Safety Control Method, Device, Equipment and Medium Applied to Driving Assistance System

Abstract

This specification provides a safety control method, apparatus, device, and medium for a driving assistance system. The method includes: when any assisted driving function of a vehicle is activated, determining a first assisted driving mode corresponding to the any assisted driving function. Obtaining driving environment data of the current driving environment of the vehicle, and determining a second assisted driving mode matching the driving environment according to the driving environment data; wherein, any one of the first assisted driving mode and the second assisted driving mode is a driving mode or a parking mode. When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, performing driving control of the vehicle according to the assisted driving tasks output by the driving decision layer.

Description

Technical Field

[0001] This specification relates to the field of intelligent driving technology, and particularly to a safety control method, device, equipment, and medium applied to a driving assistance system. Background Art

[0002] A driving assistance system (ADAS, Advanced Driver Assistance Systems) is a system that combines various sensor technologies, intelligent algorithms, and in-vehicle computing platforms, aiming to improve the driving safety, convenience, and comfort of drivers. The ADAS helps drivers avoid potential traffic accidents or driving errors by continuously monitoring the vehicle's surrounding environment and interacting with the driver, while reducing the driver's burden and enhancing the driving experience.

[0003] The driving assistance system can provide driving functions and parking functions to the driver. The driver activates the driving function or parking function to enable the driving assistance system to perform corresponding driving control on the vehicle for the activated function. However, there are significant differences in the applicable driving scenarios and control logics for these two functions. If the control logic of the driving assistance system for controlling the vehicle does not match the current driving scenario during the driver's use of the assisted driving function (driving function or parking function), it is likely to cause traffic accidents. For example, the parking control logic usually includes operations such as low-speed movement and precise parking, while in the driving scenario, the vehicle needs to maintain a certain speed and smooth driving. If the driving assistance system incorrectly executes the parking control logic in the driving scenario, the vehicle may suddenly decelerate or stop, posing a risk of rear-end collision for the following vehicles. Another example is that in the parking scenario, the speed requirement of the vehicle is relatively low. If the driving assistance system mistakenly applies the driving control logic to the parking scenario, the vehicle may suddenly accelerate or move forward, resulting in the vehicle crashing into surrounding obstacles or pedestrians. Summary of the Invention

[0004] To overcome the problems existing in the related art, this specification provides a safety control method, device, equipment, and medium applied to a driving assistance system.

[0005] According to the first aspect of the embodiments of this specification, a safety control method applied to a driving assistance system is provided. The method includes:

[0006] When any assisted driving function of the vehicle is activated, determining a first assisted driving mode corresponding to the any assisted driving function;

[0007] Obtaining driving environment data of the current driving environment of the vehicle, and determining a second assisted driving mode matching the driving environment according to the driving environment data; wherein, any one of the first assisted driving mode and the second assisted driving mode is a driving mode or a parking mode;

[0008] When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, the driving control of the vehicle is performed according to the assisted driving task output by the driving decision-making layer.

[0009] According to the second aspect of the embodiments of the present specification, a safety control device applied to a driving assistance system is provided. The device includes:

[0010] A first assisted driving mode determination module, configured to determine a first assisted driving mode corresponding to any one of the assisted driving functions when any one of the assisted driving functions of the vehicle is activated; wherein, the assisted driving functions include a driving function and a parking function;

[0011] A second assisted driving mode determination module, configured to obtain driving environment data of the current driving environment of the vehicle, and determine a second assisted driving mode matching the driving environment according to the driving environment data;

[0012] A driving control module, configured to perform driving control of the vehicle according to the assisted driving task output by the driving decision-making layer when the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode; wherein, the assisted driving modes include a driving mode and a parking mode.

[0013] According to the third aspect of the embodiments of the present specification, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the method described in the first aspect are implemented.

[0014] According to the fourth aspect of the embodiments of the present specification, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0015] The technical solutions provided by the embodiments of the present specification may include the following beneficial effects:

[0016] In the embodiments of the present specification, when any assisted driving function of a vehicle is activated, a first assisted driving mode corresponding to the assisted driving function is determined, and driving environment data of the driving environment in which the vehicle is currently located is acquired. A second assisted driving mode matching the driving environment is determined according to the driving environment data. By verifying whether the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, it can be determined whether the currently activated assisted driving function is suitable for the driving environment in which the vehicle is currently located. When the currently activated assisted driving function is suitable for the driving environment in which the vehicle is currently located, the driving of the vehicle is controlled according to the assisted driving tasks output by the driving decision layer, thereby avoiding the execution of an inappropriate driving control logic in the current driving scenario and improving the operation safety of the driving assistance system.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present specification, and are used together with the specification to explain the principles of the present specification.

