WO2019047604A1

WO2019047604A1 - Method and device for determining data collection line

Info

Publication number: WO2019047604A1
Application number: PCT/CN2018/094489
Authority: WO
Inventors: 姜雨; 郁浩; 闫泳杉; 郑超; 唐坤; 张云飞
Original assignee: 百度在线网络技术（北京）有限公司
Priority date: 2017-09-05
Filing date: 2018-07-04
Publication date: 2019-03-14
Also published as: CN107767487B; CN107767487A

Abstract

Provided are a method and device for determining a data collection line for collecting automatic drive training data. The method comprises: acquiring by a computer device a preconfigured data collection line, the driving time ratio of a straightway to a curve being estimated to be 1:1; recording actual driving data of multiple times of the data collection line, the actual driving data of each time comprising the respective driving time of the straightway and the curve; and according to the actual driving data, amending the data collection line so as to converge the driving time ratio to 1: 1. By planning the data collection line, the uniformity of end-to-end automatic driving training data is improved.

Description

Method and device for determining data acquisition route

This patent application claims Chinese patent application filed on September 5, 2017, with the application number 201710792219.3, the applicant is Baidu Online Network Technology (Beijing) Co., Ltd., and the invention name is "a method and device for determining the data collection route". The priority of this application is hereby incorporated by reference in its entirety.

Technical field

The present invention relates to the field of autonomous driving technologies, and in particular, to a technique for determining a data acquisition route for collecting training data for automatic driving.

Background technique

In the existing end-to-end automatic driving model training, the training data provided for the training model is based on single or multiple fixed acquisition routes. These acquisition routes do not take into account the influence of data imbalance between the curve and the straight channel, such as The cornering speed is slow, the corners are small, the straight speed is fast, and the straight path is long, which causes serious data imbalance. The collected curve data and the straight track data are not balanced, which is fatal to the end-to-end model training.

Summary of the invention

It is an object of the present invention to provide a method, apparatus and computer apparatus, computer readable storage medium and computer program product for determining a data acquisition route for collecting training data for autonomous driving.

According to an aspect of the present invention, a method for determining a data collection route for collecting training data for automatic driving is provided, wherein the method includes:

Obtain a preset data collection route, wherein the travel time of the straight road and the curve is estimated to be 1:1;

Recording a plurality of actual driving data of the data collection route, wherein each actual driving data includes a respective driving time of the straight road and the curved road;

The data acquisition route is corrected based on the actual travel data to converge the travel time ratio to 1:1.

According to an aspect of the present invention, there is also provided an apparatus for determining a data collection route for collecting training data of an automatic driving, wherein the apparatus comprises:

Means for obtaining a preset data acquisition route, wherein the travel time of the straight track and the curve is estimated to be 1:1;

Means for recording a plurality of actual driving data of the data collection route, wherein each actual driving data includes a respective driving time of a straight road and a curved road;

And means for correcting the data acquisition route according to the actual driving data to make the driving time ratio converge to 1:1.

According to an aspect of the present invention, a computer apparatus is provided, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program according to A method of determining a data collection route in accordance with an aspect of the present invention.

According to an aspect of the present invention, there is also provided a computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements a determination data acquisition route in accordance with an aspect of the present invention Methods.

According to an aspect of the present invention, there is also provided a computer program product, when the computer program product is executed by a computer device, implementing a method of determining a data collection route in accordance with an aspect of the present invention.

Compared with the prior art, the present invention adopts a dynamically modified data acquisition route, which is a brand-new attempt, which is applied to such as curve fitting, projection, and connection technology, which is an end-to-end automatic in the field of computational geometry. A groundbreaking combination in the field of driving engineering. By planning the data collection route, the invention improves the uniformity of the end-to-end automatic driving training data, thereby improving the ability of the trained driving model, and the stability and safety of the automatic driving are greatly improved.

