Method for improving an automatic driving system and corresponding system

Description

TECHNICAL FIELDS

[0001] The present invention is directed to a method for updating an autonomous driving system, and a corresponding system.BACKGROUND

[0002] Existing autonomous vehicles provide a variety of vehicle driving modes, such as a manual driving mode, an assisted driving mode, and an autonomous driving mode. The manual driving mode corresponds to Level 0 autonomy. The assisted driving mode corresponds to Level 1 autonomy. The autonomous driving mode corresponds to Level 2 to Level 5 autonomy. The autonomous driving mode is a mode in which an autonomous driving system of an autonomous vehicle conducts planning and control for autonomous driving of the autonomous vehicle. In the manual driving mode, the autonomous driving system is in an inactive state and does not operate. In the autonomous driving mode, the autonomous driving system is in an active state.

[0003] PCT application WO 2018 / 030082 A1 filed by Imai Masato et al. discloses an automatic driving device that includes a control program for inputting outside information and vehicle information, and outputting a target control value for a vehicle. The control program has a first program for generating a first target control amount on the basis of a dynamically changing algorithm (which outputs operations based on learning function or artificial intelligence), and a second program for generating a second target control amount on the basis of a prescribed algorithm.

[0004] European patent application EP3272611A1 filed by Motomura Hideto et al. discloses an information processing system that estimates a driving conduct includes: a detector that detects a vehicle environment state, which is at least one of surroundings of a vehicle and a driving state of the vehicle; a behavior learning unit configured to cause a neural network to learn a relationship between the vehicle environment state detected by the detector and a behavior of the vehicle implemented after the vehicle environment state; and a behavior estimation unit configured to estimate a behavior of the vehicle by inputting, into the neural network that learned, the vehicle environment state detected at a current point in time by the detector.

[0005] Another PCT application WO2018163288A1 filed by Hiramatsu Machiko discloses a travel assistance method used in a vehicle capable of switching between automatic driving and manual driving by a driver, the braking distance when stopping at an intersection during manual driving by the driver is learned, and the braking distance when there is no preceding vehicle in front of the vehicle is preferentially learned.

[0006] Since different drivers may have different driving habits, an autonomous driving system should be updated according to the driving habits of a driver without compromising the reliability of the planning and decision-making of autonomous driving, to cater to the driving habits of the driver and improve the driving experience for the driver.SUMMARY

[0007] In a first aspect, an embodiment of the present invention provides a method for updating an autonomous driving system that issues no instruction to control the driving of a vehicle in a manual driving mode. The method includes: acquiring a first path of the vehicle in the manual driving mode; acquiring data of a first sensor group and data of a second sensor group; generating environment sensing information and positioning information according to the data of the first sensor group; planning a second path for the vehicle in an autonomous driving mode according to the environment sensing information, the positioning information, and the data of the second sensor group; and updating the autonomous driving system according to the first path and the second path.

[0008] In some embodiments, the first sensor group includes a camera, a lidar, a millimeter wave radar, a GPS, and / or an IMU; and the second sensor group includes a wheel speed sensor, a speed sensor, an acceleration sensor, and / or a steering angle sensor.

[0009] According to the invention, updating the autonomous driving system according to the first path and the second path includes: determining a deviation between the first path and the second path; determining a driving behavior grade in the manual driving mode according to the first path and the data of at least one sensor of the second sensor group; and updating the autonomous driving system according to the deviation and the driving behavior grade.

[0010] According to the invention, determining the driving behavior grade in the manual driving mode according to the first path and the data of the at least one sensor of the second sensor group includes: sending the first path and the data of the second sensor group to a cloud server; and receiving the driving behavior grade from the cloud server.

[0011] In some embodiments, updating the autonomous driving system according to the deviation and the driving behavior grade includes: determining a correspondence if the deviation is greater than a preset first deviation threshold and the driving behavior grade is a first grade; and updating a planning and control algorithm of the autonomous driving system according to the correspondence, wherein the correspondence indicates that the environment sensing information, the positioning information, and the data of the second sensor group correspond to the first path, and wherein the autonomous driving system plans a path for the vehicle in the autonomous driving mode as the first path according to the environment sensing information, the positioning information, the data of the second sensor group, and the correspondence.