[0019] Figure 1 is a working framework diagram of a driving assistance system shown according to an exemplary embodiment of the present specification.

[0020] Figure 2 is a flowchart of a safety control method applied to a driving assistance system shown according to an exemplary embodiment of the present specification.

[0021] Figure 3 is a working framework diagram of verifying the safety of a driving assistance system link shown according to an exemplary embodiment of the present specification.

[0022] Figure 4 is another working framework diagram of verifying the safety of a driving assistance system link shown according to an exemplary embodiment of the present specification.

[0023] Figure 5 is another working framework diagram of verifying the safety of a driving assistance system link shown according to an exemplary embodiment of the present specification.

[0024] Figure 6 is another working framework diagram of verifying the safety of a driving assistance system link shown according to an exemplary embodiment of the present specification.

[0025] Figure 7 is a structural schematic diagram of an electronic device shown according to an exemplary embodiment of the present specification.

[0026] Figure 8It is a block diagram of a safety control device applied to a driving assistance system shown in accordance with an exemplary embodiment of this specification. Detailed implementation manners

[0027] A driving assistance system (ADAS, Advanced Driver Assistance Systems) is a system that combines multiple sensor technologies, intelligent algorithms, and in-vehicle computing platforms, aiming to enhance the driving safety, convenience, and comfort of drivers. The ADAS helps drivers avoid potential traffic accidents or driving errors by continuously monitoring the vehicle's surrounding environment and interacting with the driver. At the same time, it reduces the driver's burden and enhances the driving experience.

[0028] The driving assistance system can provide driving functions and parking functions to the driver. The driver activates the driving function or parking function to enable the driving assistance system to perform corresponding driving controls on the vehicle for the activated function. However, there are significant differences in the applicable driving scenarios and control logics of these two functions. If the control logic of the driving assistance system for controlling the vehicle does not match the current driving scenario during the driver's use of the assisted driving function (driving function or parking function), it is likely to cause traffic accidents. For example, the parking control logic usually includes operations such as low-speed movement and precise parking, while in the driving scenario, the vehicle needs to maintain a certain speed and smooth driving. If the driving assistance system wrongly executes the parking logic in the driving scenario, the vehicle may suddenly decelerate or stop, posing a risk of rear-end collision for the following vehicles. Another example is that in the parking scenario, the speed requirement of the vehicle is relatively low. If the driving assistance system mistakenly applies the driving control logic to the parking scenario, the vehicle may suddenly accelerate or move forward, resulting in the vehicle crashing into surrounding obstacles or pedestrians.

[0029] Figure 1 It is a working framework diagram of a driving assistance system shown in accordance with an exemplary embodiment of this specification. As Figure 1 shown, when the driver activates the driving function 10A or parking function 10B of the vehicle, the driving decision-making layer 11 makes a vehicle control decision based on the driving mode request or parking mode request according to information such as the current traffic environment, road conditions, or driving goals, and outputs a driving task or parking task to the vehicle control system 12, so that the vehicle control system 12 can control the running state of the vehicle according to the indication of this driving task or parking task. For example, the vehicle control system 12 can ensure that the vehicle performs corresponding operations according to the control instructions output by the driving decision-making layer 11 by controlling the motor, braking system, steering system, etc.

[0030] However, in real driving scenarios, the driver may accidentally activate a driving assistance function that is not suitable for the current driving scenario, causing the control logic of the driving assistance system to be inappropriate for the current driving scenario. For example, the driver mistakenly activates the driving function 10A in the parking lot, and the driving decision layer 11 generates a driving control instruction in response to the driving function 10A and outputs it to the vehicle control system 12, so that the vehicle control system 12 controls the vehicle according to the driving task. Of course, even if the driver operates in accordance with the specifications, the hardware problems of the vehicle itself may also lead to driving decision errors. For example, after the user presses the driving function button, a parking mode request is generated.

[0031] In view of the above technical problems, this specification provides a safety control method applied to a driving assistance system to improve the operational safety of the driving assistance system.

[0032] Next, the embodiments of this specification are described in detail.

[0033] Figure 2 This is a flowchart of a safety control method applied to a driving assistance system according to an exemplary embodiment of this specification. Figure 2 As shown, steps 201-203 are included:

[0034] Step 201: When any assisted driving function of a vehicle is activated, determine a first assisted driving mode corresponding to the any assisted driving function.

