Autonomous driving system, performance verification method and device, storage medium and vehicle

Abstract

The present application relates to the technical field of automatic driving, and particularly provides an automatic driving system, a performance verification method and device, a storage medium and a vehicle, aiming to solve the problem of how to reduce the performance verification cost and ensure effective performance verification of the automatic driving function. To this end, the first and second environment perception units can ensure the automatic driving function of the vehicle, the first and fourth perception results are fused, or the second and third perception results are fused, a data fusion result is obtained, the automatic driving performance of the vehicle can be verified based on the data fusion result in the vehicle operation process without affecting the automatic driving function, different environment perception upgrade versions are verified, the actual operation of the vehicle is not affected in the verification process, the time and road test cost of automatic driving performance verification are effectively saved, and the performance verification effect of the automatic driving function is improved.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and specifically provides an autonomous driving system, a performance verification method based on the autonomous driving system, a control device, a readable storage medium, and a vehicle. Background Technology

[0002] Advanced driver assistance systems (ADAS) and autonomous driving are attracting increasing attention, and system costs are becoming a growing challenge for OEMs and component manufacturers. Everyone is thinking about how to meet the growing needs of users while saving and reducing system costs.

[0003] Advanced driver assistance systems (ADAS) and autonomous driving require continuous upgrades and iterations. When releasing new software versions, traditional manufacturers often use simulation testing and extensive road testing to verify whether the new version represents a performance improvement or a performance regression compared to the previous version. This approach is typically costly.

[0004] Accordingly, the field needs a new performance verification scheme to address the above problems. Summary of the Invention

[0005] To overcome the above-mentioned shortcomings, this invention is proposed to provide a solution, or at least a partial solution, to the problem of how to reduce the cost of performance verification while ensuring effective performance verification of autonomous driving functions.

[0006] In a first aspect, the present invention provides an autonomous driving system, the system comprising a first environmental perception unit, a second environmental perception unit, a third environmental perception unit, a fourth environmental perception unit, and a companion fusion unit;

[0007] The first environmental perception unit is used to perform first environmental perception based on data collected by the vehicle's first on-board sensor and obtain a first perception result;

[0008] The second environmental perception unit is used to perform second environmental perception based on data collected by the vehicle's second on-board sensor and obtain a second perception result;

[0009] The third environmental perception unit is used to perform third environmental perception based on the data collected by the first vehicle-mounted sensor and obtain the third perception result.

[0010] The fourth environmental perception unit is used to perform fourth environmental perception based on the data collected by the second vehicle-mounted sensor and obtain the fourth perception result.

[0011] The third environmental perception is an upgraded version of the first environmental perception; the fourth environmental perception is an upgraded version of the second environmental perception.

[0012] The accompanying fusion unit is used to perform data fusion by using the first perception result and the fourth perception result as fusion input data, or to perform data fusion by using the second perception result and the third perception result as fusion input data.

[0013] In one technical solution of the above-mentioned autonomous driving system, the system further includes a time-division multiplexing unit;

[0014] The time-division multiplexing unit is used to determine the input data to the accompanying fusion unit through time-division multiplexing.

[0015] The input data is either the first perception result and the fourth perception result, or the second perception result and the third perception result.

[0016] In one technical solution of the above-mentioned autonomous driving system, the system includes an autonomous driving function module and a companion module;

[0017] The first environmental perception unit and the second environmental perception unit are disposed in the autonomous driving function module;

[0018] The third environmental sensing unit, the fourth environmental sensing unit, and the accompanying fusion unit are disposed in the accompanying module.

[0019] In one technical solution of the aforementioned autonomous driving system, the companion module further includes a companion driving control unit and a companion active safety control unit;

[0020] The accompanying driving control unit is used to obtain driving control commands for performance verification based on the data fusion results generated by the accompanying fusion unit.

[0021] The accompanying active safety control unit is used to obtain active safety control commands for performance verification based on the data fusion results generated by the accompanying fusion unit.

[0022] In a second aspect, the present invention provides a performance verification method based on an autonomous driving system, wherein the autonomous driving system is the autonomous driving system described in the above-mentioned autonomous driving system technical solution, and the method includes:

[0023] Acquire fused input data; wherein, in a first time period, the fused input data includes a first perception result and a fourth perception result; in a second time period, the fused input data includes a second perception result and a third perception result;

[0024] Based on the fusion input data, data fusion is performed through the accompanying fusion unit to obtain the data fusion result;

[0025] Based on the data fusion results, the autonomous driving performance of the vehicle is verified.

[0026] In one technical solution of the above-mentioned performance verification method based on an autonomous driving system, the step of acquiring fused input data includes:

[0027] The first time period and the second time period are determined by the time-division multiplexing unit of the autonomous driving system to obtain the fused input data.

[0028] In one technical solution of the above-mentioned performance verification method based on an autonomous driving system, the step of verifying the autonomous driving performance of the vehicle based on the data fusion result includes:

[0029] Based on the data fusion results, driving control commands for performance verification are obtained through the accompanying driving control unit of the autonomous driving system.

