Risk processing method based on intelligent driving scene, storage medium and program product

Abstract

The application provides a risk processing method based on an intelligent driving scene, a storage medium and a program product. The method comprises the following steps: in response to a risk trigger signal for a vehicle, determining whether an accident occurs to the vehicle; in the case that the determination result indicates that the accident occurs to the vehicle, acquiring current vehicle position information of the vehicle, and determining a corresponding emergency processing area according to the vehicle position information; and controlling the vehicle to travel to the emergency processing area.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle safety, and in particular to a risk processing method based on an intelligent driving scene, a storage medium and a program product. BACKGROUND

[0002] In the field of road traffic safety, vehicles will face many risk factors, which include not only technical failures themselves, such as vehicle spontaneous combustion, key system failure and other internal hidden dangers, but also complex natural environmental challenges, such as encountering water-involved road surfaces that cause the vehicle to be unable to pass or damaged. More seriously, the vehicle driving scene also needs to cope with man-made unexpected events, such as arson or robbery and other malicious behaviors. The combined effect of these technical, environmental and human factors greatly threatens the personal safety of passengers and pedestrians, and causes potential damage to the public environment and property. Therefore, the industry urgently needs to develop highly reliable technical solutions to protect personnel safety, reduce social property losses and environmental damage.

[0003] In related technologies, when responding to the sudden risk events that the vehicle driving scene may encounter, it is usually highly dependent on the personal judgment and operation of the driver inside the vehicle. However, this method has significant defects: first, there are great individual differences in the experience, judgment and on-the-spot reaction of the driver, and it is easy to make mistakes in highly tense or complex unexpected events; second, in the face of extreme human events such as arson or complex system multiple failures, ordinary drivers often lack effective response knowledge and ability. SUMMARY

[0004] Therefore, the present application provides a risk processing method based on an intelligent driving scene, a storage medium and a program product to solve the deficiencies in related technologies.

[0005] Specifically, the present application is achieved by the following technical solutions:

[0006] According to a first aspect of the present application, a risk processing method based on an intelligent driving scene is provided, the method comprising:

[0007] in response to a risk trigger signal for a vehicle, determining whether an accident occurs to the vehicle;

[0008] if the determination result represents that an accident occurs to the vehicle, obtaining current vehicle location information of the vehicle, and determining a corresponding emergency processing area according to the vehicle location information;

[0009] controlling the vehicle to travel to the emergency processing area.

[0010] According to a second aspect of the present specification, a computer readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, implements the steps of the method of the first aspect.

[0011] According to a third aspect of the present specification, a computer program product is provided, comprising computer programs / instructions which, when executed by a processor, implement the steps of the method of the first aspect.

[0012] The vehicle in the present specification can establish an emergency response mechanism, specifically, when responding to a risk trigger signal and confirming that the vehicle has an accident, the vehicle position can be obtained, and the appropriate emergency treatment area is determined, and then the vehicle can be controlled to travel to the area. In this process, by providing an emergency treatment area, the vehicle can execute risk avoidance operation in a standardized, predictable and rapid manner in an emergency, thereby eliminating the dependence on individual experience, immediate reaction ability and specific event knowledge reserve of the driver, and improving the safety of the passengers and the surrounding environment, minimizing the secondary accidents or loss expansion that may be caused by human judgment errors or insufficient ability, and providing reliable active safety reduction ability for the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0014] Figure 1 is a schematic diagram of a risk processing system based on an intelligent driving scene according to an embodiment of the present application;

[0015] Figure 2 is a flowchart of a risk processing method based on an intelligent driving scene according to an embodiment of the present application;

[0016] Figure 3 is a schematic diagram of another risk processing system based on an intelligent driving scene according to an embodiment of the present application;

[0017] Figure 4 is a flowchart of another risk processing method based on an intelligent driving scene according to an embodiment of the present application;

[0018] Figure 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application;

[0019] Figure 6is a block diagram of a risk processing apparatus based on an intelligent driving scene according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] The exemplary embodiments will be described in detail herein below with reference to the drawings. The following description is merely exemplary in nature and is not intended to limit the present application or the application and uses of the present application. Furthermore, there is no intention to be bound by any expressed or implied theory presented in the preceding background of the application or the following detailed description.