[0035] Step 202: Acquire driving environment data of the current driving environment of the vehicle, and determine a second assisted driving mode matching the driving environment based on the driving environment data; wherein any one of the first assisted driving mode and the second assisted driving mode is a driving mode or a parking mode.

[0036] Step 203: When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, driving control of the vehicle is performed according to the assisted driving task output by the driving decision layer.

[0037] The vehicle's assisted driving functions may include parking functions and driving functions. The driving function can help the driver perform various driving operations in driving scenarios such as highways and urban roads without human intervention. For example, on urban roads, the driving function can realize path planning based on real-time traffic data and select the optimal route to avoid congested or traffic accident areas. The parking function can help the driver automatically identify parking spaces and control the vehicle to enter the parking space safely and accurately without human intervention. For example, in residential areas or private garages, the parking space is small and it may take multiple adjustments to the direction to park in the parking space. The vehicle can be parked in the garage through automatic parking or remote parking.

[0038] There can be multiple ways to activate any of the vehicle's assisted driving functions. In one embodiment, a parking function switch and a driving function switch can be respectively configured on the vehicle and / or the remote control device. The parking function switch or the driving function switch can be a physical switch or a virtual switch. The driver can turn on the driving function switch and the parking function switch in various ways such as by contact, voice command, etc. Specifically, the remote control device can be an electronic device such as a mobile phone, glasses, a watch, a notebook, etc. The physical switch can be a physical button for starting the driving function and a physical button for starting the parking function set at positions such as the vehicle's steering wheel or center console. The virtual switch can be an icon for the driving function or an icon for the parking function displayed on the in-vehicle screen and / or the remote control device. The driver can choose to turn on the driving function switch or the parking function switch according to actual driving needs. For example, when the driver has a driving need, the driver can choose to turn on the driving function switch; when the driver has a parking need, the driver can choose to turn on the parking function switch. After the driver turns on the driving function switch, the activated assisted driving function is the driving function; after the driver turns on the parking function switch, the activated assisted driving function is the parking function.

[0039] In another embodiment, in the actual use scenario, it is possible that the driver accidentally touches the parking function switch during driving, or intends to turn on the parking function in a parking scenario but accidentally activates the driving function switch. The driving assistance system is very likely to make driving decisions in response to incorrect parking requests or driving requests. To prevent the driver from accidentally touching or incorrectly activating the assisted driving function, a combined driving and parking switch can be provided to the driver, that is, the driving function and the parking function are integrated into the combined driving and parking switch. Whether the driver has a driving need or a parking need, the switch turned on is the combined driving and parking switch, and the vehicle can intelligently sense the driving scenario the vehicle is in and intelligently turn on the driving function and the parking function.

[0040] When the assisted driving function is activated, determine whether the activated assisted driving function is the driving function or the parking function. If the driving function is activated, determine that the first assisted driving mode corresponding to the driving function is the driving mode; if the parking function is activated, determine that the first assisted driving mode corresponding to the parking function is the parking mode.

[0041] Obtain the driving environment data of the vehicle's current driving environment, and determine a second assisted driving mode that matches the driving environment according to the driving environment data. Exemplarily, the driving environment can be classified into a driving environment and a parking environment. Based on the driving environment data, it can be determined whether the vehicle's current driving environment is a driving environment or a parking environment. If it is determined that the vehicle's current driving environment is a driving environment, the second assisted driving mode that matches this driving environment is determined to be the driving mode; if it is determined that the vehicle's current driving environment is a parking environment, the second assisted driving mode that matches this driving environment is determined to be the parking mode.

[0042] When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, the vehicle's driving is controlled according to the assisted driving task output by the driving decision-making layer. For example, if the first assisted driving mode is the driving mode and the second assisted driving mode is the driving mode, then the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode. Another example is that if the first assisted driving mode is the driving mode and the second assisted driving mode is the parking mode, then the first assisted driving mode and the second assisted driving mode belong to different assisted driving modes. When the first assisted driving mode and the second assisted driving mode belong to different assisted driving modes, an alarm prompt is output and / or it is prohibited to control the vehicle's driving according to the assisted driving task output by the driving decision-making layer, and the alarm prompt is used to remind the driver to take over the vehicle.