[0030] Based on the data fusion results, active safety control commands for performance verification are obtained through the accompanying active safety control unit of the autonomous driving system.

[0031] The autonomous driving performance is verified based on the driving control commands and the active safety control commands used for performance verification.

[0032] In one technical solution of the above-mentioned performance verification method based on an autonomous driving system, the step of obtaining driving control commands for performance verification through the accompanying driving control unit of the autonomous driving system based on the data fusion result includes:

[0033] Based on the data fusion results, environmental data of the vehicle's environment is constructed.

[0034] Based on the environmental data, the driving control commands used for performance verification are obtained through the accompanying driving control unit of the autonomous driving system.

[0035] In one technical solution of the above-mentioned performance verification method based on an autonomous driving system, the step of obtaining active safety control commands for performance verification through the accompanying active safety control unit of the autonomous driving system based on the data fusion result includes:

[0036] Based on the data fusion results and vehicle positioning data, the active safety control commands used for performance verification are obtained through the accompanying active safety control unit of the autonomous driving system.

[0037] In one technical solution of the above-mentioned performance verification method based on an autonomous driving system, the step of verifying the performance of the autonomous driving system according to the driving control command and the active safety control command used for performance verification includes:

[0038] The driving control commands used for performance verification are compared with the driving control commands used for driving control of the vehicle to obtain a driving control comparison result.

[0039] The active safety control commands used for performance verification are compared with the active safety control commands used for driving control of the vehicle to obtain active safety control comparison results.

[0040] The performance of the autonomous driving system is verified based on the comparison results of the driving control and the active safety control.

[0041] In one technical solution of the above-mentioned performance verification method based on an autonomous driving system, the method further includes:

[0042] The performance verification data and / or data fusion results and / or fusion input data and / or first perception results and / or second perception results and / or third perception results and / or fourth perception results and / or data collected by the first vehicle sensor and / or data collected by the second vehicle sensor and / or the vehicle's operating data are transmitted back.

[0043] In a third aspect, a control device is provided, comprising at least one processor and at least one storage device, the storage device being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to perform the performance verification method based on an autonomous driving system as described in any of the above-described technical solutions for the performance verification method based on an autonomous driving system.

[0044] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, the program codes being adapted to be loaded and run by a processor to perform the performance verification method based on an autonomous driving system as described in any of the above-described technical solutions for the performance verification method based on an autonomous driving system.

[0045] In a fifth aspect, a vehicle is provided, the vehicle comprising the autonomous driving system described in the above-described autonomous driving system technical solution and the control device described in the above-described control device technical solution.

[0046] The present invention comprises one or more of the following technical solutions: Beneficial effects:

[0047] In implementing the technical solution of this invention, the autonomous driving system includes a first environmental perception unit, a second environmental perception unit, a third environmental perception unit, a fourth environmental perception unit, and a fusion unit. The first and third environmental perception units receive the same input data, as do the second and fourth environmental perception units. The third environmental perception unit is an upgraded version of the first environmental perception unit, and the fourth environmental perception unit is an upgraded version of the second environmental perception unit. Through this configuration, the first and second environmental perception units of this invention can ensure the autonomous driving function of the vehicle. Furthermore, by fusing the first and fourth perception results, or by fusing the second and third perception results, a data fusion result can be obtained. This allows for performance verification of the vehicle's autonomous driving performance based on the data fusion result during vehicle operation without affecting the autonomous driving function. It enables effective verification of different upgraded versions of environmental perception, and the verification process does not affect the actual operation of the vehicle. This effectively saves time and road test costs for autonomous driving performance verification and significantly improves the performance verification effect of the autonomous driving function.

[0048] Solution 1. An autonomous driving system, characterized in that the system includes a first environmental perception unit, a second environmental perception unit, a third environmental perception unit, a fourth environmental perception unit, and a companion fusion unit;

[0049] The first environmental perception unit is used to perform first environmental perception based on data collected by the vehicle's first on-board sensor and obtain a first perception result;

[0050] The second environmental perception unit is used to perform second environmental perception based on data collected by the vehicle's second on-board sensor and obtain a second perception result;

[0051] The third environmental perception unit is used to perform third environmental perception based on the data collected by the first vehicle-mounted sensor and obtain the third perception result.

[0052] The fourth environmental perception unit is used to perform fourth environmental perception based on the data collected by the second vehicle-mounted sensor and obtain the fourth perception result.

[0053] The third environmental perception is an upgraded version of the first environmental perception; the fourth environmental perception is an upgraded version of the second environmental perception.

[0054] The accompanying fusion unit is used to perform data fusion by using the first perception result and the fourth perception result as fusion input data, or to perform data fusion by using the second perception result and the third perception result as fusion input data.