DRAWINGS

Other features, objects, and advantages of the present invention will become more apparent from the Detailed Description of Description

1 shows a block diagram of an exemplary computer system/server 12 suitable for implementing embodiments of the present invention;

2 illustrates a flow chart of a method of determining a data acquisition route for acquiring training data for automated driving, in accordance with one embodiment of the present invention;

3 shows a schematic diagram of an apparatus for determining a data acquisition route for collecting training data for automatic driving, in accordance with another embodiment of the present invention.

The same or similar reference numerals in the drawings denote the same or similar components.

Detailed ways

Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as a process or method depicted as a flowchart. Although the flowcharts describe various operations as a sequential process, many of the operations can be implemented in parallel, concurrently or concurrently. In addition, the order of operations can be rearranged. The process may be terminated when its operation is completed, but may also have additional steps not included in the figures. The processing may correspond to methods, functions, procedures, subroutines, subroutines, and the like.

By "computer device" in this context is meant an intelligent electronic device that can perform predetermined processing, such as numerical calculations and/or logical calculations, by running a predetermined program or instruction, which can include a processor and a memory, executed by the processor The program instructions pre-stored in the memory are used to execute a predetermined process, or are executed by hardware such as an ASIC, an FPGA, a DSP, or the like, or a combination of the two. Computer devices include, but are not limited to, servers, personal computers (PCs), notebook computers, tablets, smart phones, and the like.

The computer device includes, for example, a user device and a network device. The user equipment includes, but is not limited to, a personal computer (PC), a notebook computer, a mobile terminal, etc., and the mobile terminal includes but is not limited to a smart phone, a PDA, etc.; the network device includes but is not limited to a single network server, and more A network of server servers or a cloud-based cloud consisting of a large number of computers or network servers, where cloud computing is a type of distributed computing, a super-virtual set of a loosely coupled set of computers. computer. Wherein, the computer device can be operated separately to implement the present invention, and can also access the network and implement the present invention by interacting with other computer devices in the network. The network in which the computer device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.

It should be noted that the user equipment, the network equipment, the network, and the like are merely examples, and other existing or future possible computer equipment or networks, such as those applicable to the present invention, are also included in the scope of the present invention. It is included here by reference.

The methods discussed later herein, some of which are illustrated by flowcharts, can be implemented in hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to carry out the necessary tasks can be stored in a machine or computer readable medium, such as a storage medium. The processor(s) can perform the necessary tasks.

The specific structural and functional details disclosed are merely representative and are for the purpose of describing exemplary embodiments of the invention. The present invention may, however, be embodied in many alternative forms and should not be construed as being limited only to the embodiments set forth herein.

It should be understood that although the terms "first," "second," etc. may be used herein to describe the various elements, these elements should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, a first unit could be termed a second unit, and similarly a second unit could be termed a first unit, without departing from the scope of the exemplary embodiments. The term "and/or" used herein includes any and all combinations of one or more of the associated listed items.

The terminology used herein is for the purpose of describing the particular embodiments, The singular forms "a", "an", It is also to be understood that the terms "comprises" and / or "comprising", "the", "the" Other features, integers, steps, operations, units, components, and/or combinations thereof.

It should also be noted that in some alternative implementations, the functions/acts noted may occur in a different order than that illustrated in the drawings. For example, two figures shown in succession may in fact be executed substantially concurrently or sometimes in the reverse order, depending on the function/acts involved.

The invention is further described in detail below with reference to the accompanying drawings.

FIG. 1 illustrates a block diagram of an exemplary computer system/server 12 suitable for use in implementing embodiments of the present invention. The computer system/server 12 shown in FIG. 1 is merely an example and should not impose any limitation on the function and scope of use of the embodiments of the present invention.

As shown in FIG. 1, computer system/server 12 is embodied in the form of a general purpose computing device. The components of computer system/server 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and bus 18 that connects different system components, including system memory 28 and processing unit 16.

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures. For example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA Bus, a Video Electronics Standards Association (VESA) local bus, and peripheral component interconnects ( PCI) bus.