[0021] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0022] It is to be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0023] Embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0024] Figure 1 is an architecture diagram of a risk processing system based on an intelligent driving scene according to an embodiment of the present application. As shown in the figure, the system can include a vehicle 10 and a risk processing platform 12. Figure 1

[0025] ​The vehicle 10 is a physical execution carrier of the above-mentioned risk processing method, in which the hardware basis of perception, decision and execution is integrated. Specifically, the vehicle 10 is equipped with necessary sensor systems, such as cameras, radars, lidars, inertial measurement units, global positioning system (GPS) modules, etc., which can be used to monitor the vehicle's own state, such as battery temperature, key system operating parameters, etc., and the surrounding environment information, such as road water depth, obstacles, abnormally close persons, etc., in real time. These perception data are the key source of generating the above-mentioned risk trigger signal. At the same time, the vehicle 10 can be built-in with a vehicle control unit, such as an electronic control unit (ECU), an automatic driving domain controller, etc., so as to have the ability to receive and execute the control instructions from the risk processing platform 12, so as to finally realize the operation of controlling the vehicle to drive to the emergency processing area. In addition, the vehicle 10 can interact with the risk processing platform 12 through vehicle-to-everything (V2X), fourth generation and fifth generation mobile communication technology (4G / 5G) or controller area network (CAN bus) and other vehicle communication modules, upload its own information, and receive the decision instructions issued by the platform.

[0026] The risk processing platform 12 is a decision device of the risk processing method, which can be a physical server containing a separate host, or the server 11 can be a virtual server carried by a host cluster. Its main functions include: receiving and processing various sensor data and system state information uploaded from the vehicle 10 in real time, identifying and responding to risk trigger signals representing potential or occurred dangers based on this, and analyzing the trigger signals to determine whether an accident has occurred to the vehicle. At the same time, after confirming the occurrence of the accident, the current vehicle location information of the vehicle is obtained. According to the obtained location information, the corresponding emergency processing area is determined. Finally, specific path planning and driving control instructions are generated to control the vehicle to drive to the emergency processing area, which can be issued to the control unit of the vehicle 10 through the communication link for execution. In summary, the risk processing platform 12 replaces the traditional reliance on the experience judgment of individual drivers through its centralized intelligent decision-making capability, and ensures that standardized and optimized risk avoidance measures are taken in the event of an accident.

[0027] Figure 2 The flowchart of the risk processing method based on the intelligent driving scene disclosed in the exemplary embodiments of the present application is shown, which is applied to a vehicle; specifically, it can include the following steps:

[0028] Step S202, in response to the risk trigger signal for the vehicle, determining whether an accident has occurred to the vehicle.

[0029] This step starts with the response of the risk processing platform in the system to the risk trigger signal for the vehicle. After receiving the signal, the above-mentioned platform can analyze based on the preset rules or algorithms to judge whether the above-mentioned vehicle has human or non-human accident. Further, quickly and accurately identify that the vehicle has been in or will be in a real accident state that needs to be avoided in an emergency.