[0055] Option 2. The autonomous driving system according to Option 1, characterized in that the system further includes a time-division multiplexing unit;

[0056] The time-division multiplexing unit is used to determine the input data to the accompanying fusion unit through time-division multiplexing.

[0057] The input data is either the first perception result and the fourth perception result, or the second perception result and the third perception result.

[0058] Option 3. The autonomous driving system according to Option 1 or 2, characterized in that the system includes an autonomous driving function module and a companion module;

[0059] The first environmental perception unit and the second environmental perception unit are disposed in the autonomous driving function module;

[0060] The third environmental sensing unit, the fourth environmental sensing unit, and the accompanying fusion unit are disposed in the accompanying module.

[0061] Option 4. The autonomous driving system according to Option 3, characterized in that the companion module further includes a companion driving control unit and a companion active safety control unit;

[0062] The accompanying driving control unit is used to obtain driving control commands for performance verification based on the data fusion results generated by the accompanying fusion unit.

[0063] The accompanying active safety control unit is used to obtain active safety control commands for performance verification based on the data fusion results generated by the accompanying fusion unit.

[0064] Solution 5. A performance verification method based on an autonomous driving system, characterized in that the autonomous driving system is an autonomous driving system based on any one of Solutions 1-4, and the method includes:

[0065] Acquire fused input data; wherein, within a first time period, the fused input data includes the first perception result and the fourth perception result; within a second time period, the fused input data includes the second perception result and the third perception result;

[0066] Based on the fusion input data, data fusion is performed through the accompanying fusion unit to obtain the data fusion result;

[0067] Based on the data fusion results, the autonomous driving performance of the vehicle is verified.

[0068] Solution 6. The performance verification method based on the autonomous driving system described in Solution 5, characterized in that,

[0069] The acquisition of fused input data includes:

[0070] The first time period and the second time period are determined by the time-division multiplexing unit of the autonomous driving system to obtain the fused input data.

[0071] Solution 7. The performance verification method based on an autonomous driving system as described in Solution 5, characterized in that,

[0072] The step of verifying the autonomous driving performance of the vehicle based on the data fusion results includes:

[0073] Based on the data fusion results, driving control commands for performance verification are obtained through the accompanying driving control unit of the autonomous driving system.

[0074] Based on the data fusion results, active safety control commands for performance verification are obtained through the accompanying active safety control unit of the autonomous driving system.

[0075] The autonomous driving performance is verified based on the driving control commands and the active safety control commands used for performance verification.

[0076] Solution 8. The performance verification method based on an autonomous driving system as described in Solution 7, characterized in that,

[0077] Based on the data fusion results, the accompanying vehicle control unit of the autonomous driving system obtains driving control commands for performance verification, including:

[0078] Based on the data fusion results, environmental data of the vehicle's environment is constructed.

[0079] Based on the environmental data, the driving control commands used for performance verification are obtained through the accompanying driving control unit of the autonomous driving system.

[0080] Solution 9. The performance verification method based on an autonomous driving system as described in Solution 7, characterized in that,

[0081] The step of obtaining active safety control commands for performance verification through the accompanying active safety control unit of the autonomous driving system based on the data fusion result includes:

[0082] Based on the data fusion results and vehicle positioning data, the active safety control commands used for performance verification are obtained through the accompanying active safety control unit of the autonomous driving system.

[0083] Solution 10. The performance verification method based on an autonomous driving system according to Solution 7, characterized in that,

[0084] The performance verification of the autonomous driving performance based on the driving control commands and the active safety control commands used for performance verification includes:

[0085] The driving control commands used for performance verification are compared with the driving control commands used for driving control of the vehicle to obtain a driving control comparison result.

[0086] The active safety control commands used for performance verification are compared with the active safety control commands used for driving control of the vehicle to obtain active safety control comparison results.

[0087] The performance of the autonomous driving system is verified based on the comparison results of the driving control and the active safety control.

[0088] Solution 11. The performance verification method based on an autonomous driving system according to any one of Solutions 5 to 10, characterized in that the method further includes:

[0089] The performance verification data and / or data fusion results and / or fusion input data and / or first perception results and / or second perception results and / or third perception results and / or fourth perception results and / or data collected by the first vehicle sensor and / or data collected by the second vehicle sensor and / or the vehicle's operating data are transmitted back.

[0090] Scheme 12. A control device comprising at least one processor and at least one storage device, the storage device being adapted to store a plurality of program codes, characterized in that the program codes are adapted to be loaded and run by the processor to perform the performance verification method based on an autonomous driving system as described in any one of Schemes 5 to 11.

[0091] Scheme 13. A computer-readable storage medium storing a plurality of program codes, characterized in that the program codes are adapted to be loaded and run by a processor to perform the performance verification method based on an autonomous driving system as described in any one of Schemes 5 to 11.