[0012] In some embodiments, the method further includes: recording a mileage of the first path as a test mileage for autonomous driving if the deviation is less than or equal to a preset second deviation threshold value.

[0013] In some embodiments, the method further includes: identifying abnormal data in the data of the second sensor group; to avoid the occurrence of the abnormal data, determining dynamics estimation data and an estimated time corresponding to the dynamics estimation data; determining a control instruction for an underlying vehicle execution system according to the dynamics estimation data; determining, according to the estimated time, historical environment sensing information and historical positioning information generated at the estimated time; and establishing a correspondence indicating that the historical environment sensing information and the historical positioning information correspond to the control instruction.

[0014] In a second aspect, the invention further provides a system including an autonomous driving system and a cloud server, the system being defined by claim 4.

[0015] In some embodiments, the third subunit is configured to: determine a correspondence if the deviation is greater than a preset first deviation threshold and the driving behavior grade is a first grade; and update a planning and control algorithm of the autonomous driving system according to the correspondence, wherein the correspondence indicates that the environment sensing information, the positioning information, and the data of the second sensor group correspond to the first path, and wherein autonomous driving system plans a path for the vehicle in the autonomous driving mode as the first path according to the environment sensing information, the positioning information, the data of the second sensor group and the correspondence.

[0016] In some embodiments, the autonomous driving system further includes: a recording unit configured to record a mileage of the first path as a test mileage for autonomous driving if the deviation is less than or equal to a preset second deviation threshold value.

[0017] In some embodiments, the autonomous driving system further includes a reverse analysis unit configured to: identify abnormal data in the data of the second sensor group; to avoid the occurrence of the abnormal data, determine dynamics estimation data and an estimated time corresponding to the dynamics estimation data; determine a control instruction for an underlying vehicle execution system according to the dynamics estimation data; determine, according to the estimated time, historical environment sensing information and historical positioning information generated at the estimated time; and establish a correspondence indicating that the historical environment sensing information and the historical positioning information correspond to the control instruction.

[0018] In a third aspect, an embodiment of the present invention further provides an on-board apparatus, including: a processor, a memory, and a communication interface, wherein the processor, the memory and the communication interface are coupled to one another through a bus system; and wherein the processor is configured to perform the steps of the method of the first aspect by executing a computer program stored in the memory.

[0019] As shown, in at least one of the embodiments of the present invention, in a manual driving mode, the autonomous driving system also senses the surrounding environment of a vehicle, performs vehicle positioning, and plans a path for autonomous driving for the vehicle according to environment sensing information, positioning information, and the data of vehicle sensors. However, the autonomous driving system does not issue an instruction to control the driving of the vehicle. Instead, it compares the path with a path along which a driver drives the vehicle in the manual driving mode to update a planning and control algorithm of the autonomous driving system, such that the updated autonomous driving system better caters to the driving habits of the driver and improves the driving experience for the driver without compromising the reliability of planning and decision-making of autonomous driving.BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to illustrate more clearly embodiments of the present invention or technical schemes in the prior art, the drawings used in description of the embodiments or the prior art will be briefly described below. Obviously, the drawings in the following description only describe some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be derived on the basis of these drawings without any inventive effort. FIG. 1 is a diagram of a general architecture of an autonomous vehicle in accordance with an embodiment of the present invention. FIG. 2 is a schematic diagram of an on-board apparatus in accordance with an embodiment of the present invention. FIG. 3 is a flowchart of a method for updating an autonomous driving system in accordance with an embodiment of the present invention. FIG. 4 is a block diagram of an autonomous driving system in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to better understand the above objects, features and advantages of the present invention, the present invention will be further described in detail with reference to the drawings and embodiments. It can be understood that the embodiments described herein are only some of but not all embodiments of the present invention. The particular embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0022] FIG. 1 is a diagram of a general architecture of an autonomous vehicle in accordance with an embodiment of the present invention. As shown in FIG. 1, data collected by a first sensor group may include but are not limited to data of the external environment and position data of the vehicle. As an example, the first sensor group may include but is not limited to at least one of a camera, a lidar, a millimeter wave radar, a global positioning system (GPS), and an inertial measurement unit (IMU). The autonomous driving system can acquire the data of the first sensor group.