Computer system/server 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer system/server 12, including both volatile and non-volatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32. Computer system/server 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (not shown in Figure 1, commonly referred to as "hard disk drives"). Although not shown in FIG. 1, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and a removable non-volatile disk (such as a CD-ROM, DVD-ROM) may be provided. Or other optical media) read and write optical drive. In these cases, each drive can be coupled to bus 18 via one or more data medium interfaces. Memory 28 can include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more applications, other programs Modules and program data, each of these examples or some combination may include an implementation of a network environment. Program module 42 typically performs the functions and/or methods of the described embodiments of the present invention.

Computer system/server 12 may also be in communication with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), and may also be in communication with one or more devices that enable a user to interact with the computer system/server 12. And/or in communication with any device (e.g., network card, modem, etc.) that enables the computer system/server 12 to communicate with one or more other computing devices. This communication can take place via an input/output (I/O) interface 22. Also, computer system/server 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through network adapter 20. As shown, network adapter 20 communicates with other modules of computer system/server 12 via bus 18. It should be understood that although not shown in FIG. 1, other hardware and/or software modules may be utilized in conjunction with computer system/server 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems. , tape drives, and data backup storage systems.

Processing unit 16 executes various functional applications and data processing by running programs stored in memory 28.

For example, the memory 28 stores therein a computer program for performing the functions and processes of the present invention, and when the processing unit 16 executes the corresponding computer program, the identification of the incoming call intention at the network side by the present invention is implemented.

The specific functions/steps of the present invention for determining a data acquisition route for collecting training data for autonomous driving will be described in detail below.

2 shows a method flow diagram in accordance with one embodiment of the present invention, which specifically illustrates a process for determining a data acquisition route for acquiring training data for automated driving.

As shown in FIG. 2, in step S1, the computer device acquires a preset data collection route, wherein the travel time ratio of the straight track and the curve is estimated to be 1:1; in step S2, the computer device records the data collection route. a plurality of actual driving data, wherein each actual driving data includes respective driving times of the straight road and the curved road; in step S3, the computer device corrects the data collecting route according to the actual driving data, so that the The travel time ratio converges to 1:1.

Specifically, in step S1, the computer device acquires a preset data collection route, wherein the travel time ratio of the straight track to the curve is estimated to be 1:1.

Here, in order to finally obtain a data acquisition route in which the travel time of the straight track and the curve converges to 1:1, it is possible to collect the balanced training data from the data acquisition route for the training of the automatic driving model, in the preset data. When collecting routes, the travel time between straight and curved roads is estimated to be 1:1.

The presupposition of the data collection route can be performed by any computing device having route planning capabilities, such as the computer device of the present invention. Alternatively, the data collection route can also be preset by experience based on experience, for example, an experienced driver predetermines the travel time of the straight track and the curve compared to the estimated data acquisition route of 1:1, such as manual setting. Multiple track points, the computer device fits these track points to get a data acquisition route.

The driving route of the vehicle is a second-order guideable smooth curve, so the data acquisition route can be mathematically modeled as a combination of straight-arc-sprung spiral. Among them, the data acquisition route includes straight roads and curved roads. The straight roads are characterized by straight lines. The curved roads are characterized by circular arc lines and snail spirals. The horn spirals are used to connect two circular arc lines and circular arc lines and straight lines.

Further, since the travel speeds required by different road sections are different, for example, some road sections have a minimum speed limit, and some road sections have a maximum speed limit. When these speed limit road traffic signs are projected into a data acquisition route, the data collection route is taken. A speed control point is generated to mark the maximum speed or the minimum speed of a certain line, and the corresponding line segment is weighted in a positive correlation with the required speed.

Therefore, the straight track may include a plurality of straight lines, and a straight line may be further divided into a plurality of straight line segments, wherein each straight line segment has different speed limit requirements, for example, a line from A to B, and C is a line on the line. For the speed control point, the maximum speed limit of the straight line AC is 80 km/h, and the maximum speed limit of the straight line CB is 60 km/h. Similarly, the curve may also include a plurality of arc lines and a snail spiral, and an arc line or a snail spiral may be further divided into a plurality of arc segments, each of which also has a different limit. Speed requirements.