[0092] Option 14. A vehicle, characterized in that the vehicle includes an automatic driving system as described in any one of Options 1-4 and a control device as described in Option 12. Attached Figure Description

[0093] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Wherein:

[0094] Figure 1 This is a schematic diagram of the main components of an autonomous driving system according to an embodiment of the present invention;

[0095] Figure 2 This is a schematic diagram of the main steps of a performance verification method based on an autonomous driving system according to an embodiment of the present invention;

[0096] Figure 3 A schematic diagram of the main implementation architecture for vehicle performance verification in existing technologies;

[0097] Figure 4 This is a schematic diagram of the main implementation architecture for vehicle performance verification according to one embodiment of the present invention. Detailed Implementation

[0098] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0099] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0100] See appendix Figure 3 , Figure 3 A schematic diagram of the main implementation architecture for vehicle performance verification in existing technologies. (Example) Figure 3As shown, in existing technologies, when verifying vehicle performance, data collected by onboard cameras, onboard LiDAR, and onboard millimeter-wave radar are often used as sensor input data. The perception model 1 in the accompanying domain, which enables the accompanying function, transmits data to the fusion module deployed in the accompanying domain through the accompanying App management module. The data management module then inputs data from the perception model 2 deployed in the accompanying domain into the accompanying fusion unit. The data from the accompanying fusion unit then enters the accompanying active safety planning and control or the accompanying environment model to verify active safety and driving functions, and to achieve data feedback. Here, the accompanying function refers to running the latest algorithm based on the same sensors in the system background, testing the performance of the latest algorithm on actual roads to achieve faster algorithm iteration efficiency and a better end-user experience.

[0101] The above methods require high costs for simulation testing and road testing. Accordingly, there is a need in this field for a new performance verification scheme.

[0102] See appendix Figure 1 , Figure 1 This is a schematic diagram of the main components of an autonomous driving system according to an embodiment of the present invention. Figure 1 As shown, the autonomous driving system in this embodiment of the invention mainly includes a first environmental perception unit, a second environmental perception unit, a third environmental perception unit, a fourth environmental perception unit, and a fusion unit. The first environmental perception unit is used to perform first environmental perception based on data collected by the vehicle's first on-board sensor and obtain a first perception result. The second environmental perception unit is used to perform second environmental perception based on data collected by the vehicle's second on-board sensor and obtain a second perception result. The third environmental perception unit is used to perform third environmental perception based on data collected by the first on-board sensor and obtain a third perception result. The fourth environmental perception unit is used to perform fourth environmental perception based on data collected by the second on-board sensor and obtain a fourth perception result. The third environmental perception is an upgraded version of the first environmental perception. The fourth environmental perception is an upgraded version of the second environmental perception. The fusion unit is used to perform data fusion by using the first perception result and the fourth perception result as fusion input data or by using the second perception result and the third perception result as fusion input data.

[0103] In this embodiment, the autonomous driving system is equipped with a first environmental perception unit and a third environmental perception unit for data collected by the first onboard sensor, and a second environmental perception unit and a fourth environmental perception unit for data collected by the second onboard sensor. The first environmental perception of the first environmental perception unit is an upgraded version of the third environmental perception of the third environmental perception unit. The second environmental perception of the second environmental perception unit is an upgraded version of the fourth environmental perception of the fourth environmental perception unit. In other words, the autonomous driving system sets up a first environmental perception unit and a third environmental perception unit for data collected by the first onboard sensor; and sets up a second environmental perception unit and a fourth environmental perception unit for data collected by the second onboard sensor. Thus, verifying the third environmental perception does not affect the function of the first environmental perception in the driving control process; similarly, verifying the fourth environmental perception does not affect the function of the second environmental perception in the driving control process.

[0104] It should be noted that the first, second, third, and fourth environmental perceptions can be perception algorithms targeting data collected by a specific type of vehicle-mounted sensor, or they can be a collection of perception algorithms targeting data collected by multiple vehicle-mounted sensors. For example, the first vehicle-mounted sensor data may be data collected by a vehicle-mounted camera, and the second vehicle-mounted sensor data may be data collected by a vehicle-mounted LiDAR. Alternatively, the first vehicle-mounted sensor data may be data collected by both a vehicle-mounted camera and a vehicle-mounted LiDAR, while the second vehicle-mounted sensor data may be data collected by a vehicle-mounted millimeter-wave radar, etc. All of these are within the scope of protection of this invention. When upgrading the environmental perception in an autonomous driving system, the performance of the upgraded environmental perception can be verified without affecting the functionality of the original environmental perception.

[0105] In one embodiment of the present invention, such as Figure 1 As shown, the autonomous driving system also includes a time-division multiplexing unit, which can be used to determine the input data of the input companion fusion unit through time-division multiplexing; the input data is the first perception result and the fourth perception result or the second perception result and the third perception result.