[0023] The data collected by the second sensor group may include but are not limited to the dynamics data of the vehicle. As an example, the second sensor group may include but is not limited to at least one of a wheel speed sensor, a speed sensor, an acceleration sensor, and a steering angle sensor. The autonomous driving system can acquire the data of the second sensor group.

[0024] In a manual driving mode, a driver drives the vehicle by operating the devices for controlling the driving of the vehicle. As an example, the devices for controlling the driving of the vehicle may include but are not limited to a brake pedal, a steering wheel, and an accelerator pedal. The devices for controlling the driving of the vehicle can directly operate an underlying vehicle execution system to control the driving of the vehicle. The underlying vehicle execution system may control the driving of the vehicle. The underlying vehicle execution system may include a steering system, a braking system, and a powertrain.

[0025] The autonomous driving system may be a software system running on an operating system. An on-board hardware system may be a hardware system supporting the operations of the operating system. The autonomous driving system may make planning and decisions for autonomous driving of the vehicle according to a planning and control algorithm. The autonomous driving system can communicate and exchange various information with a cloud server wirelessly.

[0026] The autonomous driving system issues no instruction to control the driving of the vehicle in a manual driving mode. The autonomous driving system can realize the steps provided by the embodiments of methods for updating an autonomous driving system. The steps may include, for example, steps I to V as shown below: I. acquiring a first path of the vehicle in the manual driving mode; II. acquiring data of a first sensor group and data of a second sensor group; III. generating environment sensing information and positioning information according to the data of the first sensor group; IV. planning a second path for the vehicle in an autonomous driving mode according to the environment sensing information, the positioning information, and the data of the second sensor group; and V. updating the autonomous driving system according to the first path and the second path.

[0027] In the manual driving mode, the autonomous driving system also senses the surrounding environment of the vehicle, performs vehicle positioning, and plans a path for autonomous driving for the vehicle according to environment sensing information, positioning information, and data of vehicle sensors. However, the autonomous driving system does not issue an instruction to control the driving of the vehicle. Instead, it compares the path with a path along which a driver drives the vehicle in the manual driving mode to update a planning and control algorithm of the autonomous driving system. As such, the updated autonomous driving system better caters to the driving habits of the driver, which may improve the driving experience for the driver without compromising the reliability of planning and decision-making of autonomous driving.

[0028] FIG. 2 is a schematic diagram of an on-board apparatus in accordance with an embodiment of the present invention.

[0029] The on-board apparatus shown in FIG. 2 may include at least a processor 201, memory 202, and a user interface 203. The various components of the on-board apparatus are coupled to one another through a bus system 204. It can be understood that the bus system 204 may be configured to facilitate connection and communication between these components. The bus system 204 may include a power bus, a control bus and a status signal bus in addition to a data bus. However, for clarity of illustration, various buses are generally labeled as the bus system 204 in FIG. 2.

[0030] The user interface 203 may include a display, a keyboard, a pointing device (e.g., a mouse, a trackball, a touch pad, etc.).

[0031] It can be understood that the memory 202 in this embodiment may be a volatile memory or a nonvolatile memory or may include both volatile and nonvolatile memories. The nonvolatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM) or a flash memory. The volatile memory may be a random-access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM may be used, such as a static RAM (SRAM), a dynamic RAM (DRAM), synchronous DRAM (SDRAM), a double data rate SDRAM (DDRSDRAM), an enhanced SDRAM (ESDRAM), a synchlink DRAM (SLDRAM) and a direct Rambus RAM (DRRAM). The memory 202 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0032] In some embodiments, the memory 202 may store the following elements, executable units or data structures, or a subset or superset thereof: an operating system 2021 and an application program 2022.