[0030] Among them, the so-called risk trigger signal can be generated in any of the following ways: 1, the passengers in the vehicle perform the alarm operation: that is, when the vehicle occupant as a driver or passenger perceives an emergency situation, such as being robbed, a sudden serious illness, finding that the vehicle is smoking abnormally, etc., the signal can be triggered by the pre-set physical emergency button in the vehicle, the virtual alarm control on the touch screen or the voice instruction. The signal constitutes the above-mentioned risk trigger signal. 2, receiving an alarm request from an external device: that is, the vehicle can receive an alarm request sent by an external device through its vehicle-mounted communication module. Such external devices can include: a traffic management center platform that monitors vehicle abnormalities or regional dangers, other nearby networked vehicles that support reporting the abnormal state of the vehicle, a road side unit (RSU) for detecting road segment dangers such as water accumulation, landslides and warning the vehicle, or law enforcement agency systems. 3, the sensing data collected by the environmental sensors of the vehicle meets the preset alarm condition: the vehicle continuously monitors the vehicle's own state and the surrounding environment based on its environmental perception sensor system, including but not limited to cameras, millimeter wave radars, laser radars, temperature sensors, smoke detectors, water depth sensors, inertial measurement units IMU, microphones, etc. When the combination of certain sensing data collected reaches or exceeds the preset safety threshold or pattern matching rule, the system will automatically generate a risk trigger signal. For example, the battery temperature rises sharply above the critical value, the flame or smoke features are detected, the water depth sensor detects that the wading depth exceeds the safety line, the IMU detects an abnormal severe collision, the microphone recognizes the sound of broken glass or gunshots, etc.

[0031] In summary, after receiving the risk trigger signal from any of the above-mentioned ways, the above-mentioned risk processing platform can enter the accident judgment process. The judgment process can be implemented in one or more of the following ways:

[0032] In an embodiment, the above-mentioned platform can call and analyze the image data collected by the vehicle-mounted camera of the above-mentioned vehicle. Using computer vision algorithms, the platform can identify specific features or patterns in the image, such as: water level, flame, smoke, broken windows / vehicle body, abnormally gathered personnel, weapons, severe water immersion signs, etc. The platform compares these identification results with the preset accident feature library, and judges whether an accident such as arson, robbery, severe collision, deep wading, etc. has occurred according to the identification results.

[0033] In another embodiment, the above-mentioned platform can provide a voice interaction channel between the in-vehicle microphone and the speaker and the passengers in the vehicle. The platform actively plays preset voice inquiries such as "Is there an emergency?" "Do you need help?" "Is anyone injured?" to the passengers in the vehicle through the channel, and collects the voice feedback of the passengers. The platform analyzes the content, tone, emotional state, and keywords of the voice feedback information, such as "help" and "robbery", using voice recognition and natural language processing technology. According to the analysis result of the voice feedback information, the platform can assist or directly determine whether the accident occurs.

[0034] In summary, by combining image recognition and / or voice interaction analysis, the risk processing platform can more comprehensively and reliably verify the risk trigger signal, thereby accurately determining whether the vehicle has truly occurred an accident that requires the start of an emergency avoidance program, and avoiding false triggering or missing real danger. Of course, the judgment process of the above-mentioned platform can be automatically executed by the corresponding program of the system, or additional worker audits can be performed by corresponding platform auditors alone or in combination to further improve the accuracy of accident judgment and reduce the false positive rate.

[0035] Step S204, in the case where the judgment result represents that the vehicle has occurred an accident, obtaining the current vehicle position information of the vehicle, and determining the corresponding emergency handling area according to the vehicle position information.

[0036] Once the judgment result confirms that the vehicle has occurred an accident, the system will obtain the current vehicle position information of the vehicle. This is usually achieved through a positioning system such as a vehicle-mounted global positioning system (GPS), Beidou Navigation Satellite System (BDS), or a combination of inertial navigation and high-precision map positioning module. After obtaining the accurate position, the platform can determine the corresponding emergency handling area according to the vehicle position information, thereby minimizing the risk of the above-mentioned accident. The emergency handling area includes but is not limited to: emergency lane, auxiliary lane area, road end area, right turn dedicated lane area, lane splitting area, emergency avoidance lane, service area parking area, etc. The common point of these areas is that they can provide a relatively safe physical isolation space for the accident vehicle, so that it can quickly escape from the main traffic flow or high-risk environment. Specifically, these areas usually have the following key features: far away from the main traffic flow, easy for vehicle to safely park, minimize traffic interference, easy for subsequent processing, such as easy access and operation of rescue vehicles such as wrecker, ambulance, and fire truck.

[0037] In the step of determining the emergency handling area, the present specification provides an optimized, accident type-based dynamic selection strategy, thereby selecting the emergency handling area that best meets the current avoidance demand and the optimal path to the area, significantly improving the safety and pertinence of the avoidance operation.