[0043] Figure 3 It is a working framework diagram for verifying the safety of the assisted driving system link shown in this specification according to an exemplary embodiment. As Figure 3 shown, when the driving function 10A of the vehicle is activated, the vehicle sends a driving mode request to the driving decision-making layer 11, and then it can be determined that the first assisted driving mode is the driving mode according to this driving mode request; when the parking function 10B of the vehicle is activated, the vehicle sends a parking mode request to the driving decision-making layer 11, and then it can be determined that the first assisted driving mode is the parking mode according to this parking mode request. The driving decision-making layer 11 can be provided with a scenario adaptation module 111, and this scenario adaptation module 111 can be used to obtain the driving environment data of the vehicle's current driving environment and determine a second assisted driving mode that matches the driving environment according to the driving environment data. When the first assisted mode and the second assisted mode belong to the same assisted driving mode, it indicates that the currently activated assisted driving function is adapted to the vehicle's current driving environment, and the vehicle's driving can be controlled according to the assisted driving task output by the driving decision-making layer. When the first assisted mode and the second assisted mode belong to different assisted driving modes, it indicates that the currently activated assisted driving function is not adapted to the vehicle's current driving environment, and the assisted driving task output by the driving decision-making layer may be incorrect, and it is prohibited to control the vehicle's driving according to the assisted driving task output by the driving decision-making layer.

[0044] By verifying whether the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, it can be determined whether the currently activated assisted driving function is adapted to the current driving environment of the vehicle. When the currently activated assisted driving function is adapted to the current driving environment of the vehicle, the driving of the vehicle is controlled according to the assisted driving task output by the driving decision-making layer, thereby solving the problem that the driving assistance system makes an incorrect vehicle control decision when the driver or the driving assistance system activates an assisted driving function that is not adapted to the vehicle's current scenario.

[0045] In one embodiment, the driving decision-making layer may include a driving and parking state machine. When any assisted driving function of the vehicle is activated, the first assisted driving mode corresponding to the any assisted driving function is determined. The function state output by the driving and parking state machine for the activated assisted driving function is obtained, and the third assisted driving mode corresponding to the function state is determined. The driving environment data of the current driving environment of the vehicle is obtained, and the second assisted driving mode matching the driving environment is determined according to the driving environment data. When the first assisted driving mode, the second assisted driving mode, and the third assisted driving mode all belong to the same assisted driving mode, the driving of the vehicle is controlled according to the assisted driving task output by the driving decision-making layer. When the first assisted driving mode, the second assisted driving mode, and the third assisted driving mode belong to different assisted driving modes, an alarm prompt is output and / or the driving of the vehicle is prohibited from being controlled according to the assisted driving task output by the driving decision-making layer, and the alarm prompt is used to remind the driver to take over the vehicle.

[0046] Figure 4 This is another working framework diagram for verifying the safety of the driving assistance system link shown in this specification according to an exemplary embodiment. As Figure 4As shown, after the driving function 10A is activated, it sends a driving mode request to the driving and parking state machine 112, or after the parking function 10B is activated, it sends a parking mode request to the driving and parking state machine 112. The first assisted driving mode can be determined by reading the driving mode request or the parking mode request. The driving and parking state machine 112 can switch the function state to the corresponding driving function state or parking function state in response to the activation of the driving function or parking function. The third assisted driving mode corresponding to this function state can be determined by reading the function state switched by the driving and parking state machine. For example, the driving and parking state machine can switch the function state to the driving function state in response to the activation of the driving function, read the driving function state, and determine that the third assisted driving mode corresponding to this driving function state is the driving mode. Another example is that the driving and parking state machine can switch the function state to the parking function state in response to the activation of the parking function, and determine that the third assisted driving mode corresponding to this parking function state is the parking function. The scenario adaptation module 111 can obtain the driving environment data of the current driving environment of the vehicle and determine the second assisted driving mode matching the driving environment according to the driving environment data. The driving decision-making layer 11 can generate a driving task or a parking task and send the driving task or the parking task to the vehicle control system 12.

[0047] Due to the limitations of the algorithm, the function state switched by the driving and parking state machine may not accurately correspond to the activated assisted driving function. For example, when the driving and parking state machine responds to the activation of the driving function, the switched function state may be the parking function state. The driving and parking state machine switching to the wrong function state will affect the driving decision-making result of the driving decision-making layer. For example, in an application framework of the driving decision-making layer, the driving decision-making layer may further include a control large model, which is used to respond to the function state output by the driving and parking state machine, call the driving control logic corresponding to this function state to generate an assisted driving task, and output the assisted driving task for vehicle driving control. For example, the activated assisted driving function of the vehicle is the driving function, but the function state switched by the driving and parking state machine is the parking state. The control large model responds to the parking state output by the driving and parking state machine, executes the parking-related control logic, and outputs the parking-related assisted driving task for vehicle driving control. It can be seen that the driving and parking state machine switching to the wrong function state will affect the decision-making correctness of the function nodes associated with it in the driving decision-making layer 11.