[0033] The operating system 2021 may include various system programs, such as a framework layer, a core library layer and a drive layer, to implement various basic services and handle hardware-based tasks. The application program 2022 may include various application programs, such as a media player and a browser, to implement various application services. A program implementing a method of the embodiments of the present invention may be included in the application program 2022.

[0034] In an embodiment of the present invention, the processor 201 may be configured to execute a program or instructions stored in the memory 202, particularly the program or instructions stored in the application program 2022, to perform the steps of a method for updating an autonomous driving system in accordance with some embodiments. The steps may include, for example, steps I to V as shown below: I. acquiring a first path of the vehicle in the manual driving mode; II. acquiring data of a first sensor group and data of a second sensor group; III. generating environment sensing information and positioning information according to the data of the first sensor group; IV. planning a second path for the vehicle in an autonomous driving mode according to the environment sensing information, the positioning information, and the data of the second sensor group; and V. updating the autonomous driving system according to the first path and the second path.

[0035] The method disclosed in the above embodiment of the present invention can be applied to the processor 201 or implemented by the processor 201. The processor 201 may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above method can be performed by an integrated logic circuit of hardware in the processor 201 or instructions in the form of software. The above-mentioned processor 201 may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor. The steps of the method disclosed in connection with the embodiments of the present invention can be directly embodied as implementation by a hardware decoding processor, or by a combination of hardware and software units of the decoding processor. The software unit can be located in a sophisticated storage medium in the art such as a random-access memory, a flash memory, a read-only memory, a programmable read-only memory or electrically erasable programmable memory, a register, etc. The storage medium may be located in the memory 202, and the processor 201 reads the information in the memory 202 and performs the steps of the above method in combination with its hardware.

[0036] It can be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for implementing the functions described herein, or combinations thereof.

[0037] For software implementation, the technique scheme described herein may be implemented by units that perform the functions described herein. Software codes may be stored in memory and executed by a processor. The memory may be implemented in the processor or external to the processor.

[0038] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical scheme. Specialized technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0039] Those skilled in the art can clearly understand that for convenience and conciseness of description, the specific working processes of the above-described systems, devices and units can refer to the corresponding processes in the above-described embodiments of the method and will not be further described here.

[0040] In the embodiments provided in this invention, it should be understood that the execution order can be adjusted arbitrarily unless there is an expressly stated order between the steps of the methods. The disclosed device and method can be realized in alternative ways. For example, the apparatus embodiments described above are only for illustration. For example, the division of the units is only a logic function division. In actual implementation, there may be other division methods, for example, multiple units or assemblies may be combined or integrated into another system, or some features may be omitted or not implemented. Further, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

[0041] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0042] In addition, the functional units in each embodiment of the present invention may be integrated into one processing unit, or each unit may physically exist separately, or two or more units may be integrated into one unit.

[0043] If the functions are implemented in the form of functional units of software and sold or used as independent products, they can be stored in a computer-readable storage medium. On the basis of this understanding, the substance or the parts that contribute to the existing technology or a part of the technical schemes of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present invention. The aforementioned storage medium includes USB drive, mobile hard disk drive, ROM, RAM, magnetic disk or optical disk and other mediums that can store program codes.

[0044] FIG. 3 is a flowchart of a method for updating an autonomous driving system in accordance with an embodiment of the present invention. The method may be performed by an on-board apparatus.

[0045] As shown in FIG. 3, according to a method for updating an autonomous driving system disclosed in this embodiment, the autonomous driving system issues no instruction to control the driving of a vehicle in a manual driving mode. The method may include the following steps 301 to 305: 301. acquiring a first path of the vehicle in the manual driving mode; 302. acquiring data of a first sensor group and data of a second sensor group; 303. generating environment sensing information and positioning information according to the data of the first sensor group; 304. planning a second path for the vehicle in an autonomous driving mode according to the environment sensing information, the positioning information, and the data of the second sensor group; and 305. updating the autonomous driving system according to the first path and the second path.

