length for the prediction unit to generate the prediction result, and generates the planning result based on the prediction result.

[0027] Specifically, the planning result generation method, planning result generation device and electronic device provided in the present application first generate prediction results with a first time length as a period by a prediction unit running at a first frequency, and then obtain the prediction results with a second time length as a period by a planning unit running at a second frequency. Finally, when the first frequency meets the preset conditions, the planning result is generated by the planning unit based on the prediction results within the second time length.

[0028] In this way, the planning result generation method, planning result generation device and electronic device provided by the present application obtain the generated prediction result with a second time length different from the first time length for the prediction unit to generate the prediction result, and generate the planning result based on the obtained prediction result. That is, the planning unit runs with the second time length, and the second time length is different from the first time length as the operation cycle of the prediction unit, so the planning unit and the prediction unit run asynchronously.

[0029] Therefore, even if the planning unit still needs to generate planning results based on the prediction results generated by the prediction unit, the planning unit does not need to keep running synchronously with the prediction unit, thereby improving the operation efficiency of the planning unit, improving the planning result generation process, and improving the security of the use of the planning results.

[0030] When the planning result generation method, planning result generation device and electronic device provided by the present application are applied to an autonomous driving system, the normal performance of the entire autonomous driving system can be guaranteed. That is, by asynchronously using a prediction unit, such as an environmental prediction module, the prediction unit can be operated at a lower frequency than the planning unit calls the prediction result. Therefore, the present application solves the problem that "if the prediction unit is placed in the autonomous driving system in a synchronous operation manner, the operating frequency of the entire system will be reduced due to the limitation of the operating frequency of the prediction unit, affecting the safety of driving."

[0031] After introducing the basic principles of the present application, various non-limiting embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0032] Exemplary Methods

[0033] Figure 1 The figure illustrates a flow chart of a method for generating planning results according to an embodiment of the present application.

[0034] like Figure 1 As shown, the planning result generating method according to the embodiment of the present application includes the following steps.

[0035] Step S110, generating a prediction result by a prediction unit running at a first frequency with a first time length as a period. In the embodiment of the present application, the prediction unit runs at a first frequency, denoted as f prediction , for example, 3 Hz. Therefore, the prediction unit runs once to generate a prediction result with a running step length of t prediction =1 / f prediction , for example, corresponding to 0.33 seconds of 3 Hz. In addition, the prediction unit requires multiple running steps, that is, the first time length, and the prediction unit generates prediction results based on this as a period.

[0036] Step S120, obtaining the prediction result by a planning unit running at a second frequency with a second time length as a period. In the embodiment of the present application, the planning unit runs at a second frequency, denoted as f planning , for example, 10 Hz. Therefore, the planning unit runs once to generate a planning result with a running step length of t planning =1 / f planning , for example, corresponding to 0.1 seconds of 10 Hz. In addition, the planning unit requires a plurality of running steps, that is, the second time length, and the planning unit generates planning results based on this as a cycle.

[0037] It is worth noting that in the embodiments of the present application, the operating frequency of the planning unit needs to meet the needs of the actual application scenario. For example, in the application scenario of autonomous driving, in order to improve the safety of autonomous driving, the frequency of the planning unit generating planning results needs to be greater than a predetermined time threshold, so as to ensure that the planning results are generated in a sufficiently short time and improve the safety of the planning behavior.

[0038] Therefore, in the embodiment of the present application, in order to meet the frequency requirement of the planning unit, the operating frequency of the planning unit may be different from the operating frequency of the prediction unit, so as to operate in an asynchronous manner with the prediction unit. Furthermore, since the planning unit needs to use the prediction result generated by the prediction unit to generate the planning result, the planning unit obtains the prediction result of the prediction unit with a second time length as a period.

[0039] Step S130, when the first frequency meets the preset condition, the planning result is generated by the planning unit based on the prediction result within the second time length. As described above, the planning unit generates the planning result based on the prediction result generated by the prediction unit, and the planning unit does not need to run synchronously with the first frequency of the prediction unit, but can run at its own second frequency. Therefore, the time period for the planning unit to obtain the prediction result is not the first time length of the prediction unit, but the second time length of the planning unit, and the planning result is generated based on this.

