Driving mode adjusting method and device, equipment, medium and product
By using decision trees in the autonomous driving system to analyze the causes of the exit event of the autonomous driving mode, and automatically adjust the driving strategy, the problem of difficulty in analyzing the reasons for taking over by autonomous driving systems in the existing technology is solved, and the intelligence level and algorithm optimization of autonomous driving are improved efficiency.
Patent Information
- Application Number
- CN202411153525.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-12
AI Technical Summary
In autonomous driving systems, it is difficult for the prior art to automatically analyze the reasons for vehicle takeover, resulting in low algorithm optimization efficiency and insufficient intelligence level.
By detecting the exit event of the autonomous driving mode, the driving data of the target vehicle is analyzed using the pre-trained decision tree, the reason for taking over is determined, and the driving strategy is adjusted according to the reason, so as to achieve automated takeover reason analysis and targeted adjustment.
The intelligence level of the autonomous driving system has been improved, and through automated analysis of the reasons for taking over and adjusting strategies, the algorithm optimization efficiency has been improved, ensuring driving safety and efficiency.
Smart Images

Figure CN118928467A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of autonomous driving vehicle technology, and in particular to a driving style adjustment method, device, equipment, medium and product. Background Art
[0002] With the development of autonomous driving technology, autonomous driving systems are undergoing large-scale research and development and testing stages. During the research and development of autonomous driving systems, takeover reason analysis during road testing is an important part of algorithm optimization. It is used to view scenarios that autonomous driving cannot pass through. Timely analysis of the reasons for autonomous driving takeover can help improve algorithm optimization efficiency.
[0003] Therefore, how to automatically analyze the reasons for manual takeover of the target vehicle, so as to adjust the driving strategy in a targeted manner and improve the intelligence level of autonomous driving, is a problem that needs to be solved urgently. Summary of the invention
[0004] The present invention provides a driving style adjustment method, device, equipment, medium and product to automatically analyze the takeover reason after the target vehicle is manually taken over, so as to adjust the driving strategy in a targeted manner and improve the intelligence level of automatic driving.
[0005] According to one aspect of the present invention, a driving style adjustment method is provided, comprising:
[0006] If an automatic driving mode exit event of the target vehicle is detected, determining target driving data of the target vehicle within a target time period;
[0007] According to the target driving data, based on the pre-trained target decision tree, determine the target takeover reason for the target vehicle to exit the autonomous driving mode;
[0008] According to the target takeover reason, an adjustment strategy for the driving style of the target vehicle is determined to instruct relevant personnel to adjust the driving style according to the adjustment strategy.
[0009] According to another aspect of the present invention, there is provided a driving style adjustment device, comprising:
[0010] a data determination module, configured to determine target driving data of the target vehicle within a target time period if an automatic driving mode exit event of the target vehicle is detected;
[0011] A cause determination module, for determining a target takeover cause of a target vehicle exiting an autonomous driving mode based on target driving data and a pre-trained target decision tree;
[0012] The adjustment module is used to determine an adjustment strategy for the driving style of the target vehicle according to the target takeover reason, so as to instruct relevant personnel to adjust the driving style according to the adjustment strategy.
[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0014] at least one processor; and
[0015] a memory communicatively connected to the at least one processor; wherein,
[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the driving style adjustment method described in any embodiment of the present invention.
[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the driving style adjustment method described in any embodiment of the present invention when executed.
[0018] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the driving style adjustment method of any embodiment of the present invention is implemented.
[0019] The technical solution of the embodiment of the present invention is to determine the target driving data of the target vehicle within the target time period if an exit event of the automatic driving mode of the target vehicle is detected; determine the target takeover reason for the target vehicle to exit the automatic driving mode based on the target driving data and a pre-trained target decision tree; determine the adjustment strategy for the driving style of the target vehicle based on the target takeover reason to instruct relevant personnel to adjust the driving style according to the adjustment strategy. By using the target decision tree to comprehensively analyze and match the target takeover data, the takeover reason can be automatically analyzed after the target vehicle is manually taken over, thereby adjusting the driving strategy in a targeted manner and improving the intelligence level of automatic driving.