[0038] In an embodiment, the platform can obtain a plurality of alternative emergency regions, and respectively plan alternative paths from the vehicle to each of the alternative regions based on the vehicle location information, determine a corresponding path selection condition according to the accident type of the unexpected accident, and select a path matching the path selection condition from the alternative paths as an emergency path based on the path selection condition, and determine the alternative region corresponding to the emergency path as an emergency handling region. Wherein, the alternative region can be derived from a pre-set local database, a cloud platform or a nearby place meeting the basic safety condition searched dynamically based on real-time map data. In the process of planning the alternative path, the real-time road topology, traffic congestion, road type, such as whether it is a highway / urban road, and basic traffic restrictions, such as whether it is a one-way street, can be considered. It is worth mentioning that different unexpected accidents have different core safety requirements for escape paths and regions. For example: in the case of fire / self-ignition accident, the path selection condition can give priority to places away from gas stations, gas stations, forests, dense buildings, etc. flammable and explosive places, and then the shortest path / time-consuming the least to escape danger as soon as possible. In the case of hijacking / human attack, the path selection condition can give priority to "paths passing through or ending near police stations, checkpoints, areas with monitoring facilities", or "paths exposed to main roads or public view as much as possible". In the case of serious waterlogging, the path selection condition requires that "the path and the end region have a significantly higher elevation than the current water level" to avoid secondary waterlogging. In the case of key system failure such as braking, the path selection condition can give priority to "path end as long uphill or dedicated escape lane" to take advantage of terrain parking. The above selection conditions can be predefined as a rule base and associated with different accident type labels.

[0039] In the matching process of selecting a path matching the path selection condition from the alternative paths as an emergency path, the platform can respectively evaluate to what extent each alternative path meets the core conditions set for the current accident type based on weighted calculation and other algorithms, such as calculating the nearest distance of the path to flammable materials, evaluating the coverage of police / monitoring near the end, checking the elevation change of the path, and under the premise of meeting the core conditions, further optimizing secondary goals such as shortest time and shortest distance. Finally, the alternative region corresponding to the emergency path is determined as the emergency handling region.

[0040] It is worth noting that in special or extreme cases, such as disasters causing large areas to be inaccessible, alternative regions being occupied or having serious safety hazards, there may be no path in the alternative path that matches the path selection condition. This specification provides a corresponding emergency mechanism to ensure maximum safety in any scenario.

[0041] In an embodiment, the platform can control the vehicle to stop at the nearest safe location and activate the vehicle warning device to perform a warning operation in the case that none of the alternative paths matches the path selection condition. The nearest safe location is not a random stop, but a location that is relatively safe in the current environment around the vehicle as perceived by the system in real time. The selection criteria can include: away from the main lane, i.e. as far as possible into the emergency lane, shoulder or non-motor vehicle lane; avoid high-risk points, i.e. avoid stopping under a viaduct, steep slope, blind curve, near flammable / dangerous goods, low-lying water area, etc.; maximize the field of view and space, i.e. preferentially select open, well-lit, and away from obstacles.

[0042] The emergency warning operation can include: automatically turning on the hazard warning flasher, automatically sounding the horn in the preset emergency mode, such as continuous sounding or specific rhythm, etc., issuing a sound warning when the visibility is below a corresponding threshold or special attention is needed, automatically turning on the headlights, all external vehicle lighting including the clearance lamp, to enhance the visibility of the vehicle in the dark or bad weather. Activating the vehicle electronic display screen to display preset emergency information to clearly warn the rear and surrounding vehicles and pedestrians, automatically sending the precise vehicle position and state information to the traffic management center or emergency rescue agency to request external assistance.

[0043] In summary, through this emergency mechanism, even in the extreme case that the ideal emergency handling area cannot be reached, the system can ensure that the vehicle is placed in a relatively safe location and actively sends a strong warning signal, minimizing the risk of secondary accidents caused by the vehicle being stranded in a dangerous location, while gaining time and space for passenger evacuation and external rescue.