[0040] Therefore, in order to ensure the accuracy of the generated planning results, the first frequency needs to meet the preset conditions so that the planning unit generates planning results based on different prediction results in two adjacent time periods, thereby ensuring that the planning results can actually reflect the differences in the predicted results and improve the effectiveness of the planned behavior. The preset conditions that the first frequency needs to meet will be further described in detail below.

[0041] In this way, when the first frequency meets the preset conditions, the planning unit generates a planning result based on the prediction result within the second time length. Even if the planning unit still needs to generate a planning result based on the prediction result generated by the prediction unit, the planning unit does not need to keep running synchronously with the prediction unit, thereby improving the operation efficiency of the planning unit, improving the planning result generation process, and improving the security of the use of the planning results.

[0042] In the embodiment of the present application, the relationship between the first frequency of the prediction unit and the second frequency of the planning unit is not limited. For example, if the first frequency is greater than or equal to the second frequency, the prediction unit and the planning unit can be used directly without any changes to their hardware and algorithms. However, in general, the first frequency is less than the second frequency, so that the operation of the planning unit is limited by the frequency at which the prediction unit generates prediction results, thereby limiting the operating efficiency of the planning unit and reducing the security of the use of the planning results.

[0043] Therefore, in the embodiment of the present application, the prediction unit and the planning unit are no longer executed in sequence, but are a parallel structure, for example, information can be transmitted through inter-module communication. The prediction unit obtains the perception information at a certain frequency, and after a certain period of calculation, it will obtain the prediction result of the set time length. Then, the planning unit runs at another frequency that is independent of the operating frequency of the prediction unit, and each time it obtains the latest perception information at the current moment, and obtains the prediction result of the corresponding time period according to the current time.

[0044] How to determine whether the first frequency meets the preset condition will be described in detail below.

[0045] As described above, the first frequency of the prediction unit needs to meet a preset condition so that the planning unit generates a planning result based on different prediction results in two adjacent time periods. Therefore, the preset condition is determined based on the first frequency and the first time length of the prediction unit, and the second frequency and the second time length of the planning unit.

[0046] For example, assuming that the first frequency of the prediction unit is f prediction , the second frequency of the planning unit is f planning , then the first running step length t of the prediction unit prediction =1 / f prediction , and the second operation step length of the planning unit is t planning =1 / f planning , and assuming that the prediction unit can predict n t backwards each time planning The prediction result of the duration, and the planning unit needs to use k t each time planning The predicted results of duration.

[0047] Then the result observed at time T1 will be prediction The time is stored, for example, in the system cache, and the timestamps of each prediction result are T1, T1+t planning ,…,T1+n×t planning .

[0048] When T1+t prediction <T2≤T1+2×t prediction When the planning unit reuses the prediction results in the cache, the timestamps of the prediction results used are T2, T2+t planning ,…,T2+k×t planning Then, to ensure that the asynchronous planning results of the planning unit use different prediction results, the following conditions need to be met:

[0049] T1+2×t prediction +k×t planning ≤T1+n×t planning

[0050] In this way, the preset condition that the first frequency needs to meet can be obtained as follows:

[0051]

[0052]

[0053] Figure 2 The flowchart illustrates an example of a process of determining a preset condition in a planning result generating method according to an embodiment of the present application.

[0054] like Figure 2 As shown, in Figure 1 Based on the embodiment shown, the method further includes step S140, determining the preset condition based on the first frequency, the second frequency, the first time length and the second time length. In addition, step S140 specifically includes the following steps.

[0055] Step S141: According to the second frequency, obtain the operation step length of the planning unit, that is, t planning .

[0056] Step S142: Obtain the first running step number corresponding to the first time length, that is, n as described above, according to the first time length and the running step.

[0057] Step S143: Obtain the number of second running steps corresponding to the second time length, that is, k as described above, according to the second time length and the running step length.