[0048] Therefore, in this embodiment, by verifying the consistency among the activated assisted driving function, the function status output by the driving and parking state machine, and the external driving environment, it is possible not only to verify whether the assisted driving function is wrongly activated according to the external driving environment, but also to verify whether the driving and parking state machine in the driving decision-making layer correctly responds to the activated assisted driving function, so as to ensure that in the function chain of the driving assistance system, the assisted driving mode triggered by the assisted driving function activation node and the driving and parking state machine node is the same assisted driving mode, and to verify that this assisted driving mode is adapted to the current driving scenario, thereby improving the operation safety of the driving assistance system.

[0049] In one embodiment, when any assisted driving function of the vehicle is activated, a first assisted driving mode corresponding to the any assisted driving function is determined. Driving environment data of the current driving environment of the vehicle is obtained, and a second assisted driving mode matching the driving environment is determined according to the driving environment data. A fourth assisted driving mode corresponding to the assisted driving task output by the driving decision-making layer is determined. When the first assisted driving mode, the second assisted driving mode, and the fourth assisted driving mode all belong to the same assisted driving mode, the driving control of the vehicle is performed according to the assisted driving task output by the driving decision-making layer. When the first assisted driving mode, the second assisted driving mode, and the fourth assisted driving mode belong to different assisted driving modes, an alarm prompt and / or a prohibition of performing the driving control of the vehicle according to the assisted driving task output by the driving decision-making layer is output, and the alarm prompt is used to remind the driver to take over the vehicle. Among them, when determining the fourth assisted driving mode corresponding to the assisted driving task output by the driving decision-making layer, the type of the assisted driving task can be determined. If the assisted driving task is a driving task, the fourth assisted driving mode can be determined as the driving mode; if the assisted driving task is a parking task, the fourth assisted driving mode can be determined as the parking mode.

[0050] By verifying the consistency among the assisted driving task output by the driving decision-making layer, the activated assisted driving function, and the external environment, it can be ensured that the activated assisted driving function is consistent with the driving scenario, and the assisted decision-making layer also outputs an assisted driving task corresponding to the activated assisted driving function. In the actual application scenario, it can solve the problem that the driver correctly activates the assisted driving function, but the incorrect driving control logic executed by the driving decision-making layer is not discovered. For example, in a parking scenario, the driver activates the parking function, but the vehicle executes the driving control logic. Through the above verification method, the problem of the intermixing of the driving control logic and the parking control logic inside the driving decision-making layer can be discovered in time.

[0051] In one embodiment, when any assisted driving function of a vehicle is activated, a first assisted driving mode corresponding to the activated assisted driving function is determined. The function status output by the driving and parking state machine for the first assisted driving mode is obtained, and a third assisted driving mode corresponding to the function status is determined. A fourth assisted driving mode corresponding to the assisted driving task output by the driving decision-making layer is determined. The driving environment data of the current driving environment of the vehicle is obtained, and a second assisted driving mode matching the driving environment is determined according to the driving environment data. When the first assisted driving mode, the second assisted driving mode, the third assisted driving mode, and the fourth assisted driving mode belong to the same assisted driving mode, the driving control of the vehicle is performed according to the assisted driving task output by the driving decision-making layer.

[0052] Figure 5 This is another working framework diagram for verifying the link security of a driving assistance system shown in this specification according to an exemplary embodiment. As Figure 5 shown, after the driving function 10A is activated, a driving mode request is sent to the driving and parking state machine 112, or after the parking function 10B is activated, a parking mode request is sent to the driving and parking state machine 112. The first assisted driving mode can be determined by reading the driving mode request or the parking mode request. The driving and parking state machine 112 can switch the function status to the corresponding driving function status or parking function status in response to the activation of the driving function or the parking function, and the switched function status of the driving and parking state machine can be read to determine the third assisted driving mode corresponding to the function status. The control large model 113 can generate an assisted driving task in response to the function status output by the driving and parking state machine. For example, when the control large model 113 receives a driving instruction sent by the driving and parking state machine 112, it calls the driving control logic to generate a driving task and outputs the driving task to the vehicle control system 12; for another example, when the control large model 113 receives a parking instruction sent by the parking state machine 112, it calls the parking control logic to generate a parking task and outputs the parking task to the vehicle control system 12. The scenario adaptation module 111 can obtain the driving environment data of the current driving environment of the vehicle and determine a second assisted driving mode matching the driving environment according to the driving environment data. The scenario adaptation module 111 can be integrated into the control large model 113 or independent of the control large model 113, and this specification does not impose any restrictions on this.