Here, the present invention obtains balanced training data for various models of automatic driving, and the data collection route for training data acquisition can be driven in a closed scene. Closed scenes can be set, for example, by limited scenes, limited routes, limited ranges, typically for example a closed campus with limited coverage, where the routes that can be traveled end-to-end are also limited and can be encountered It is also limited.

Typically, the data collection route is a closed loop route that travels in a closed scene, ie the start and end points are the same. Alternatively, the data collection route may be an end-to-end route in a closed scene where the start and end points are different, but the travel time of the straight and curved roads is estimated to be 1:1.

In addition, in the present invention, in order to finally obtain a data acquisition route in which the travel time of the straight track and the curve converges to 1:1, a plurality of data acquisition routes may be preset to subsequently respectively respectively preset the respective data according to the actual driving data. The data collection route is corrected to select one route from the plurality of data acquisition routes obtained after the correction as the final data collection route.

In step S2, the computer device records a plurality of actual driving data of the preset data collection route, wherein each actual driving data includes respective driving times of the straight road and the curved road.

Here, the actual number of travels of the preset data collection route may be set according to a predetermined number of times, or set according to a predetermined period.

For example, the actual number of travels is set to 10 times, the driver travels 10 times according to the preset data collection route, and the computer equipment records the travel data of the 10 travels, wherein each travel time includes a straight line in the preset data acquisition route. The driving time of each corner. Subsequently, the computer device can correct the preset data acquisition route according to the 10 actual driving data.

For another example, the predetermined period is set to be daily, the driver travels multiple times per day according to the preset data collection route, and the computer device records the driving data for each driving in one day, wherein each driving time includes the respective driving time of the straight road and the curved road. Subsequently, the computer device can correct the preset data collection route according to the actual driving data in the day.

For another example, the number of times and the period can be set at the same time. For example, if the driver travels 10 times a day, the driver travels 10 times a day according to the preset data collection route, and the computer device records the driving data for each driving in one day, wherein each driving time includes a straight road and The driving time of each corner. Subsequently, the computer device can correct the preset data acquisition route according to the 10 actual driving data every day.

Here, the actual driving of the preset data collection route needs to introduce manual driving to obtain more realistic and reasonable driving data. Manual driving can't strictly follow the data collection route. It is always inevitable to deviate to the left or right. This can bring the possibility and guidance to the correction of the data collection route.

In step S3, the computer device corrects the preset data collection route according to the actual driving data of the preset data collection route, so that the traveling time ratio of the straight track and the curve converges to 1:1.

Here, if the running time of the straight road in the actual running is longer than the running time of the curved road, adjust the curve line in the data collecting route, for example, increase the curvature of the circular line; if the running time of the curved road is actually straighter than the straight running Travel long time, adjust the straight line in the data acquisition route, such as the length of the straight line.

The curved line includes a plurality of circular arc lines and a plurality of horn spirals, wherein each circular arc or horn spiral includes one or more arc segments having corresponding speed limit requirements, and the adjustment of the curved line includes Any of the following:

1) adjusting the turning radius and/or curvature of the circular arc;

For example, when the running time of the curve is shorter than the running time of the straight road, and the length of the curve needs to be increased at this time, the turning radius and/or curvature of the circular arc line may be increased to lengthen the curved length.

2) Adjust the curvature of the snail spiral.

The horn spiral is used as part of the curve to make a transition between a straight line and a circular line or between two circular lines. When the travel time of the curve is shorter than the travel time of the straight road, the curvature of the spiral of the horn can be increased to lengthen the curve.

Wherein, the straight line includes a plurality of straight lines, wherein each straight line includes one or more straight line segments having respective speed limit requirements, and the adjustment of the straight line includes adjusting the length and/or direction of the straight line.

For example, when the running time of the straight road is shorter than the running time of the curved road, and the length of the straight road needs to be increased at this time, the length of the straight line may be increased to lengthen the curved road length.

Stretching of a straight line can be done by adjusting the length and/or direction. For example, keep the direction of a straight line and stretch its length directly. For another example, the starting point of a straight line is a fixed point, and the direction is fine-tuned, and the length of the straight line can also be stretched.