[0058] Step S144, determining the preset condition based on the first frequency, the second frequency, the first operation step number and the second operation step number. prediction 、f planning , n and k need to meet the preset conditions.

[0059] And, as described above, when determining the preset condition based on the first frequency, the second frequency, the first running step number and the second running step number, the difference between the first running step number and the second running step number, that is, the value of nk, is first calculated.

[0060] Then, the preset condition of the first frequency is determined according to the difference and the second frequency. For example, as described above, the preset condition of the first frequency is greater than or equal to the product of the quotient of 2 and the difference and the second frequency.

[0061] Therefore, when the above-mentioned preset conditions are met, the prediction unit only needs to be at least By running at a frequency of , it can be ensured that the planning unit can obtain the latest prediction results every time.

[0062] For example, suppose the planning unit needs to run at a frequency of 10Hz, while the prediction unit can only run at a maximum frequency of 3Hz due to computing power limitations. The planning unit needs 5s of prediction results each time, while the prediction unit can provide 6s of prediction results each time. If the traditional single-threaded operation mode is adopted, the entire system can only work at a frequency of 3Hz, which is far from meeting actual needs.

[0063] After adopting the asynchronous operation method according to the embodiment of the present application, because f planning =10, and t planning = 0.1s, we can calculate n = 60, k = 50, then f planningThe theoretical lower limit is 2 Hz. That is, the prediction unit only needs to work at a frequency greater than or equal to 2 Hz, and the actual operating frequency of 3 Hz can fully meet the demand due to the limitation of computing power.

[0064] Therefore, by Figure 2 The process of determining the preset conditions shown can make the entire system including the prediction module and the planning module run faster, reduce the demand for computing power to a certain extent, and save computing costs. In addition, due to the reduced demand for computing power, the prediction algorithm of the prediction unit can occupy more computing resources, achieve better prediction results, and thus improve the performance of the entire system.

[0065] In addition, it is worth noting that in the embodiment of the present application, when the first frequency of the prediction unit and the second frequency of the planning unit do not satisfy the above equation, the first frequency of the prediction unit and the second frequency of the planning unit can be made to satisfy the above equation by increasing the first running step number n or reducing the second running step number k. Moreover, the first running step number and the second running step number are respectively related to the first time length and the second time length, so the first frequency can be made to meet the preset condition by adjusting the first time length and the second time length. That is, when the first frequency does not meet the preset condition, the first time length and the second time length can be adjusted based on the first frequency and the second frequency.

[0066] Figure 3 The flowchart illustrates an example of a process of generating a planning result in a planning result generating method according to an embodiment of the present application.

[0067] like Figure 3 As shown, in Figure 1 Based on the illustrated embodiment, step S130 includes the following steps.

[0068] Step S131, the planning unit obtains the perception result used by the prediction unit to generate the prediction result at the start time point of the second time length. That is, the planning unit obtains the latest perception result while generating the planning result, so as to correct the prediction result of the prediction unit.

[0069] Step S132, the prediction result at the start time point of the first time length is corrected with the perception result to obtain a corrected prediction result. That is, if there is a deviation between the actual perception result and the prediction result, the prediction result will be corrected in real time. And if there is a newly perceived target, this target will also be added.

[0070] Step S133: Generate the planning result based on the corrected prediction result within the second time length. In this way, by generating the planning result based on the corrected prediction result, the accuracy of the planning result can be improved.

[0071] For example, if the prediction unit obtains the prediction result within 0 to 5 seconds, and the planning unit makes the plan within 3 to 4 seconds, the prediction result within 3 to 4 seconds needs to be used to generate the planning result. During correction, after the planning unit obtains the perception result in the 3rd second, because the prediction result of the prediction unit within 0 to 5 seconds is based on the prediction result at 0 seconds, the perception result needs to be used to correct the prediction result of the prediction unit at 0 seconds, so as to obtain the corrected prediction result within 3 to 4 seconds.