[0053] In one embodiment, when any assisted driving function of the vehicle is activated, a first assisted driving function corresponding to the activated assisted driving function is determined. Driving environment data of the current driving environment of the vehicle is obtained, and a second assisted driving mode matching the driving environment is determined based on the driving environment data. When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, the type of the assisted driving task output by the driving decision-making layer is determined. If the assisted driving task is a driving task and the driving control parameters of the driving task meet the driving safety conditions, the vehicle is controlled to drive according to the assisted driving task output by the driving decision-making layer; otherwise, an alarm prompt is given, and the alarm prompt is used to remind the driver to take over the vehicle. If the assisted driving task is a parking task and the driving control parameters of the parking task meet the parking safety constraints, the vehicle is controlled to drive according to the assisted driving task output by the driving decision-making layer; otherwise, an alarm prompt is given, and the alarm prompt is used to remind the driver to take over the vehicle.

[0054] Exemplarily, the driving safety constraints and the parking safety constraints can be set in accordance with automotive functional safety standards. For example, the driving safety constraints may include that the deceleration of intelligent cruise control shall not be greater than 0.5g, and the starting acceleration shall not be greater than 0.3g, etc. The parking safety constraints may include that the acceleration of the memory parking function shall not be greater than 0.15g, and the maximum vehicle speed shall not be greater than 30 km / h, etc.

[0055] In this embodiment, on the basis of verifying that the activated assisted driving function of the vehicle is adapted to the actual driving scenario of the vehicle, it is further verified whether the driving control parameters of the driving task or the parking control parameters of the parking task output by the driving decision-making layer meet the corresponding safety specifications. In practical application scenarios, it can solve the problem that the assisted driving function is correctly activated, but the driving control parameters of the assisted driving task output by the driving decision-making layer do not meet the safety specifications, resulting in traffic accidents. For example, in a parking scenario, the vehicle parks at a driving speed during the parking process. Through the above verification method, it is possible to ensure that the control operation of the vehicle meets the safety specifications on the basis of ensuring that the activated assisted driving function is adapted to the vehicle driving scenario.

[0056] In one embodiment, when any of the assisted driving functions of the vehicle is activated, a first assisted driving mode corresponding to the activated assisted driving function is determined. The functional state output by the driving and parking state machine for the activated assisted driving function is obtained, and a third assisted driving mode corresponding to the functional state is determined. The driving environment data of the current driving environment of the vehicle is obtained, and a second assisted driving mode matching the driving environment is determined according to the driving environment data. A fourth assisted driving mode corresponding to the assisted driving task output by the driving decision-making layer is determined. When the first assisted driving mode, the second assisted driving mode, the third assisted driving mode, and the fourth assisted driving mode belong to the same assisted driving mode, the type of the assisted driving task output by the driving decision-making layer is determined. If the assisted driving task is a driving task and the driving control parameters of the driving task meet the driving safety constraint conditions, the driving control of the vehicle is performed according to the assisted driving task output by the driving decision-making layer; if the assisted driving task is a parking task and the driving control parameters of the parking task meet the parking safety constraint conditions, the driving control of the vehicle is performed according to the assisted driving task output by the driving decision-making layer.

[0057] In this embodiment, by verifying the consistency of the activated assisted driving function of the vehicle, the functional state output by the driving and parking state machine, the assisted driving task output by the driving decision-making layer, and the driving scenario where the vehicle is located, it can be determined whether the vehicle has activated the appropriate assisted driving function, and whether the black box state assisted decision-making layer correctly responds to the activated assisted driving function. Moreover, on this basis, by further checking whether the driving control parameters of the assisted driving task output by the assisted decision-making layer meet the safety specifications, the operation safety of the assisted driving system can be further ensured.

[0058] Figure 6 This is another working framework diagram for verifying the safety of the assisted driving system link shown in this specification according to an exemplary embodiment. As Figure 6 shown, on the basis of Figure 5 , the parking task and the driving task output by the control large model 113 can be respectively input into the driving safety verification module 60A and the parking safety verification module 60B. The driving safety verification module can encapsulate the driving safety verification logic for verifying whether the driving control parameters of the driving task meet the driving safety constraint conditions. When the driving control parameters of the driving task meet the driving safety constraint conditions, the driving task is forwarded to the vehicle control system 12. The parking safety verification module can encapsulate the parking safety verification logic for verifying whether the driving control parameters of the parking task meet the parking safety constraint conditions. When the driving control parameters of the parking task meet the parking safety constraint conditions, the parking task is sent to the vehicle control system 12.