Here, the adjustment of straight or curved roads combines geometrical calculations so that the travel time ratio of straight or curved roads can finally converge to 1:1. Adjustments to any line segment on the data acquisition route may result in adjustments to other connected line segments and may even need to be reconnected to one or more new line segments. Moreover, due to the adjustment of the straight line, the circular arc line or the horn spiral, a new speed control point will be generated on the data acquisition route, and the straight line segments and arc segments thus divided and their respective speed weights.

Further, the computer device counts the plurality of actual travel times obtained in step S2 for correction judgment.

For example, the computer equipment can average the straight travel time and the curve travel time in 10 trips to obtain the average travel time of the straight lane and the average travel time of the curve, thereby determining which of the two has a shorter average travel time. In order to increase the proportion of their travel time. This averaging method can effectively denoise, ie filter out the noise in these actual driving times.

For another example, the computer equipment can select the actual driving route when the running time of the straight road and the curve is relatively closer to 1:1 according to the actual driving time, and use the actual driving route as the modified collecting route to perform the data collecting route. Corrected so that the travel time ratio of straight and curved roads converges to 1:1.

In the present invention, the correction of the data acquisition route is iterative. In one correction process, the multiple actual travel data recorded in step S2 is used in step S3 to travel the data acquisition route toward the straight road and the curve. The time is corrected by 1:1, and then proceeds to the next correction process, and the plurality of actual travel data newly recorded in step S2 is used again for the travel time ratio of the data acquisition route to the straight track and the curve in step S3 is 1:1. A new round of corrections, such a loop iteration, until the travel time of the straight and the curve is converged to a data acquisition route of 1:1.

Here, the correction of the data acquisition route is always performed toward the actual 1:1, and the iteration correction of the data acquisition route makes the travel time ratio of the straight track and the curve in the final data acquisition route converge to 1:1.

Due to the calculation error and the inevitable instability of human driving, according to the statistics of the proportion of the straight roads collected, the data acquisition route is fine-tuned. As time goes by, the travel time ratio of straight and curved road will eventually converge. To almost 1:1.

3 shows a schematic diagram of a device in accordance with one embodiment of the present invention, specifically showing an apparatus for determining a data acquisition route for collecting training data for autonomous driving.

As shown in FIG. 3, the route determining device 300 is installed in a computer device, and further includes a route obtaining device 301, a data recording device 302, and a route correcting device 303.

The route obtaining device 301 acquires a preset data collection route, wherein the travel time ratio of the straight track and the curve is estimated to be 1:1; the data recording device 302 records the plurality of actual travel data of the data collection route, wherein each time The actual travel data includes the respective travel times of the straight lanes and the curved lanes; the route correction device 303 corrects the data acquisition route based on the actual travel data so that the travel time ratio converges to 1:1.

Specifically, the route obtaining device 301 acquires a preset data collection route, wherein the travel time ratio of the straight track to the curve is estimated to be 1:1.

Typically, the data collection route is a closed loop route that travels in a closed scene, that is, the start and end points are the same. Alternatively, the data collection route may be an end-to-end route in a closed scene where the start and end points are different, but the travel time of the straight and curved roads is estimated to be 1:1.

Subsequently, the data recording device 302 records a plurality of actual travel data of the preset data collection route, wherein each actual travel data includes the respective travel times of the straight lane and the curve.

For example, the actual number of travels is set to 10 times, the driver travels 10 times according to the preset data collection route, and the data recording device 302 records the travel data of the 10 travels, wherein each travel time includes the preset data acquisition route. The travel time of straight and curved roads. Subsequently, the route correction device 303 can correct the preset data acquisition route based on the 10 actual travel data.

For another example, the predetermined period is set to be daily, the driver travels multiple times per day according to the preset data collection route, and the data recording device 302 records the driving data for each driving in one day, wherein each driving time includes the respective driving of the straight road and the curved road. time. Subsequently, the route correction device 303 can correct the preset data collection route according to the actual travel data in the plurality of times per day.