[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0022] Figure 1 is a flow chart of a driving style adjustment method provided in Embodiment 1 of the present invention;
[0023] Figure 2 is a flow chart of a driving style adjustment method provided by Embodiment 2 of the present invention;
[0024] Figure 3 is a structural block diagram of a driving style adjustment device provided in Embodiment 3 of the present invention;
[0025] Figure 4 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION
[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0027] It should be noted that the terms "first", "second", "target", "candidate", "alternative", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.
[0028] Embodiment 1
[0029] Figure 1 is a flow chart of a driving style adjustment method provided in the first embodiment of the present invention; this embodiment is applicable to the case where the takeover reason analysis is performed according to the target decision tree and the takeover data when the vehicle exits the automatic driving mode so as to adjust the driving strategy in a targeted manner. The method can be executed by a driving style adjustment device, and the driving style adjustment device can be implemented in the form of hardware and / or software. The driving style adjustment device can be configured in an electronic device, such as a vehicle, and executed by an electronic control unit of the vehicle, such as Figure 1 As shown, the driving style adjustment method includes:
[0030] S101. If an automatic driving mode exit event of a target vehicle is detected, target driving data of the target vehicle within a target time period is determined.
[0031] Among them, the target vehicle refers to the vehicle whose driving mode is adjusted in real time by analyzing the reasons for takeover. The automatic driving mode exit event refers to the event that the driving mode of the target vehicle exits the automatic driving mode, which can be specifically the event that the driving mode of the target vehicle is converted from the automatic driving mode to the manual driving mode, that is, the event that the driving of the vehicle is taken over manually. The target time period refers to the time period of a preset length before and after the time when the target vehicle is manually taken over. The target driving data refers to the data that characterizes the driving condition of the target vehicle during the target time period. The target driving data may include at least one of the following channel data: chassis data, lidar data, positioning data, prediction data, fusion perception data, traffic light data, PNC (Planning and Control) data and monitoring data. The monitoring data may be, for example, data obtained by monitoring the frame rate of each functional module of the target vehicle. PNC data refers to the relevant data obtained by the PNC module of the target vehicle for path planning.
[0032] Optionally, determine the target driving data of the target vehicle within a target time period, including: determining the target takeover time for the target vehicle to exit the automatic driving mode for manual takeover; determine the target time period based on the target takeover time, a preset forward time length, and a preset additional time length, and obtain the target driving data of the target vehicle within the target time period.
[0033] The target takeover time refers to the time point of manual takeover. The preset forward time refers to the time range before the takeover time. The preset additional time refers to the time range after the takeover time. The preset forward time and the preset additional time can be the same or different. For example, the preset forward time can be 10 seconds, and the preset additional time can be 5 seconds.
[0034] Exemplarily, based on the target takeover time, you can go back 10 seconds and add 5 seconds to determine the target time period, and based on different types of target driving data, obtain corresponding driving data from different modules or different detection devices of the target vehicle to obtain the target driving data.
[0035] S102. Determine the target takeover reason for the target vehicle to exit the automatic driving mode according to the target driving data and based on a pre-trained target decision tree.
[0036] Among them, the target decision tree is a classification decision tree generated based on the random forest algorithm according to the historical driving data of the target vehicle and its corresponding historical takeover reasons and other information in advance. The target decision tree contains at least two classification nodes, each of which corresponds to an evaluation condition for driving characteristics. If the evaluation condition is met, it corresponds to a target takeover reason. Driving characteristics refer to the characteristics extracted from the target driving data, and the number of driving characteristics is at least two. The driving characteristics can be, for example, at least one of the following: the detection characteristics of the laser radar obtained by integrating and extracting the laser radar detection data in the target driving data, the frame rate information of each functional module of the target vehicle, the speed level of the obstacle vehicle in front, the speed level of the target vehicle before taking over, whether the target vehicle has an emergency brake before taking over (such as within 5s before taking over), whether the target vehicle has a sharp turn before taking over, the variable number of lanes (such as 0, 1 or 2), the distance between the front and rear vehicles of the left and right lanes, whether the target vehicle changes lanes before taking over, the static obstacle information around the target vehicle recorded in the map, and whether the target vehicle is near the preset rest area.