[0059] In one embodiment, when determining a second assisted driving mode that matches the driving environment based on driving environment data, environmental features can be extracted from the driving environment data, the driving environment can be classified according to the environmental features, and the second assisted driving mode corresponding to the classification result can be determined. Among them, the categories of the driving environment include driving environment and parking environment.

[0060] The driving environment data may include vehicle driving state data and vehicle surrounding environment data. The vehicle driving state data may include vehicle speed, vehicle position, etc. The vehicle surrounding environment data may include road signs, lane signs, road conditions, the position relationship between the vehicle and other vehicles, and obstacle types, etc. The environmental features extracted from the driving environment data can characterize the driving scene category. For example, parking space features, traffic light features, street features, parking lot sign features, etc. The driving environment can be classified according to these environmental features. The classification of the driving environment can be achieved by means of machine learning or rule judgment. This specification does not impose any restrictions on the specific classification algorithm.

[0061] Corresponding to the embodiments of the foregoing method, this specification also provides embodiments of a device and a terminal to which the device is applied.

[0062] Figure 7 is a schematic structural diagram of an electronic device shown according to an exemplary embodiment of this specification. As Figure 7 shown, at the hardware level, the electronic device 700 includes a processor 702, an internal bus 704, a network interface 706, a memory 708, and a non-volatile memory 710. Of course, there may also be other hardware required for other services. One or more embodiments of this specification can be implemented in a software manner. For example, the processor 702 reads the corresponding computer program from the non-volatile memory 710 into the memory 708 and then runs it. Of course, in addition to the software implementation manner, one or more embodiments of this specification do not exclude other implementation manners, such as a logic device or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic module, and can also be hardware or a logic device.

[0063] Figure 8 is a block diagram of a safety control device applied to a driving assistance system shown according to an exemplary embodiment of this specification. As Figure 8 shown, the device can be applied to the electronic device 700 shown as Figure 7 shown to implement the technical solution of this specification. The device includes:

[0064] A first assisted driving mode determination module 802, configured to determine a first assisted driving mode corresponding to any one of the assisted driving functions of the vehicle when any one of the assisted driving functions of the vehicle is activated;

[0065] A second assisted driving mode determination module 804, configured to obtain driving environment data of the current driving environment of the vehicle, and determine a second assisted driving mode matching the driving environment according to the driving environment data; wherein, any one of the first assisted driving mode and the second assisted driving mode is a driving mode or a parking mode;

[0066] A driving control module 806, configured to perform driving control of the vehicle according to the assisted driving task output by the driving decision-making layer when the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode.

[0067] Optionally, the device further includes a third assisted driving mode determination module, configured to obtain the function state output by the driving and parking state machine for the activated assisted driving function, and determine a third assisted driving mode corresponding to the function state. The driving control module 806 is specifically configured to perform driving control of the vehicle according to the assisted driving task output by the driving decision-making layer when the first assisted driving mode, the second assisted driving mode, and the third assisted driving mode all belong to the same assisted driving mode.

[0068] Optionally, the driving decision-making layer includes a control large model, and the driving control module 806 is specifically configured to the control large model output an assisted driving task to perform driving control of the vehicle in response to the function state output by the driving and parking state machine.

[0069] Optionally, the device further includes a fourth assisted driving mode determination module, configured to determine a fourth assisted driving mode corresponding to the assisted driving task. The driving control module 806 is specifically configured to perform driving control of the vehicle according to the assisted driving task output by the driving decision-making layer when the first assisted driving mode, the second assisted driving mode, and the fourth assisted driving mode all belong to the same assisted driving mode.

[0070] Optionally, the driving control module 806 is specifically configured to determine the type of the assisted driving task output by the driving decision-making layer when the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode. If the assisted driving task is a driving task and the driving control parameters of the driving task meet the driving safety constraint conditions, the driving control of the vehicle is performed according to the assisted driving task output by the driving decision-making layer. If the assisted driving task is a parking task and the driving control parameters of the parking task meet the parking safety constraint conditions, the driving control of the vehicle is performed according to the assisted driving task output by the driving decision-making layer.