[0044] Step S206, controlling the vehicle to travel to the emergency handling area.

[0045] After determining the appropriate emergency handling area, the platform can generate a path to the area and control the vehicle to travel to the emergency handling area, thereby quickly moving the accident vehicle away from the dangerous environment or high-risk location, maximizing the safety of passengers and pedestrians and minimizing the negative impact on the public environment and traffic flow.

[0046] The implementation of the behavior of controlling the vehicle to travel can be adapted according to the automation capability level of the vehicle itself, specifically including the following two modes:

[0047] The first mode is to control the vehicle by the auxiliary driving system. In the case that the vehicle is equipped with an auxiliary driving system with functions of lane keeping, adaptive cruise control, automatic lane changing, or even higher level of automatic driving, the risk processing platform can control the vehicle to drive to the emergency processing area by the auxiliary driving system of the vehicle as the control subject, or request the vehicle control unit to control the vehicle to drive to the emergency processing area autonomously. In this mode, the control subject can generate a detailed driving path and speed plan to the emergency processing area, and directly issue specific steering, acceleration, braking, etc. control instructions to the electric power steering system (EPS), electronic stability program (ESP), drive motor / engine control unit, etc. execution mechanism of the vehicle through CAN, Ethernet, etc. vehicle bus. At this time, the vehicle can safely and quickly drive to the target emergency area along the planned path completely autonomously without any operation intervention of the driver. Therefore, it belongs to the highest degree of automation of the risk avoidance execution mode that meets the high level of automatic driving scene, and can ensure reliable execution of risk avoidance when the driver may not be able to operate.

[0048] The second mode is to provide navigation information to guide the driver. In the case that the vehicle does not have the ability to directly execute full path control, or the system strategy / regulation requires to reserve the final decision-making right of the driver, such as in the case of partial automation L2 level / conditional automation L3 level scene, the risk processing platform can provide navigation information to the vehicle for driving to the emergency processing area. The navigation information is usually clearly and strongly presented to the driver through the human-machine interface (HMI) of the vehicle in the form of images, sounds, etc. These navigation information aims to guide the driver of the vehicle to drive the vehicle to the emergency processing area in the form of images, sounds, etc. At this time, the driver can quickly and accurately execute the risk avoidance operation in combination with the assistance of the navigation information, and reduce the risk caused by human judgment errors.

[0049] Through the above two flexible control modes, the present specification ensures that the vehicle can be effectively guided or controlled to a safe emergency processing area after confirming the accident, and the risk avoidance goal is achieved to the greatest extent.

[0050] After successfully controlling or guiding the vehicle to the initially determined emergency processing area, the present specification does not terminate its safety monitoring and response responsibilities. Instead, it can further continuously evaluate and dynamically optimize risk avoidance, so as to cope with the risk of continuous evolution of the accident state, such as fire spreading, structural damage aggravation, etc., and finally improve the robustness and reliability of safety protection in complex and dynamically developing unexpected accidents.

[0051] In an embodiment, in the case where the vehicle drives to the emergency handling area described above, the risk handling platform can periodically obtain the accident severity of the unexpected accident, including but not limited to: continuously receiving and analyzing vehicle sensor data, continuously monitoring through vehicle-mounted cameras, maintaining voice interaction channels with passengers in the vehicle, asking and analyzing their status, and receiving updates from external devices such as rescue vehicles, traffic monitoring cameras, etc. The platform can integrate these information, and use one or more preset algorithms or models based on time series analysis, threshold comparison, pattern recognition, etc. to quantitatively or qualitatively evaluate the accident severity, where the evaluation dimensions can consider aspects such as stable, slow deterioration, rapid deterioration, emergence of new risk sources, etc. which are not described in detail in this specification.