[0037] The number of target takeover reasons may be at least one. The target takeover reason is a takeover reason obtained by matching and analyzing the target driving data or driving characteristics according to the target decision tree. The target takeover reason may include at least one of the following: static obstacles do not bypass, the system exits the automatic driving mode, the distance to the vehicle in front is too close to cause a collision risk, the sudden stop and brake without reason causes a collision risk, the lane change causes a collision risk, the cut-in causes a collision risk, the traffic light recognition error, the road repair or abnormal road conditions, the presence of unmarked obstacles in the map, and the vehicle shakes. The system exits the automatic driving mode refers to the exit of the automatic driving mode due to a system module failure. The collision risk caused by the cut-in refers to the collision risk caused by other vehicles changing lanes in the left and right lanes.
[0038] Optionally, if according to the target driving data and based on a pre-trained target decision tree, it is determined that the speed of the obstacle vehicle in front of the target vehicle is at a low level (if the speed of the obstacle vehicle is at a medium or high level, the corresponding matching fails, and the target takeover reason does not include the risk of collision due to being too close to the vehicle in front), and the distance between the target vehicle and the obstacle vehicle is less than a preset distance threshold, then it can be determined that the target takeover reason is the risk of collision due to being too close to the vehicle in front.
[0039] Optionally, if it is determined according to the target driving data and based on a pre-trained target decision tree that the target vehicle has an emergency brake before taking over, then the reason for the target takeover can be determined to be the risk of collision caused by sudden stopping or braking without reason.
[0040] Optionally, if according to the target driving data and based on a pre-trained target decision tree, it is determined that the target vehicle changes lanes before taking over, then the target takeover cause can be determined as a collision risk caused by lane change; if according to the target driving data, it is determined that the interval distance between the target vehicle and the front and rear vehicles in the left and right lanes is less than a preset interval distance threshold, then the target takeover cause is determined to be a cut-in collision risk.
[0041] Optionally, if the driving feature is static obstacle information around the target vehicle recorded in the map, if the map records no obstacles but the lidar detects obstacle data, it can be determined that the cause of the target takeover is the presence of unmarked obstacles in the map.
[0042] Optionally, a decision forest including at least two decision trees can be constructed based on historical driving data and corresponding takeover reasons. After determining the target driving data, each decision tree in the decision forest is used to classify the target driving data, and the target takeover reason is determined based on the classification results.
[0043] Optionally, according to the target driving data and based on a pre-trained target decision tree, a target takeover reason for the target vehicle to exit the autonomous driving mode is determined, including: extracting features from the target driving data based on a preset feature extraction method to determine driving characteristics; determining evaluation conditions for each classification node in the pre-trained target decision tree, and matching the driving characteristics with each evaluation condition to determine the target takeover reason for the target vehicle to exit the autonomous driving mode based on the matching results.
[0044] The preset feature extraction method may be an extraction method for extracting different driving features respectively. For example, feature extraction may be performed on the laser radar detection data in the target driving data to obtain abnormal driving features detected by the laser radar. Feature extraction may also be performed on the frame rate data of each functional module of the target vehicle in the target driving data to obtain frame rate information of each functional module of the target vehicle, that is, frame rate information driving features. The target decision number includes at least two classification nodes, each of which corresponds to an evaluation condition.
[0045] Optionally, each driving feature may be matched with each evaluation condition of each classification node in the target decision tree. If the match is successful, the corresponding classification node is determined as a target takeover reason, until all classification nodes are traversed to obtain the final target takeover reason.