[0072] Thus, by Figure 3 The process of generating planning results shown can correct the prediction results according to the latest perception information and supplement the newly emerging goals to improve the accuracy of the production planning results.

[0073] As described above, since the planning unit and the prediction unit operate asynchronously, in order for the planning unit to conveniently obtain the prediction result of the prediction unit, the prediction result is stored in the cache unit.

[0074] That is, in the planning result generating method according to the embodiment of the present application, generating the prediction result with a first time length as a period by a prediction unit running at a first frequency includes: storing the prediction result in a cache unit.

[0075] Figure 4 A schematic diagram of an operation example of a planning result generating method according to an embodiment of the present application is illustrated.

[0076] like Figure 4 As shown in the figure, at time T1, the prediction module obtains the perception results and performs a round of prediction, and predicts the obstacle trajectory from time T1 to time T1+n. After the trajectory is predicted, the prediction result will be placed in a cache area, and the cache is indexed by the timestamp. Before the new prediction result is updated to the cache area, the prediction result at time T1 will be used repeatedly until the new prediction result is calculated. Assuming that the planning module needs the prediction of the current time and the next k times, when calling the prediction result, it will obtain the results of time T2 to time T2+k from the cache according to the timestamp T2 of the current time, and then correct and supplement the prediction generated at time T1 according to the information of all obstacles actually observed at time T2. The final corrected result is used to participate in the planning at time T2.

[0077] As described above, in the embodiment of the present application, the relationship between the first frequency and the second frequency is not limited. That is, even if the first frequency of the prediction unit is the same as the second frequency of the planning unit, the prediction unit and the planning unit may have different triggering moments, thereby operating in an asynchronous manner.

[0078] In addition, in the embodiment of the present application, the asynchronous operation mode is not limited to one prediction unit and one planning unit. There may be multiple prediction units and multiple planning units, which operate asynchronously with each other.

[0079] For example, in the planning result generating method according to an embodiment of the present application, generating a prediction result with a first time length as a period by a prediction unit running at a first frequency includes: generating another prediction result with a third time length as a period by another prediction unit running at a third frequency different from the first frequency.

[0080] Alternatively, in the planning result generating method according to an embodiment of the present application, obtaining the prediction result with a second time length as a period by a planning unit operating at a second frequency includes: obtaining the prediction result or the other prediction result with a fourth time length as a period by another planning unit operating at a fourth frequency different from the second frequency.

[0081] In addition, even the same prediction unit or the same planning unit can work at a variable frequency, for example, this can deal with the situation where the frequency of the prediction unit or the planning unit itself is unstable. Alternatively, it is also possible to switch between prediction units and planning units running at different frequencies to improve the application scenarios where the prediction unit and the planning unit run asynchronously.

[0082] In addition, because in the planning result generation method according to the embodiment of the present application, in each calculation cycle of the prediction unit, the planning unit will run one or several cycles, obtain different time periods of the same prediction result in different cycles, and reuse the output of a single prediction, the prediction module can be run at a lower frequency. Moreover, because it is not necessary to maintain precise synchronization between the prediction unit and the planning unit, even if the performance of the prediction unit or the planning unit is unstable, when one unit needs to be restarted, it will not affect each other.

[0083] Exemplary Devices

[0084] Figure 5 The figure illustrates a block diagram of a planning result generating device according to an embodiment of the present application.

[0085] like Figure 5As shown, according to an embodiment of the present application, a planning result generating device 200 includes: a result generating unit 210, which is used to generate a prediction result with a first time length as a period by a prediction unit running at a first frequency; a result acquiring unit 220, which is used to acquire the prediction result with a second time length as a period by a planning unit running at a second frequency; and a planning generating unit 230, which is used to generate a planning result by the planning unit based on the prediction result within the second time length acquired by the result acquiring unit when the first frequency meets a preset condition.

[0086] Figure 6 A block diagram illustrating an example of a condition determination unit of a planning result generating device according to an embodiment of the present application is illustrated.

[0087] like Figure 6 As shown, in Figure 5 On the basis of the illustrated embodiment, the planning result generating device 200 further includes a condition determination unit 240, which is used to determine the preset condition based on the first frequency, the second frequency, the first time length and the second time length.