[0046] In this embodiment, in a manual driving mode, a driver drives the vehicle by operating devices for controlling the driving of the vehicle. As an example, the devices for controlling the driving of the vehicle may include but are not limited to a brake pedal, a steering wheel, and an accelerator pedal. The devices for controlling the driving of the vehicle can directly operate an underlying vehicle execution system to control the driving of the vehicle. The underlying vehicle execution system may control the driving of the vehicle, and the underlying vehicle execution system may include a steering system, a braking system, and a powertrain.

[0047] When the driver drives the vehicle, the autonomous driving system can acquire the data of the first sensor group. The data collected by the first sensor group may include but are not limited to data of the external environment and position data of the vehicle. As an example, the first sensor group may include but is not limited to at least one of a camera, a lidar, a millimeter wave radar, a global positioning system (GPS) and an inertial measurement unit (IMU). The autonomous driving system can acquire the data of the first sensor group.

[0048] Therefore, the autonomous driving system can generate environment sensing information and positioning information based on the data of the first sensor group. Specifically, the autonomous driving system may generate environment sensing information and positioning information based on the sensing data and positioning data.

[0049] When the driver drives the vehicle, the autonomous driving system can also acquire the data of the second sensor group. The data collected by the second sensor group may include but are not limited to the dynamics data of the vehicle. As an example, the second sensor group may include but is not limited to at least one of a wheel speed sensor, a speed sensor, an acceleration sensor, and a steering angle sensor.

[0050] Therefore, the autonomous driving system can plan a second path for the vehicle in an autonomous driving mode according to the environment sensing information, the positioning information, and the data of the second sensor group. Specifically, the autonomous driving system may make planning and decisions according to the environment sensing information, positioning information, and dynamics data, to derive the second path for the vehicle in the autonomous driving mode.

[0051] In the manual driving mode, the autonomous driving system also senses the surrounding environment of a vehicle, performs vehicle positioning, and plans a path for autonomous driving for the vehicle according to environment sensing information, positioning information, and data of vehicle sensors. However, the autonomous driving system does not issue an instruction to control the driving of the vehicle. Instead, it compares the path with a path along which a driver drives the vehicle in the manual driving mode to update a planning and control algorithm of the autonomous driving system. As such, the updated autonomous driving system better caters to the driving habits of the driver and improves the driving experience for the driver without compromising the reliability of planning and decision-making of autonomous driving.

[0052] According to the invention, updating the autonomous driving system according to the first path and the second path in step 303 includes the following steps (1) to (3): (1) determining a deviation between the first path and the second path; (2) determining a driving behavior grade in the manual driving mode according to the first path and the data of at least one sensor of the second sensor group; and (3) updating the autonomous driving system according to the deviation and the driving behavior grade.

[0053] According to the invention, the autonomous driving system determines the deviation between the first path and the second path, and the determination of the deviation between the two paths can use an existing method, which will not be detailed here.

[0054] Since the first path is a path along which the driver drives the vehicle, and the data of the second sensor group may include vehicle dynamics data, which can reflect the driving state of the vehicle, it can be determined whether the driver's driving behavior is abnormal according to the first path and the data of at least one sensor in the second sensor group. For example, if the vehicle has experienced abnormal events such as sharp turning, emergency braking and fast overtaking, it means that the driver's behavior is abnormal.

[0055] According to the invention, the driving behavior grade in the manual driving mode may be used to evaluate whether the driver's behavior is abnormal. The first grade of driving behavior may indicate no abnormality, and the second grade of driving behavior may indicate abnormality. In specific applications, different grades can be used to express different degrees of how well or how badly a driver behaves.

[0056] After the deviation between the first path and the second path and the driving behavior grade are determined, it can be determined whether to update the planning and control algorithm of the autonomous driving system.

[0057] If the driver's behavior is abnormal, no update may be performed. If the driver's behavior is not abnormal, an update may be performed, so that the decision-making and planning of the autonomous driving system based on the updated planning and control algorithm better caters to the driver's habits and improves the driving experience for the driver.

[0058] According to the invention, determining a driving behavior grade in the manual driving mode according to the first path and the data of at least one sensor of the second sensor group includes the following steps (1) and (2): (1) sending the first path and the data of the second sensor group to a cloud server; and (2) receive the driving behavior grade from the cloud server.