For another example, the number of times and the period can be set at the same time. For example, if the driver travels 10 times a day, the driver travels 10 times a day according to the preset data collection route, and the data recording device 302 records the driving data for each driving in one day, wherein each driving time includes The travel time of straight and curved roads. Subsequently, the route correction device 303 can correct the preset data acquisition route based on the 10 actual travel data per day.

Here, the actual driving of the preset data collection route needs to introduce manual driving to obtain more realistic and reasonable driving data. Manual driving cannot strictly follow the data collection route, and it is always inevitable to deviate to the left or right, which can bring possible guidance and guidance to the correction of the data collection route.

The route correction device 303 corrects the preset data acquisition route according to the actual travel data of the preset data acquisition route, so that the travel time ratio of the straight track and the curve converges to 1:1.

1) adjusting the turning radius and/or curvature of the circular arc;

2) Adjust the curvature of the snail spiral.

Here, the adjustment of straight or curved roads combines geometrical calculations so that the travel time ratio of straight or curved roads can finally converge to 1:1. Adjustments to any of the line segments on the data acquisition route may result in adjustments to other connected line segments and may even need to be reconnected to one or more new line segments. Moreover, due to the adjustment of the straight line, the circular arc line or the horn spiral, a new speed control point will be generated on the data acquisition route, and the straight line segments and arc segments thus divided and their respective speed weights.

Further, the route correction means 303 counts the plurality of actual travel times obtained by the route correction means 303 for correction determination.

For example, the route correction device 303 can average the straight travel time and the curved travel time of the 10 travels to obtain the average travel time of the straight lane and the average travel time of the curve, thereby determining which of the two is the average travel time. Shorter in order to increase the proportion of their travel time. This averaging method can effectively denoise, ie filter out the noise in these actual driving times.

For another example, the route correction device 303 can select the actual travel route when the travel time of the straight lane and the curve is relatively closer to 1:1 according to the actual travel time, and use the actual travel route as the modified acquisition route to collect data. The route is corrected so that the travel time ratio of the straight track to the curve converges to 1:1.

In the present invention, the correction of the data acquisition route is iterative. In one correction process, the plurality of actual travel data recorded by the data recording device 302 is used by the route correction device 303 to face the data acquisition route toward the straight track and the curve. The travel time is corrected by 1:1, and then proceeds to the next correction process, and the plurality of actual travel data newly recorded by the data recording device 302 is again used by the route correction device 303 to compare the travel time of the data acquisition route toward the straight track and the curve. A new round of correction of 1:1, such a loop iteration, until the travel time of the straight and the curve is converged to a data acquisition route of 1:1.

It should be noted that the present invention can be implemented in software and/or a combination of software and hardware, for example, using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device. In one embodiment, the software program of the present invention may be executed by a processor to implement the steps or functions described above. Likewise, the software program (including related data structures) of the present invention can be stored in a computer readable recording medium such as a RAM memory, a magnetic or optical drive or a floppy disk and the like. Additionally, some of the steps or functions of the present invention may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions _.

Additionally, a portion of the invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide a method and/or solution in accordance with the present invention. The program instructions for invoking the method of the present invention may be stored in a fixed or removable recording medium and/or transmitted by a data stream in a broadcast or other signal bearing medium, and/or stored in a The working memory of the computer device in which the program instructions are run. Herein, an embodiment in accordance with the present invention includes a device including a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, triggering The apparatus operates based on the aforementioned methods and/or technical solutions in accordance with various embodiments of the present invention.

It is apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the invention is defined by the appended claims instead All changes in the meaning and scope of equivalent elements are included in the present invention. Any reference signs in the claims should not be construed as limiting the claim. In addition, it is to be understood that the word "comprising" does not exclude other elements or steps. A plurality of units or devices recited in the system claims can also be implemented by a unit or device by software or hardware. The first, second, etc. words are used to denote names and do not denote any particular order.