[0106] In one embodiment of the present invention, such as Figure 1 As shown, the autonomous driving system may include an autonomous driving function module and an accompanying module. A first environmental perception unit and a second environmental perception unit are located in the autonomous driving function module; a third environmental perception unit, a fourth environmental perception unit, and an accompanying fusion unit are located in the accompanying module. That is, the first and second environmental perception units are used to implement the autonomous driving function, while the third, fourth, and accompanying fusion units are used to implement accompanying functions to verify the performance of the upgraded environmental perception algorithm.

[0107] In one implementation, such as Figure 1 As shown, the companion module may also include a companion driving control unit and a companion active safety control unit; the companion driving control unit is used to obtain driving control commands for performance verification based on the data fusion results generated by the companion fusion unit; the companion active safety control unit is used to obtain active safety control commands for performance verification based on the data fusion results generated by the companion fusion unit.

[0108] In this embodiment, the data fusion results can be input to the accompanying vehicle control unit and the accompanying active safety control unit to obtain vehicle control commands and active safety control commands for performance verification, respectively, so as to perform performance verification of autonomous driving performance based on the vehicle control commands and active safety control commands for performance verification.

[0109] With the above configuration, the autonomous driving system of this embodiment includes a first environmental perception unit, a second environmental perception unit, a third environmental perception unit, a fourth environmental perception unit, and a fusion unit. The first and third environmental perception units input the same data, as do the second and fourth environmental perception units. The third environmental perception unit is an upgraded version of the first environmental perception unit, and the fourth environmental perception unit is an upgraded version of the second environmental perception unit. Through this configuration, the first and second environmental perception units of this embodiment can ensure the vehicle's autonomous driving function. Furthermore, by fusing the first and fourth perception results, or the second and third perception results, a data fusion result can be obtained. This allows for performance verification of the vehicle's autonomous driving performance based on the data fusion result during vehicle operation without affecting the autonomous driving function. It enables effective verification of different upgraded versions of environmental perception, and the verification process does not affect the actual operation of the vehicle. This effectively saves time and road test costs for autonomous driving performance verification, and significantly improves the performance verification effect of the autonomous driving function.

[0110] Furthermore, the present invention also provides a performance verification method based on an autonomous driving system.

[0111] See appendix Figure 2 , Figure 2 This is a schematic flowchart of the main steps of a performance verification method based on an autonomous driving system according to an embodiment of the present invention. Figure 2 As shown, the autonomous driving system in this embodiment of the invention is the autonomous driving system described in the above-mentioned autonomous driving system embodiment. The performance verification method based on the autonomous driving system mainly includes the following steps S101-S103.

[0112] Step S101: Obtain fusion input data; wherein, in the first time period, the fusion input data includes the first perception result and the fourth perception result; in the second time period, the fusion input data includes the second perception result and the third perception result.

[0113] In this embodiment, the first perception result and the fourth perception result, as well as the second perception result and the third perception result, can be used as fusion input data at different time periods. Specifically, the first perception result is obtained through first environmental perception based on data collected by the vehicle's first onboard sensor; the second perception result is obtained through second environmental perception based on data collected by the vehicle's second onboard sensor; the third perception result is obtained through third environmental perception based on data collected by the first onboard sensor; and the fourth perception result is obtained through fourth environmental perception based on data collected by the second onboard sensor. The third environmental perception is an upgraded version of the first environmental perception; and the fourth environmental perception is an upgraded version of the second environmental perception.

[0114] The first and second time periods can be continuous or discontinuous. For example, the end time of the first time period can coincide with the start time of the second time period, or vice versa. Alternatively, the second time period may begin after a certain interval following the end of the first time period, or vice versa. All of these are within the scope of this invention.

[0115] In one implementation, see Appendix Figure 4 , Figure 4 This is a schematic diagram of the main implementation architecture for vehicle performance verification according to one embodiment of the present invention. Figure 4 As shown, the first environmental perception unit (functional model first environmental perception) and the second environmental perception unit (functional model second environmental perception) can be set in the vehicle's functional domain (autonomous driving function module), while the third environmental perception unit (accompanying model first environmental perception) and the fourth environmental perception unit (accompanying model second environmental perception) can be set in the vehicle's accompanying domain (accompanying module). The accompanying domain's accompanying app allows selection of whether to use the third or fourth perception result as fusion input data into the accompanying fusion unit; similarly, the functional domain's app module allows selection of whether to use the first or second perception result as fusion input data into the accompanying fusion unit.

[0116] Step S102: Based on the fusion input data, perform data fusion through the accompanying fusion unit to obtain the data fusion result.

[0117] In this embodiment, data fusion can be performed using a companion fusion unit based on the input data to obtain the data fusion result. Commonly used data fusion algorithms in the art can be applied for data fusion. For example... Figure 4 As shown, the fusion input data can be input into the accompanying fusion unit for data fusion to obtain the data fusion result.

[0118] Step S103: Based on the data fusion results, verify the autonomous driving performance of the vehicle.

[0119] In this embodiment, the autonomous driving performance of the vehicle can be verified based on the data fusion results.