[0046] Optionally, the driving characteristics are matched with each evaluation condition to determine the target takeover reason for the target vehicle to exit the automatic driving mode based on the matching result, including: if the driving characteristic is a lidar detection abnormality, and the classification node is static obstacle non-detour, then the lidar detection abnormality data is analyzed to determine whether the cause of the lidar detection abnormality is the presence of an obstacle ahead; if so, it is determined that the lidar detection abnormal driving characteristics and the classification node are successfully matched, and it is determined that the target takeover reason for the target vehicle to exit the automatic driving mode is static obstacle non-detour.
[0047] Optionally, if it is determined based on the abnormal data detected by the lidar that the abnormality detected by the lidar is the presence of an obstacle ahead, then it is determined that the abnormal driving characteristics detected by the lidar and the static obstacle non-bypass classification node are successfully matched, that is, the target takeover reason is static obstacle non-bypass, that is, the reason why the target vehicle exits the automatic driving mode for manual takeover is that the target vehicle detects an obstacle ahead during driving and cannot pass through.
[0048] Optionally, the driving characteristics are matched with each evaluation condition to determine the target takeover reason for the target vehicle to exit the automatic driving mode based on the matching result, including: if the driving characteristic is the frame rate information of each functional module of the target vehicle, and the classification node is the system exiting the automatic driving mode, then based on the frame rate information and a preset frame rate range, determine whether there is frame loss in each functional module of the target vehicle; if so, determine that the frame rate information driving characteristic and the classification node are successfully matched, and determine that the target takeover reason for the target vehicle to exit the automatic driving mode is the system exiting the automatic driving mode.
[0049] The preset frame rate range may include a stable frame rate range, a light frame loss range, and a heavy frame loss range. The stable frame rate range may be, for example, 80% to 100% of the standard frame rate, the light frame loss range may be, for example, 60% to 80% of the standard frame rate, and the heavy frame loss range may be, for example, 60% below the standard frame rate. System exit from the automatic driving mode means that some modules of the target vehicle exit due to too low a frame rate, causing the vehicle system to exit the automatic driving mode.
[0050] Optionally, the frame rate information of each functional module of the target vehicle can be compared with a preset frame rate range. If the frame rate information of a functional module is in a mild frame loss range or a severe frame loss range, it is determined that frame loss exists. At this time, it is determined that the frame rate information driving characteristics and the system exiting the automatic driving mode classification node are successfully matched. In other words, the target vehicle's automatic driving mode is exited due to the existence of frame loss in the functional module of the target vehicle.
[0051] It should be noted that the present invention uses a decision tree to record and visualize a wide variety of driving characteristics and corresponding takeover reasons in the form of a tree structure, which helps to deal with the classification problem of multi-dimensional output, that is, to determine the reason for autonomous driving takeover, thereby improving the accuracy and efficiency of takeover reason matching.
[0052] S103. Determine an adjustment strategy for the driving style of the target vehicle according to the target takeover reason, and instruct relevant personnel to adjust the driving style according to the adjustment strategy.
[0053] Among them, the adjustment strategy may include the adjustment strategy for the operation mode of different modules of the target vehicle, and may also include the decision on the driving mode, such as continuing manual driving or re-entering the automatic driving mode.
[0054] It should be noted that the decision on driving mode can be determined based on the driver's choice. For example, the driver can choose to continue manual driving for the sake of safety. If the analyzed target takeover reason is a minor problem, the driver can continue to use the automatic driving mode to control the vehicle.
[0055] Optionally, based on the target takeover reason, an adjustment strategy for the target vehicle's driving mode is determined, including: if the target takeover reason is not detouring around static obstacles, then the planning and control PNC module of the target vehicle is controlled to re-plan the path to continue driving according to the updated planned path; if the target takeover reason is that the distance to the vehicle in front is too close, resulting in a collision risk, then the collision prediction module of the target vehicle is controlled to re-predict the collision risk around the target vehicle to perform driving control based on the goal of avoiding collision risks.
[0056] Among them, the risk of collision caused by being too close to the vehicle in front refers to the risk of sudden braking and collision caused by the target vehicle misjudging the route of nearby vehicles.