[0071] Optionally, the second assisted driving mode determination module 804 is specifically configured to extract environmental features from the driving environment data, classify the driving environment according to the environmental features, and determine a second assisted driving mode corresponding to the classification result; wherein, the categories of the driving environment include a driving environment and a parking environment.

[0072] Optionally, the device further includes an alarm module, which is specifically configured to output an alarm prompt and / or prohibit vehicle driving control according to the assisted driving task output by the driving decision-making layer when the first assisted driving mode and the second assisted driving mode belong to different assisted driving modes, and the alarm prompt is used to remind the driver to take over the vehicle.

[0073] For the implementation processes of the functions and roles of each module in the above device, please refer to the implementation processes of the corresponding steps in the above method for details, which will not be elaborated here.

[0074] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiments described above are only illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place, or may be distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in this specification. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0075] This specification also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the foregoing safety control methods applied to a driving assistance system provided by this application are implemented.

[0076] Specifically, computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (such as EPROM, EEPROM, and flash memory devices), magnetic disks (such as internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks.

Claims

1. A safety control method for a driving assistance system, characterized in that: The method comprises: When any assisted driving function of the vehicle is activated, determining a first assisted driving mode corresponding to the any assisted driving function; Acquiring driving environment data of the current driving environment of the vehicle, and determining a second assisted driving mode matching the driving environment according to the driving environment data; wherein any one of the first assisted driving mode and the second assisted driving mode is a driving mode or a parking mode; When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, driving control of the vehicle is performed according to the assisted driving task output by the driving decision layer.

2. The method according to claim 1, characterized in that The driving decision layer includes a parking state machine, and the method further includes: Acquire a functional state output by the parking state machine for the activated assisted driving function, and determine a third assisted driving mode corresponding to the functional state; When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, controlling the driving of the vehicle according to the assisted driving task output by the driving decision layer includes: When the first assisted driving mode, the second assisted driving mode and the third assisted driving mode all belong to the same assisted driving mode, the driving control of the vehicle is performed according to the assisted driving task output by the driving decision layer.

3. The method according to claim 2, characterized in that The driving decision layer also includes a control model, and the driving control of the vehicle is performed according to the auxiliary driving task output by the driving decision layer, including: The control model outputs an auxiliary driving task to control the vehicle's driving in response to the functional state output by the parking state machine.

4. The method according to claim 1, characterized in that: The method further comprises: determining a fourth assisted driving mode corresponding to the assisted driving task; When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, controlling the driving of the vehicle according to the assisted driving task output by the driving decision layer includes: In the case where the first assisted driving mode, the second assisted driving mode and the fourth assisted driving mode all belong to the same assisted driving mode, driving control of the vehicle is performed according to the assisted driving task output by the driving decision layer.

5. The method according to claim 1, characterized in that When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, controlling the driving of the vehicle according to the assisted driving task output by the driving decision layer includes: When the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode, determining a type of the assisted driving task output by the driving decision layer; If the auxiliary driving task is a driving task and the driving control parameters of the driving task meet the driving safety constraint conditions, then the vehicle driving control is performed according to the auxiliary driving task output by the driving decision layer; If the assisted driving task is a parking task and the driving control parameters of the parking task meet the parking safety constraint conditions, the vehicle driving control is performed according to the assisted driving task output by the driving decision layer.

6. The method according to claim 1, characterized in that The determining, according to the driving environment data, a second assisted driving mode matching the driving environment comprises: Environmental features are extracted from the driving environment data, the driving environment is classified according to the environmental features, and a second assisted driving mode corresponding to the classification result is determined; wherein the categories of the driving environment include a driving environment and a parking environment.

7. The method according to claim 1, characterized in that In the case that the first assisted driving mode and the second assisted driving mode belong to different assisted driving modes, an alarm prompt is output and / or driving control of the vehicle according to the assisted driving task output by the driving decision layer is prohibited, and the alarm prompt is used to remind the driver to take over the vehicle.

8. A safety control device for a driving assistance system, characterized in that: The device comprises: A first assisted driving mode determination module, configured to, when any assisted driving function of the vehicle is activated, determine a first assisted driving mode corresponding to any assisted driving function; a second assisted driving mode determination module, configured to obtain driving environment data of a current driving environment of the vehicle, and determine a second assisted driving mode matching the driving environment according to the driving environment data; wherein any one of the first assisted driving mode and the second assisted driving mode is a driving mode or a parking mode; The driving control module is used to control the driving of the vehicle according to the assisted driving task output by the driving decision layer when the first assisted driving mode and the second assisted driving mode belong to the same assisted driving mode.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images