[0120] In one implementation, the accompanying control command of the vehicle can be obtained based on the data fusion result. The accompanying control command is compared with the corresponding actual control command of the vehicle. When the difference is less than or equal to a preset threshold, the verification is considered to be successful. When the difference is greater than the preset threshold, the verification is considered to be unsuccessful, indicating that the upgraded version of environmental perception has a performance regression.

[0121] Based on steps S101-S103 above, in the first time period, the first perception result and the fourth perception result are used as fusion input data; in the second time period, the second perception result and the third perception result are used as fusion input data. The first and third perception results are based on the same onboard sensor data, and the environmental perception corresponding to the third perception result is an upgraded version of the environmental perception corresponding to the first perception result. Similarly, the second and fourth perception results are based on the same onboard sensor data, and the environmental perception corresponding to the fourth perception result is an upgraded version of the environmental perception corresponding to the second perception result. In different time periods, the perception results obtained from different upgraded versions of environmental perception are fused with the perception results obtained from other environmental perceptions without upgrades, and the vehicle's performance is verified based on the fusion results. Through this configuration, the present invention can effectively verify different upgraded versions of environmental perception during vehicle operation, and the verification process does not affect the actual operation of the vehicle. This effectively saves time and road test costs for autonomous driving performance verification and effectively improves the performance verification effect of autonomous driving functions.

[0122] The following provides further explanation of steps S101 and S103.

[0123] In one embodiment of the present invention, step S101 may be further configured as follows:

[0124] The time-division multiplexing unit of the autonomous driving system determines the first time period and the second time period through time-division multiplexing to obtain fused input data.

[0125] In this embodiment, such as Figure 4 As shown, the first and second time periods can be determined through time-sharing multiplexing. That is, it can be achieved through... Figure 4 The advanced data closed-loop management module provides time-division multiplexing logic, enabling the selection of the first and second time periods. Time-division multiplexing refers to the process of segmenting input data using time as a signal.

[0126] For example, the first time period is the first half of each month, and the second time period is the second half of each month. In the first half of each month, the advanced data closed-loop management module transmits the first perception result obtained by the first environmental perception of the functional model located in the functional domain to the accompanying fusion unit located in the accompanying domain through the app module of the functional domain. The advanced data closed-loop perception module then transmits the fourth perception result obtained by the second environmental perception of the accompanying model located in the accompanying domain to the accompanying fusion unit of the accompanying domain through the accompanying app manager of the accompanying domain. In the second half of each month, the advanced data closed-loop management module transmits the second perception result obtained by the second environmental perception of the functional model located in the functional domain to the accompanying fusion unit located in the accompanying domain through the app module of the functional domain. The advanced data closed-loop perception module then transmits the third perception result obtained by the first environmental perception of the accompanying model located in the accompanying domain to the accompanying fusion unit of the accompanying domain through the accompanying app manager of the accompanying domain. The first and second environmental perceptions of the accompanying model are based on data collected by onboard sensors.

[0127] In one embodiment of the present invention, step S103 may further include steps S1031 to S1033:

[0128] Step S1031: Based on the data fusion results, obtain the driving control commands used for performance verification.

[0129] In this embodiment, step S1031 may further include the following steps S10311 and S10312:

[0130] Step S10311: Based on the data fusion results, construct environmental data of the vehicle's environment.

[0131] In this embodiment, environmental data of the vehicle's environment can be constructed based on the data fusion results. For example... Figure 4 As shown, the data fusion results can be input into the associated environment model to obtain environmental data of the vehicle's environment.

[0132] In one implementation, environmental data of the vehicle's environment can be obtained by combining data fusion results and non-vehicle-side perception data. The non-vehicle-side perception data can include map data provided by a map module, etc. Map data, data fusion results, high-precision map data, GNSS positioning data, vehicle speed data, and data fused from the above data can be input into the accompanying environment model to obtain environmental data of the vehicle's environment.

[0133] Step S10312: Based on environmental data, obtain driving control commands for performance verification through the accompanying driving control unit of the autonomous driving system.

[0134] In this embodiment, driving control commands for performance verification can be obtained based on environmental data. For example... Figure 4 As shown, the data fusion results generated by the associated fusion unit are input into the associated environment model to obtain the environmental data of the vehicle's environment. The environmental data is then input into the associated driving control unit to obtain driving control commands for performance verification.

[0135] In one implementation, environmental data and vehicle positioning data can be combined to obtain driving control commands for performance verification.

[0136] Step S1032: Based on the data fusion results, obtain active safety control commands for performance verification through the accompanying active safety control unit of the autonomous driving system.

[0137] In this embodiment, active safety control commands for performance verification can be obtained based on the data results and vehicle-side positioning data. For example... Figure 4 As shown, the data fusion result output by the companion fusion unit is input into the companion active safety planning and control unit to obtain active safety control commands for performance verification.

[0138] Step S1033: Perform performance verification on the vehicle based on the driving control commands and active safety control commands used for performance verification.