[0059] According to the invention, the autonomous driving system sends the first path and the data of the second sensor group to the cloud server, and the cloud server may be responsible for determining the driving behavior grade. The cloud server determines the driving behavior grade and then sends it to the autonomous driving system to reduce the workload of the autonomous driving system.

[0060] In addition, the processing capacity of the cloud server may be much greater than that of the on-board hardware devices on which the autonomous driving system depends. It can determine the driving behavior grade faster and meet the real-time requirements of the autonomous driving system.

[0061] Since the first path is a path along which the driver drives the vehicle, and the data of the second sensor group includes vehicle dynamics data, which can reflect the driving state of the vehicle, the cloud server can determine whether the driver's driving behavior is abnormal according to the first path and the data of at least one sensor in the second sensor group. For example, if the vehicle has experienced abnormal events such as sharp turning, emergency braking and fast overtaking, it means that the driver's behavior is abnormal.

[0062] In addition, if the cloud server determines that the driver's behavior is abnormal, a log file is generated and stored for the driver or other professionals to check and analyze.

[0063] In some embodiments, updating the autonomous driving system according to the deviation and the driving behavior grade may include the following steps (1) and (2): (1) determining a correspondence if the deviation is greater than a preset first deviation threshold and the driving behavior grade is a first grade; and (2) updating a planning and control algorithm of the autonomous driving system according to the correspondence, wherein the correspondence indicates that the environment sensing information, the positioning information, and the data of the second sensor group correspond to the first path, and wherein the autonomous driving system plans a path for the vehicle in the autonomous driving mode as the first path according to the environment sensing information, the positioning information, the data of the second sensor group and the correspondence.

[0064] In this embodiment, the first deviation threshold may indicate that the second path planned by the autonomous driving system is considerably different from the first path along which the driver controls the vehicle and therefore does not conform to the operating habits of the driver.

[0065] If the deviation is greater than the first deviation threshold and the driving behavior grade is the first grade (that is, the driver's behavior is not abnormal), the planning and control algorithm of the autonomous driving system may be updated, such that the updated autonomous driving system better caters to the driving habits of the driver and improves the driving experience for the driver without compromising the reliability of the planning and decision-making of autonomous driving.

[0066] If the deviation is less than or equal to the preset second deviation threshold, the second path planned by the autonomous driving system may not be much different from the first path along which the driver controls the vehicle and therefore may conform to the driver's operating habits and no update may be needed. Also, a mileage of the first path can be recorded as a test mileage for autonomous driving. The second deviation threshold may be less than or equal to the first deviation threshold.

[0067] In some embodiments, the method for updating an autonomous driving system may further include a reverse analysis process, which specifically includes the following steps (1) to (5): (1) identifying abnormal data in the data of the second sensor group; (2) to avoid the occurrence of the abnormal data, determining dynamics estimation data and an estimated time corresponding to the dynamics estimation data; (3) determining a control instruction for an underlying vehicle execution system according to the dynamics estimation data; (4) determining, according to the estimated time, historical environment sensing information and historical positioning information generated at the estimated time; and (5) establishing a correspondence indicating that the historical environment sensing information and the historical positioning information correspond to the control instruction.

[0068] In this embodiment, the abnormal data can be understood as abnormal data corresponding to abnormal events such as sharp turning, emergency braking, and fast overtaking.

[0069] To avoid the occurrence of the abnormal data by determining the dynamics estimation data and the estimated time corresponding to the dynamics estimation data, the control instruction for the underlying vehicle execution system corresponding to the dynamics estimation data and the historical environment sensing information and historical positioning information generated at the estimated time can be determined.

[0070] By establishing a correspondence indicating that the historical environment sensing information and the historical positioning information correspond to the control instruction, the autonomous driving system may generate the control instruction to avoid the occurrence of the occurrence of abnormal events if the autonomous driving system determines that environmental sensing information is the historical environment sensing information and positioning information is the historical positioning information during autonomous driving.

[0071] As shown in FIG. 4, this embodiment discloses an autonomous driving system that issues no instruction to control the driving of a vehicle in a manual driving mode. The autonomous driving system may include a first acquisition unit 41, a second acquisition unit 42, a generation unit 43, a planning unit 44, and an updating unit 45, which are detailed below.