[0057] Optionally, the target takeover reasons can be classified to determine whether they are reasons that can be improved through technical optimization or non-technical reasons. Specifically, the system exits the autonomous driving mode, the risk of collision due to being too close to the vehicle in front, the risk of collision due to sudden stopping or braking without reason, the risk of collision due to lane change, traffic light recognition errors, and vehicle shaking are reasons that can be improved through technical optimization, while static obstacles are not bypassed, cut-in collision risks, and road repairs or abnormal road conditions are non-technical reasons. For non-technical reasons, relevant personnel can be notified to make improvements. For technical reasons, the operation strategy can be adjusted by controlling the corresponding modules (such as the PNC module and the collision prediction module), so as to automatically achieve targeted improvements to the takeover reasons and realize intelligent driving of autonomous driving vehicles.
[0058] The technical solution of the embodiment of the present invention is to determine the target driving data of the target vehicle within the target time period if an exit event of the automatic driving mode of the target vehicle is detected; determine the target takeover reason for the target vehicle to exit the automatic driving mode based on the target driving data and a pre-trained target decision tree; determine the adjustment strategy for the driving style of the target vehicle based on the target takeover reason to instruct relevant personnel to adjust the driving style according to the adjustment strategy. By using the target decision tree to comprehensively analyze and match the target takeover data, the takeover reason can be automatically analyzed after the target vehicle is manually taken over, thereby adjusting the driving strategy in a targeted manner and improving the intelligence level of automatic driving.
[0059] Embodiment 2
[0060] Figure 2 is a flow chart of a driving style adjustment method provided in Embodiment 2 of the present invention; based on the above embodiments, this embodiment provides a preferred example of performing takeover reason analysis based on a target decision tree to adjust the driving style, specifically, Figure 2 As shown, the method includes:
[0061] S201. If an automatic driving mode exit event of the target vehicle is detected, a target takeover time for the target vehicle to exit the automatic driving mode and undergo manual takeover is determined.
[0062] S202: Determine a target time period according to the target takeover time, the preset forward time period, and the preset additional time period, and obtain target driving data of the target vehicle within the target time period.
[0063] S203: Extract features from the target driving data based on a preset feature extraction method to determine driving features.
[0064] S204: Determine the evaluation conditions of each classification node in the pre-trained target decision tree.
[0065] S205. Match the driving feature with each evaluation condition. If the driving feature is that the laser radar detection is abnormal, and the classification node is that static obstacles are not detoured, analyze the laser radar detection abnormal data to determine whether the abnormal cause of the laser radar detection is the existence of an obstacle ahead.
[0066] S206: If yes, it is determined that the abnormal driving features detected by the laser radar are matched successfully with the classification node, and it is determined that the target takeover reason for the target vehicle to exit the automatic driving mode is that the static obstacle is not detoured.
[0067] S207: If the driving feature is the frame rate information of each functional module of the target vehicle, and the classification node is that the system exits the automatic driving mode, determine whether there is frame loss in each functional module of the target vehicle based on the frame rate information and a preset frame rate range.
[0068] S208: If yes, it is determined that the frame rate information driving feature and the classification node are matched successfully, and the target takeover reason for the target vehicle to exit the automatic driving mode is determined to be the system exiting the automatic driving mode.
[0069] S209: Determine an adjustment strategy for the driving style of the target vehicle according to the target takeover reason, and instruct relevant personnel to adjust the driving style according to the adjustment strategy.