[0139] In this embodiment, step S1033 may further include the following steps S10331 to S10333:

[0140] Step S10331: Compare the driving control commands used for performance verification with the driving control commands used for driving control of the vehicle to obtain the driving control comparison results.

[0141] In this embodiment, the driving control commands used for performance verification can be compared with the driving control commands used by the vehicle for driving control, thereby obtaining the driving control comparison result.

[0142] In one implementation, a driving control threshold can be set. When the difference between the driving control command used for performance verification and the driving control command used by the vehicle for driving control is less than or equal to the driving control threshold, the driving control comparison result is considered to be passed; when the difference between the driving control command used for performance verification and the driving control command used by the vehicle for driving control is greater than the driving control threshold, the driving control comparison result is considered to be failed.

[0143] Step S10332: Compare the active safety control commands used for performance verification with the active safety control commands used for driving control of the vehicle to obtain the active safety control comparison results.

[0144] In this embodiment, the active safety control commands used for performance verification can be compared with the active safety control commands used for driving control of the vehicle to obtain the active safety control comparison results.

[0145] In one implementation, an active safety control threshold can be set. When the difference between the active safety control command used for performance verification and the active safety control command used for driving control of the vehicle is less than or equal to the active safety control threshold, the active safety control comparison result is considered to be passed. When the difference between the active safety control command used for performance verification and the active safety control command used for driving control of the vehicle is greater than the active safety control threshold, the active safety control comparison result is considered to be failed.

[0146] Step S10333: Based on the comparison results of driving control and active safety control, the performance of the vehicle is verified.

[0147] In this embodiment, vehicle performance can be verified based on the comparison results of driving control and active safety control.

[0148] In one implementation, if at least one of the driving control comparison result and the active safety control comparison result is unsuccessful, the vehicle's performance verification is deemed unsuccessful.

[0149] In one embodiment of the present invention, one or more of the following data can be transmitted back to facilitate after-sales problem analysis: performance verification data, data fusion results, fusion input data, first perception results, second perception results, third perception results, fourth perception results, data collected by the first vehicle sensor, data collected by the second vehicle sensor, and vehicle operation data.

[0150] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0151] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0152] Furthermore, the present invention also provides a control device. In one embodiment of the control device according to the present invention, the control device includes a processor and a storage device. The storage device can be configured to store a program for executing the performance verification method based on an autonomous driving system of the above-described method embodiments. The processor can be configured to execute the program in the storage device, which includes, but is not limited to, the program for executing the performance verification method based on an autonomous driving system of the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The control device can be a control device device comprising various electronic devices.

[0153] In embodiments of the present invention, the control device may be a control device device comprising various electronic devices. In some possible implementations, the control device may include multiple storage devices and multiple processors. The program executing the performance verification method based on the autonomous driving system of the above method embodiments can be divided into multiple subroutines, each subroutine can be loaded and run by a processor to execute different steps of the performance verification method based on the autonomous driving system of the above method embodiments. Specifically, each subroutine can be stored in different storage devices, and each processor can be configured to execute programs in one or more storage devices to jointly implement the performance verification method based on the autonomous driving system of the above method embodiments, that is, each processor executes different steps of the performance verification method based on the autonomous driving system of the above method embodiments to jointly implement the performance verification method based on the autonomous driving system of the above method embodiments.

[0154] The aforementioned multiple processors can be processors deployed on the same device. For example, the aforementioned control device can be a high-performance device composed of multiple processors, and the aforementioned multiple processors can be processors configured on that high-performance device. Alternatively, the aforementioned multiple processors can also be processors deployed on different devices. For example, the aforementioned control device can be a server cluster, and the aforementioned multiple processors can be processors on different servers within the server cluster.

[0155] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program that performs the performance verification method based on an autonomous driving system described in the above-described method embodiments. This program can be loaded and run by a processor to implement the performance verification method based on an autonomous driving system described above. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0156] Furthermore, the present invention also provides a vehicle. In one embodiment of the present invention, the vehicle includes an autonomous driving system in an autonomous driving system embodiment and a control device in a control device embodiment.

[0157] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0158] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0159] The relevant user personal information that may be involved in the various embodiments of this application is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on the reasonable purpose of the business scenario, and is personal information that users actively provide or that is generated due to the use of the product / service, as well as personal information obtained with user authorization.

[0160] The personal information processed in this application will vary depending on the specific product / service scenario and will be based on the specific scenario in which the user uses the product / service. This may involve the user's account information, device information, driving information, vehicle information, or other related information. This application will treat the user's personal information and its processing with the utmost diligence.

[0161] This application attaches great importance to the security of users' personal information and has taken reasonable and feasible security protection measures that comply with industry standards to protect users' information and prevent unauthorized access, disclosure, use, modification, damage or loss of personal information.