[0072] The first acquisition unit 41 is configured to acquire a first path of the vehicle in the manual driving mode.

[0073] The second acquisition unit 42 is configured to acquire data of a first sensor group and data of a second sensor group.

[0074] The generation unit 43 is configured to generate environment sensing information and positioning information according to the data of the first sensor group.

[0075] The planning unit 44 is configured to plan a second path for the vehicle in an autonomous driving mode according to the environment sensing information, the positioning information, and the data of the second sensor group.

[0076] The updating unit 45 is configured to update the autonomous driving system according to the first path and the second path.

[0077] In some embodiments, the first sensor group may include a camera, a lidar, a millimeter wave radar, a GPS, and / or an IMU; and the second sensor group may include a wheel speed sensor, a speed sensor, an acceleration sensor, and / or a steering angle sensor.

[0078] According to the invention, the updating unit 45 includes: a first subunit configured to determine a deviation between the first path and the second path; a second subunit configured to determine a driving behavior grade in the manual driving mode according to the first path and the data of at least one sensor of the second sensor group; and a third subunit configured to update the autonomous driving system according to the deviation and the driving behavior grade.

[0079] According to the invention, the second subunit is configured to: send the first path and the data of the second sensor group to a cloud server; and receive the driving behavior grade from the cloud server.

[0080] In some embodiments, the third subunit may be configured to: determine a correspondence if the deviation is greater than a preset first deviation threshold and the driving behavior grade is a first grade; and update a planning and control algorithm of the autonomous driving system according to the correspondence, wherein the correspondence indicates that the environment sensing information, the positioning information, and the data of the second sensor group correspond to the first path, and wherein the autonomous driving system plans a path for the vehicle in the autonomous driving mode as the first path according to the environment sensing information, the positioning information, the data of the second sensor group and the correspondence.

[0081] In some embodiments, the autonomous driving system may further include: a recording unit configured to record a mileage of the first path as a test mileage for autonomous driving if the deviation is less than or equal to a preset second deviation threshold value.

[0082] In some embodiments, the autonomous driving system may further include a reverse analysis unit configured to: identify abnormal data in the data of the second sensor group; to avoid the occurrence of the abnormal data, determine dynamics estimation data and an estimated time corresponding to the dynamics estimation data; determine a control instruction for an underlying vehicle execution system according to the dynamics estimation data; determine, according to the estimated time, historical environment sensing information and historical positioning information generated at the estimated time; and establish a correspondence indicating that the historical environment sensing information and the historical positioning information correspond to the control instruction.

[0083] The autonomous driving system disclosed in the above embodiments can realize the methods for updating the autonomous driving system disclosed in the above method embodiments and will not be repeated here to avoid repetition.

[0084] It should be noted that in this context, the terms "comprise," "include" or any variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or device that includes a series of elements not only includes those listed elements but also includes other elements not expressly listed or further includes elements inherent to such a process, method, article, or device. Without additional restrictions, an element defined by the phrase "comprising a / an ..." does not exclude the presence of a further identical element in the process, method, article or device that includes the element.INDUSTRIAL APPLICABILITY

[0085] The method for updating an autonomous driving system, system and on-board apparatus provided by the embodiments of the present invention also sense the surrounding environment of a vehicle, perform vehicle positioning, and plan a path for autonomous driving for the vehicle according to environment sensing information, positioning information, and data of vehicle sensors. However, the autonomous driving system does not issue an instruction to control the driving of the vehicle. Instead, it compares the path with a path along which a driver drives the vehicle in the manual driving mode to update a planning and control algorithm of the autonomous driving system. As such, the updated autonomous driving system better caters to the driving habits of the driver and improves the driving experience for the driver without compromising the reliability of planning and decision-making of autonomous driving.