[0070] Embodiment 3
[0071] Figure 3 : is a structural block diagram of a driving style adjustment device provided in Embodiment 3 of the present invention; this embodiment can be applied to the situation where the takeover reason analysis is performed according to the target decision tree and the takeover data when the vehicle exits the automatic driving mode, so as to adjust the driving strategy in a targeted manner. The driving style adjustment device provided in the embodiment of the present invention can execute the driving style adjustment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method; the driving style adjustment device can be implemented in the form of hardware and / or software, and configured in an electronic device with a driving style adjustment function, such as a vehicle, and executed by the electronic control unit of the vehicle, such as Figure 3 As shown, the driving style adjustment device specifically includes:
[0072] The data determination module 301 is used to determine the target driving data of the target vehicle within the target time period if an automatic driving mode exit event of the target vehicle is detected;
[0073] A reason determination module 302 is used to determine a target takeover reason for the target vehicle to exit the automatic driving mode based on the target driving data and a pre-trained target decision tree;
[0074] The adjustment module 303 is used to determine an adjustment strategy for the driving style of the target vehicle according to the target takeover reason, so as to instruct relevant personnel to adjust the driving style according to the adjustment strategy.
[0075] The technical solution of the embodiment of the present invention is to determine the target driving data of the target vehicle within the target time period if an exit event of the automatic driving mode of the target vehicle is detected; determine the target takeover reason for the target vehicle to exit the automatic driving mode based on the target driving data and a pre-trained target decision tree; determine the adjustment strategy for the driving style of the target vehicle based on the target takeover reason to instruct relevant personnel to adjust the driving style according to the adjustment strategy. By using the target decision tree to comprehensively analyze and match the target takeover data, the takeover reason can be automatically analyzed after the target vehicle is manually taken over, thereby adjusting the driving strategy in a targeted manner and improving the intelligence level of automatic driving.
[0076] Furthermore, the data determination module 301 is specifically used for:
[0077] Determine the target takeover time for the target vehicle to exit the autonomous driving mode and undergo manual takeover;
[0078] According to the target takeover time, the preset forward time and the preset additional time, the target time period is determined, and the target driving data of the target vehicle within the target time period is obtained.
[0079] Further, the cause determination module 302 may include:
[0080] A feature determination unit, used to extract features from target driving data based on a preset feature extraction method to determine driving features;
[0081] The cause determination unit is used to determine the evaluation conditions of each classification node in the pre-trained target decision tree, and match the driving characteristics with each evaluation condition to determine the target takeover cause of the target vehicle exiting the automatic driving mode based on the matching result.
[0082] Furthermore, the cause determination unit is specifically used for:
[0083] If the driving feature is abnormal LiDAR detection, and the classification node is static obstacle not detouring, the abnormal LiDAR detection data is analyzed to determine whether the abnormal cause of the LiDAR detection is an obstacle ahead;
[0084] If so, it is determined that the abnormal driving features detected by the lidar and the classification node are matched successfully, and it is determined that the target takeover reason for the target vehicle to exit the autonomous driving mode is that the static obstacle is not detoured.
[0085] Furthermore, the cause determination unit is further configured to:
[0086] If the driving feature is the frame rate information of each functional module of the target vehicle, and the classification node is that the system exits the automatic driving mode, then it is determined whether there is frame loss in each functional module of the target vehicle according to the frame rate information and a preset frame rate range;
[0087] If so, it is determined that the frame rate information driving feature and the classification node match successfully, and the target takeover reason for the target vehicle to exit the automatic driving mode is determined to be the system exiting the automatic driving mode.
[0088] Furthermore, the adjustment module 303 is specifically used for:
[0089] If the target takeover reason is that the static obstacle is not detoured, the planning and control PNC module of the target vehicle is controlled to re-plan the path to continue driving according to the updated planned path;
[0090] If the reason for the target takeover is that the distance to the front vehicle is too close, resulting in a collision risk, the collision prediction module of the target vehicle is controlled to re-predict the collision risk around the target vehicle so as to perform driving control based on the goal of avoiding the collision risk.
[0091] Embodiment 4
[0092] Figure 4 is a schematic diagram of the structure of an electronic device provided by Embodiment 4 of the present invention; Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0093] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0094] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0095] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a driving style adjustment method.
[0096] In some embodiments, the driving style adjustment method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the driving style adjustment method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the driving style adjustment method in any other appropriate manner (e.g., by means of firmware).