[0088] Furthermore, if Figure 6 As shown, the condition determination unit 240 includes: a step length acquisition subunit 241, used to obtain the operating step length of the planning unit according to the second frequency; a first quantity acquisition subunit 242, used to obtain the first operating step length quantity corresponding to the first time length according to the first time length and the operating step length obtained by the step length acquisition subunit 241; a second quantity acquisition subunit 243, used to obtain the second operating step length quantity corresponding to the second time length according to the second time length and the operating step length obtained by the step length acquisition subunit 241; a condition determination subunit 244, used to determine the preset condition based on the first frequency, the second frequency, the first operating step length quantity obtained by the first quantity acquisition subunit 242, and the second operating step length quantity obtained by the second quantity acquisition subunit 243.

[0089] In one example, in the above-mentioned planning result generating device 200, the condition determination subunit 244 is used to: calculate the difference between the first number of running steps and the second number of running steps; and determine the preset condition according to the difference and the second frequency.

[0090] In one example, the above-mentioned planning result generating device 200 further includes: an adjusting unit, which is used to adjust the first time length and the second time length based on the first frequency and the second frequency when the first frequency does not meet the preset condition.

[0091] Figure 7 A block diagram of an example of a planning generation unit of a planning result generation device according to an embodiment of the present application is illustrated.

[0092] like Figure 7 As shown, in Figure 5 On the basis of the illustrated embodiment, the planning generation unit 230 includes: a perception result acquisition subunit 231, which is used to acquire, through the planning unit, the perception result used for the prediction unit to generate the prediction result at the starting time point of the second time length; a prediction result correction subunit 232, which is used to correct the prediction result at the starting time point of the first time length with the perception result acquired by the perception result acquisition subunit 231 to obtain a corrected prediction result; and a planning result generation subunit 233, which is used to generate the planning result based on the corrected prediction result of the prediction result correction subunit 232 within the second time length.

[0093] In one example, in the above-mentioned planning result generating device 200, the result generating unit 210 is used to: store the prediction result in a cache unit.

[0094] In one example, in the above-mentioned planning result generating device 200, the result generating unit 210 is used to: generate another prediction result with a third time length as a period by another prediction unit running at a third frequency different from the first frequency.

[0095] In one example, in the above-mentioned planning result generating device 200, the result obtaining unit 220 is used to: obtain the prediction result or the other prediction result with a fourth time length as a period through another planning unit running at a fourth frequency different from the second frequency.

[0096] Here, those skilled in the art can understand that the specific functions and operations of the various units and modules in the above-mentioned planning result generating device 200 have been described in the above reference. Figures 1 to 4 It has been introduced in detail in the description of the planning result generation method, and therefore, its repeated description will be omitted.

[0097] As described above, the planning result generating device 200 according to the embodiment of the present application can be implemented in various terminal devices, such as an on-board automatic driving system. In one example, the planning result generating device 200 according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the planning result generating device 200 can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the planning result generating device 200 can also be one of the many hardware modules of the terminal device.

[0098] Alternatively, in another example, the planning result generating apparatus 200 and the terminal device may also be separate devices, and the planning result generating apparatus 200 may be connected to the terminal device via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0099] Exemplary Electronic Devices

[0100] Below, reference Figure 8 To describe an electronic device according to an embodiment of the present application.

[0101] Figure 8 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0102] like Figure 8 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0103] The processor 13 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0104] The memory 12 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the planning result generation method of each embodiment of the present application described above and / or other desired functions. Various contents such as prediction results may also be stored in the computer-readable storage medium.

[0105] In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0106] The input device 13 may include, for example, a keyboard, a mouse, etc.