Claims

1. (Currently Amended) A method for updating an autonomous driving system, the autonomous driving system issuing no instruction to control the driving of a vehicle in a manual driving mode, the method comprising the steps of: acquiring (301) a first path of the vehicle in the manual driving mode, wherein the first path is a path along which a driver drives the vehicle; acquiring (302) data of a first sensor group and data of a second sensor group; generating (303) environment sensing information and positioning information according to the data of the first sensor group; planning (304) a second path for the vehicle in an autonomous driving mode according to the environment sensing information, the positioning information, and the data of the second sensor group; and updating (305) the autonomous driving system according to the first path and the second path wherein the updating comprises: determining a deviation between the first path and the second path; determining a driving behavior grade in the manual driving mode according to the first path and data of at least one sensor of the second sensor group; comprising: sending the first path and the data of the second sensor group to a cloud server, determining, by the cloud server, that the driving behavior of the driver is abnormal according to the first path and the data of at least one sensor in the second sensor group; responsive to determining, by the cloud server, the driving behavior of the driver is abnormal, generating and storing a log file for the driver for analysis. receiving the driving behavior grade from the cloud server; and updating the autonomous driving system according to the deviation and the driving behavior grade.

2. (Previously Presented) The method of claim 1, wherein the first sensor group comprises at least one of a camera, a lidar, a millimeter wave radar, a GPS, or an IMU, and wherein the second sensor group comprises at least one of a wheel speed sensor, a speed sensor, an acceleration sensor, or a steering angle sensor.

3. (Previously Presented) The method of claim 1, wherein updating the autonomous driving system according to the deviation and the driving behavior grade comprises: determining a correspondence if the deviation is greater than a preset first deviation threshold and the driving behavior grade is a first grade; and updating a planning and control algorithm of the autonomous driving system according to the correspondence, wherein the correspondence indicates that the environment sensing information, the positioning information, and the data of the second sensor group correspond to the first path, and wherein the autonomous driving system plans a path for the vehicle in the autonomous driving mode as the first path according to the environment sensing information, the positioning information, the data of the second sensor group and the correspondence.

4. (Currently Amended) A system including an autonomous driving system that issues no instructions to control the driving of a vehicle in a manual driving mode, and that also includes a cloud server; the autonomous driving system comprising: a first acquisition unit (41) configured to acquire a first path of the vehicle in the manual driving mode, wherein the first path is a path along which a driver drives the vehicle; a second acquisition unit (42) configured to acquire data of a first sensor group and data of a second sensor group; a generation unit (43) configured to generate environment sensing information and positioning information according to the data of the first sensor group; a planning unit (44) configured to plan a second path for the vehicle in an autonomous driving mode according to the environment sensing information, the positioning information, and the data of the second sensor group; and an updating unit (45) configured to update the autonomous driving system according to the first path and the second path, wherein the updating unit (45) comprises: a first subunit configured to determine a deviation between the first path and the second path; a second subunit configured to determine a driving behavior grade in the manual driving mode according to the first path and data of at least one sensor of the second sensor group wherein the second subunit is configured to: send the first path and the data of the second sensor group to the cloud server and to receive the driving behavior grade from the cloud server; and a third subunit configured to update the autonomous driving system according to the deviation and the driving behavior grade, wherein the cloud server determines that driving behavior of the driver is abnormal according to the first path and the data of at least one sensor in the second sensor group, wherein the cloud server generates and stores a log file for the driver for analysis based on determining the driving behavior of the driver.

5. (Previously Presented) The system of claim 4, wherein the first sensor group comprises at least one of a camera, a lidar, a millimeter wave radar, a GPS, or an IMU, and wherein the second sensor group comprises at least one of a wheel speed sensor, a speed sensor, an acceleration sensor, or a steering angle sensor.

6. (Previously Presented) The system of claim 4, wherein the third subunit is configured to: determine a correspondence if the deviation is greater than a preset first deviation threshold and the driving behavior grade is a first grade; and update a planning and control algorithm of the autonomous driving system according to the correspondence, wherein the correspondence indicates that the environment sensing information, the positioning information, and the data of the second sensor group correspond to the first path, and wherein the autonomous driving system plans a path for the vehicle in the autonomous driving mode as the first path according to the environment sensing information, the positioning information, the data of the second sensor group and the correspondence.