[0162] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. An autonomous driving system, characterized in that, The system includes a first environmental sensing unit, a second environmental sensing unit, a third environmental sensing unit, a fourth environmental sensing unit, and a companion fusion unit; The first environmental perception unit is used to perform first environmental perception based on data collected by the vehicle's first on-board sensor and obtain a first perception result; The second environmental perception unit is used to perform second environmental perception based on data collected by the vehicle's second on-board sensor and obtain a second perception result; The third environmental perception unit is used to perform third environmental perception based on the data collected by the first vehicle-mounted sensor and obtain the third perception result. The fourth environmental perception unit is used to perform fourth environmental perception based on the data collected by the second vehicle-mounted sensor and obtain the fourth perception result. The third environmental perception is an upgraded version of the first environmental perception; the fourth environmental perception is an upgraded version of the second environmental perception. The accompanying fusion unit is used to perform data fusion by using the first perception result and the fourth perception result as fusion input data, or to perform data fusion by using the second perception result and the third perception result as fusion input data. The system includes an autonomous driving function module and a companion module; The first environmental perception unit and the second environmental perception unit are disposed in the autonomous driving function module; The third environmental sensing unit, the fourth environmental sensing unit, and the accompanying fusion unit are disposed in the accompanying module.

2. The autonomous driving system according to claim 1, characterized in that, The system also includes a time-division multiplexing unit; The time-division multiplexing unit is used to determine the input data to the accompanying fusion unit through time-division multiplexing. The input data is either the first perception result and the fourth perception result, or the second perception result and the third perception result.

3. The autonomous driving system according to claim 1, characterized in that, The accompanying module also includes an accompanying driving control unit and an accompanying active safety control unit; The accompanying driving control unit is used to obtain driving control commands for performance verification based on the data fusion results generated by the accompanying fusion unit. The accompanying active safety control unit is used to obtain active safety control commands for performance verification based on the data fusion results generated by the accompanying fusion unit.

4. A performance verification method based on an autonomous driving system, characterized in that, The autonomous driving system is an autonomous driving system based on any one of claims 1-3, and the method includes: Acquire fused input data; wherein, within a first time period, the fused input data includes the first perception result and the fourth perception result; within a second time period, the fused input data includes the second perception result and the third perception result; Based on the fusion input data, data fusion is performed through the accompanying fusion unit to obtain the data fusion result; Based on the data fusion results, the autonomous driving performance of the vehicle is verified.

5. The performance verification method based on an autonomous driving system according to claim 4, characterized in that, The acquisition of fused input data includes: The first time period and the second time period are determined by the time-division multiplexing unit of the autonomous driving system to obtain the fused input data.

6. The performance verification method based on an autonomous driving system according to claim 4, characterized in that, The step of verifying the autonomous driving performance of the vehicle based on the data fusion results includes: Based on the data fusion results, driving control commands for performance verification are obtained through the accompanying driving control unit of the autonomous driving system. Based on the data fusion results, active safety control commands for performance verification are obtained through the accompanying active safety control unit of the autonomous driving system. The autonomous driving performance is verified based on the driving control commands and the active safety control commands used for performance verification.

7. The performance verification method based on an autonomous driving system according to claim 6, characterized in that, Based on the data fusion results, the accompanying vehicle control unit of the autonomous driving system obtains driving control commands for performance verification, including: Based on the data fusion results, environmental data of the vehicle's environment is constructed. Based on the environmental data, the driving control commands used for performance verification are obtained through the accompanying driving control unit of the autonomous driving system.

8. The performance verification method based on an autonomous driving system according to claim 6, characterized in that, The step of obtaining active safety control commands for performance verification through the accompanying active safety control unit of the autonomous driving system based on the data fusion result includes: Based on the data fusion results and vehicle positioning data, the active safety control commands used for performance verification are obtained through the accompanying active safety control unit of the autonomous driving system.

9. The performance verification method based on an autonomous driving system according to claim 6, characterized in that, The performance verification of the autonomous driving performance based on the driving control commands and the active safety control commands used for performance verification includes: The driving control commands used for performance verification are compared with the driving control commands used for driving control of the vehicle to obtain a driving control comparison result. The active safety control commands used for performance verification are compared with the active safety control commands used for driving control of the vehicle to obtain active safety control comparison results. The performance of the autonomous driving system is verified based on the comparison results of the driving control and the active safety control.

10. The performance verification method based on an autonomous driving system according to any one of claims 4 to 9, characterized in that, The method further includes: The performance verification data and / or data fusion results and / or fusion input data and / or first perception results and / or second perception results and / or third perception results and / or fourth perception results and / or data collected by the first vehicle sensor and / or data collected by the second vehicle sensor and / or the vehicle's operating data are transmitted back.

11. A control device comprising at least one processor and at least one storage device, said storage device being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the performance verification method based on an autonomous driving system as described in any one of claims 4 to 10.

12. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the performance verification method based on an autonomous driving system as described in any one of claims 4 to 10.

13. A vehicle, characterized in that, The vehicle includes the autonomous driving system according to any one of claims 1-3 and the control device according to claim 11.

Images