[0107] The output device 14 can output various information to the outside, including planning results, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0108] Of course, to simplify, Figure 8Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0109] Exemplary computer program products and computer-readable storage media

[0110] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the planning result generation method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0111] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0112] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the planning result generation method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0113] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0114] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0115] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0116] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0117] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0118] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for generating planning results for an autonomous driving scenario, comprising: Generate a prediction result with a first time length as a period by a prediction unit running at a first frequency; The prediction result is obtained by a planning unit running at a second frequency with a second time length as a period; wherein the second time length is different from the first time length, and the planning unit and the prediction unit run asynchronously; When the first frequency meets a preset condition, generating a planning result based on the prediction result within the second time length by a planning unit; and Determining the preset condition based on the first frequency, the second frequency, the first time length, and the second time length includes: Obtaining an operation step length of the planning unit according to the second frequency; According to the first time length and the running step length, obtaining the first running step length quantity corresponding to the first time length; According to the second time length and the running step length, obtaining the number of second running steps corresponding to the second time length; determining the preset condition based on the first frequency, the second frequency, the first number of operating steps, and the second number of operating steps; Wherein, determining the preset condition based on the first frequency, the second frequency, the first running step number, and the second running step number includes: Calculating a difference between the first number of running steps and the second number of running steps; and The preset condition is determined according to the difference and the second frequency.

2. The planning result generating method according to claim 1, further comprising: When the first frequency does not meet the preset condition, the first time length and the second time length are adjusted based on the first frequency and the second frequency.

3. The planning result generation method according to claim 1, wherein: Generating a planning result based on the prediction result within the second time length by a planning unit includes: Acquiring, by a planning unit at a starting time point of the second time length, a perception result used by the prediction unit to generate the prediction result; Correcting the prediction result at the start time point of the first time length with the perception result to obtain a corrected prediction result; and The planning result is generated based on the corrected prediction result within the second time length.

4. The planning result generation method according to claim 1, wherein: Generating a prediction result with a first time length as a period by a prediction unit running at a first frequency includes: The prediction result is stored in a cache unit.

5. The planning result generation method according to claim 1, wherein: Generating a prediction result with a first time length as a period by a prediction unit running at a first frequency includes: Another prediction result is generated with a third time length as a period by another prediction unit operating at a third frequency different from the first frequency.

6. The planning result generation method according to claim 5, wherein: Acquiring the prediction result with a second time length as a period by a planning unit operating at a second frequency includes: The prediction result or the another prediction result is obtained with a fourth time length as a period by another planning unit operating at a fourth frequency different from the second frequency.

7. A planning result generating device for an autonomous driving scenario, comprising: A result generating unit, configured to generate a prediction result with a first time length as a period by using a prediction unit running at a first frequency; A result acquisition unit, configured to acquire the prediction result with a second time length as a period through a planning unit running at a second frequency; wherein the second time length is different from the first time length, and the planning unit and the prediction unit run asynchronously; and a planning generating unit, configured to generate a planning result by the planning unit based on the prediction result within the second time length acquired by the result acquiring unit when the first frequency meets a preset condition; a condition determination unit, configured to determine the preset condition based on the first frequency, the second frequency, the first time length, and the second time length; The condition determination unit includes: a step length acquisition subunit, which is used to obtain the operation step length of the planning unit according to the second frequency; a first quantity acquisition subunit, which is used to obtain the first operation step length quantity corresponding to the first time length according to the first time length and the operation step length obtained by the step length acquisition subunit; a second quantity acquisition subunit, which obtains the second operation step length quantity corresponding to the second time length according to the second time length and the operation step length obtained by the step length acquisition subunit; a condition determination subunit, which is used to determine the preset condition based on the first frequency, the second frequency, the first operation step length quantity obtained by the first quantity acquisition subunit, and the second operation step length quantity obtained by the second quantity acquisition subunit; wherein determining the preset condition based on the first frequency, the second frequency, the first operation step length quantity, and the second operation step length quantity includes: Calculating a difference between the first number of running steps and the second number of running steps; and The preset condition is determined according to the difference and the second frequency.

8. An electronic device comprising: processor; as well as A memory, in which computer program instructions are stored, and when the computer program instructions are executed by the processor, the processor executes the planning result generating method according to any one of claims 1 to 6.

Images