Claims

A method for determining a data collection route for collecting training data for automatic driving, wherein the method includes:

Obtain a preset data collection route, wherein the travel time of the straight road and the curve is estimated to be 1:1;

Recording a plurality of actual driving data of the data collection route, wherein each actual driving data includes a respective driving time of the straight road and the curved road;

The data acquisition route is corrected based on the actual travel data to converge the travel time ratio to 1:1.
The method of claim 1, wherein the correcting step comprises:

The data acquisition route is corrected according to the average travel time of each of the straight track and the curve in the plurality of actual travel data, so that the travel time ratio converges to 1:1.
The method of claim 1, wherein the correcting step comprises:

Selecting a modified acquisition route according to the plurality of actual driving data;

The data acquisition route is modified according to the modified acquisition route to converge the travel time ratio to 1:1.
The method according to any one of claims 1 to 3, wherein the correcting the data collection route specifically comprises:

If the running time of the straight road in the actual driving is longer than the running time of the curved road, adjust the curve line in the data collecting route;

If the travel time of the curve in actual driving is longer than the travel time of the straight road, the straight line in the data acquisition route is adjusted.
The method of claim 4, wherein the curve line comprises a plurality of circular arc lines and a plurality of claw spirals, wherein each of the circular arc lines or the horn spiral includes one or more of the respective speed limit requirements The arc segment, the adjustment of the curve line includes any of the following:

Adjusting the turning radius and/or curvature of the circular arc;

- Adjusting the curvature of the snail spiral.
The method of claim 4 wherein said straight line comprises a plurality of straight lines, wherein each straight line comprises one or more straight line segments having respective speed limit requirements, and adjusting said straight line comprises adjusting said straight line Length and / or direction.
The method of any of claims 1 to 6, wherein the data collection route comprises a closed loop route traveling in a closed scene.
A device for determining a data collection route, the data collection route is used for collecting training data of automatic driving, wherein the device comprises:

Means for obtaining a preset data acquisition route, wherein the travel time of the straight track and the curve is estimated to be 1:1;

Means for recording a plurality of actual driving data of the data collection route, wherein each actual driving data includes a respective driving time of a straight road and a curved road;

And means for correcting the data acquisition route according to the actual driving data to make the driving time ratio converge to 1:1.
The apparatus according to claim 8, wherein the correcting operation specifically comprises:

The data acquisition route is corrected according to the average travel time of each of the straight track and the curve in the plurality of actual travel data, so that the travel time ratio converges to 1:1.
The apparatus according to claim 8, wherein the correcting operation specifically comprises:

Selecting a modified acquisition route according to the plurality of actual driving data;

The data acquisition route is modified according to the modified acquisition route to converge the travel time ratio to 1:1.
The apparatus according to any one of claims 8 to 10, wherein the operation of correcting the data collection route specifically comprises:

If the running time of the straight road in the actual driving is longer than the running time of the curved road, adjust the curve line in the data collecting route;

If the travel time of the curve in actual driving is longer than the travel time of the straight road, the straight line in the data acquisition route is adjusted.
The apparatus according to claim 11, wherein said curve line comprises a plurality of circular arc lines and a plurality of claw spirals, wherein each of said circular arc lines or horn spirals includes one or more of said ones having respective speed limit requirements. The arc segment, the adjustment of the curve line includes any of the following:

Adjusting the turning radius and/or curvature of the circular arc;

- Adjusting the curvature of the snail spiral.
The apparatus of claim 11 wherein said straight track comprises a plurality of straight lines, wherein each straight line comprises one or more straight line segments having respective speed limit requirements, and adjusting said straight line comprises adjusting said straight line Length and / or direction.
Apparatus according to any one of claims 8 to 13 wherein the data collection route comprises a closed loop route traveling in a closed scene.
A computer device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor executes the computer program, as claimed in any one of claims 1 to The method described.
A computer readable storage medium having stored thereon a computer program, wherein the computer program is executed by a processor to implement the method of any one of claims 1 to 7.
A computer program product, which when the computer program product is executed by a computer device, implements the method of any one of claims 1 to 7.