[0097] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0098] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0099] In the context of the present invention, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0100] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0101] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0102] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0103] In one embodiment, the embodiment of the present invention further includes a computer program product, the computer program product includes a computer program, and the computer program implements the driving style adjustment method of any embodiment of the present invention when executed by a processor.
[0104] In the process of implementation, the computer program product can be written in one or more programming languages or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).
[0105] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document is not limited here. The above specific implementation methods do not constitute limitations on the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A driving style adjustment method, characterized in that: include: If an automatic driving mode exit event of the target vehicle is detected, determining target driving data of the target vehicle within a target time period; According to the target driving data, based on the pre-trained target decision tree, determine the target takeover reason for the target vehicle to exit the autonomous driving mode; According to the target takeover reason, an adjustment strategy for the driving style of the target vehicle is determined to instruct relevant personnel to adjust the driving style according to the adjustment strategy.
2. The method according to claim 1, characterized in that: Determine target driving data for a target vehicle within a target time period, including: Determine the target takeover time for the target vehicle to exit the autonomous driving mode and undergo manual takeover; According to the target takeover time, the preset forward time and the preset additional time, the target time period is determined, and the target driving data of the target vehicle within the target time period is obtained.
3. The method according to claim 1, characterized in that According to the target driving data, based on the pre-trained target decision tree, the target takeover reason for the target vehicle to exit the autonomous driving mode is determined, including: Extracting features from target driving data based on a preset feature extraction method to determine driving features; Determine the evaluation conditions of each classification node in the pre-trained target decision tree, and match the driving characteristics with each evaluation condition to determine the target takeover reason for the target vehicle to exit the autonomous driving mode based on the matching results.
4. The method according to claim 3, characterized in that: The driving characteristics are matched with each evaluation condition to determine the target takeover reason for the target vehicle to exit the autonomous driving mode based on the matching result, including: If the driving feature is abnormal LiDAR detection, and the classification node is static obstacle not detouring, the abnormal LiDAR detection data is analyzed to determine whether the abnormal cause of the LiDAR detection is an obstacle ahead; If so, it is determined that the abnormal driving features detected by the lidar and the classification node are matched successfully, and it is determined that the target takeover reason for the target vehicle to exit the autonomous driving mode is that the static obstacle is not detoured.
5. The method according to claim 3, characterized in that: The driving characteristics are matched with each evaluation condition to determine the target takeover reason for the target vehicle to exit the autonomous driving mode based on the matching result, including: If the driving feature is the frame rate information of each functional module of the target vehicle, and the classification node is that the system exits the automatic driving mode, then it is determined whether there is frame loss in each functional module of the target vehicle according to the frame rate information and a preset frame rate range; If so, it is determined that the frame rate information driving feature and the classification node match successfully, and the target takeover reason for the target vehicle to exit the automatic driving mode is determined to be the system exiting the automatic driving mode.
6. The method according to claim 1, characterized in that According to the target takeover reason, determine the adjustment strategy for the target vehicle's driving style, including: If the target takeover reason is that the static obstacle is not detoured, the planning and control PNC module of the target vehicle is controlled to re-plan the path to continue driving according to the updated planned path; If the reason for the target takeover is that the distance to the front vehicle is too close, resulting in a collision risk, the collision prediction module of the target vehicle is controlled to re-predict the collision risk around the target vehicle so as to perform driving control based on the goal of avoiding the collision risk.
7. A driving style adjustment device, characterized in that: include: a data determination module, configured to determine target driving data of the target vehicle within a target time period if an automatic driving mode exit event of the target vehicle is detected; A cause determination module, for determining a target takeover cause of a target vehicle exiting an autonomous driving mode based on target driving data and a pre-trained target decision tree; The adjustment module is used to determine an adjustment strategy for the driving style of the target vehicle according to the target takeover reason, so as to instruct relevant personnel to adjust the driving style according to the adjustment strategy.
8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the driving style adjustment method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the driving style adjustment method according to any one of claims 1 to 6 when executed.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the driving style adjustment method according to any one of claims 1 to 6 is implemented.