[0052] Meanwhile, the platform can dynamically adjust the corresponding emergency handling area based on the change trend of the accident severity. The decision logic can be: when the accident severity is monitored to show a stable or downward trend: maintain the vehicle in the current emergency handling area, continuously monitor and wait for external rescue. When the accident severity is monitored to show a deterioration trend or the emergence of a new major risk: judge that the current emergency area may no longer be safe, for example: the fire spreads and may ignite nearby vegetation, the vehicle has an explosion risk and needs to be away from road facilities, the water level continues to rise and will soon flood the current location, the hijacker tries to force the vehicle to leave the safe zone, at this time the platform can trigger the area determination process again: that is, based on the latest position of the vehicle and the current accident state, re-execute the step of "determining the corresponding emergency handling area according to the vehicle position information" in the foregoing, thereby re-searching for alternative areas, planning paths, and selecting paths according to the latest risk conditions. Assuming that a new, more suitable emergency handling area is determined, the platform can again control the vehicle to drive to the new emergency handling area.

[0053] For example, assuming that the vehicle catches fire due to battery thermal runaway, and initially avoids danger by stopping in a highway emergency lane, and the platform continuously monitors and finds that the battery temperature is still rising rapidly and the smoke is intensifying, and predicts that there is a risk of explosion. Then the platform can adjust the emergency area to a more open flat ground away from the current lane and below the roadbed, and control the vehicle to drive away from the main road of the highway to the new area, thereby minimizing the threat to the main road traffic and rescue personnel.

[0054] The following will be described in conjunction with Figure 3 and Figure 4 , respectively from the aspects of architecture and logical method, another risk handling process based on intelligent driving scenarios is introduced.

[0055] First, as Figure 3 shown, the figure contains the following modules:

[0056] 1. Wading perception module 302, as the perception terminal of the vehicle wading state, through water depth sensor, humidity sensor and other hardware, it can monitor the key data such as wading depth, water flow speed, environmental humidity in real time. Among them, when detecting wading risk, such as depth exceeding the safety threshold, immediately send the wading signal to the autonomous driving domain controller 306 as the risk trigger signal, and drive the system to automatically upload the vehicle position, running state to the platform, while triggering the subsequent risk handling process.

[0057] 2. Emergency button 304, as a physical trigger entry for users to provide active help, covering collision, being trapped, health abnormalities and other sudden danger scenarios. When the user presses it, it can send an emergency help signal to the autonomous driving domain controller 306 as a risk trigger signal, and drive the system to automatically upload the vehicle position, running state to the platform, while triggering the subsequent risk handling process.

[0058] 3. Autonomous driving domain controller 306, as the decision and execution center of the autonomous driving system, it integrates multiple source signals and coordinates vehicle control. And it can process the risk trigger signals of wading perception module 302 and response emergency button 304. Specifically, it can push the risk trigger signal and the real-time video stream of the vehicle camera to the network connection domain controller 310; At the same time, it can also receive the control instructions of the network connection domain controller 310 to drive the vehicle to execute driving or system control actions.

[0059] 4. Real-time dialogue device 308, as a real-time interaction channel for building a "user-vehicle-platform" path, supporting voice and text two-way communication. When the user initiates a voice demand such as "I need rescue", it can receive feedback from the risk handling platform 312, and at the same time can transmit the dialogue content to the network connection domain controller 310 bidirectionally.

[0060] 5. Network connection domain controller 310, responsible for data forwarding and instruction routing. It can synchronize the above risk trigger signals, video streams of autonomous driving domain controller 306, user dialogue of real-time dialogue device 308 to risk handling platform 312, and also can receive various instructions issued by risk handling platform 312, and accurately forward them to autonomous driving domain controller 306 or other modules.

[0061] 6. Risk handling platform 312, in response to risk trigger signals for vehicles, supports the use of AI algorithms to analyze video streams and dialogue content to determine whether a vehicle has been involved in an accident. If the determination indicates an accident, it obtains the vehicle's current location information and determines the corresponding emergency handling area based on this information. It then sends control commands to the network domain controller 310 to move the vehicle to the emergency handling area. Simultaneously, it integrates with third-party systems such as the 120 emergency rescue platform and roadside assistance centers to automate the entire process of "hazard → response → handling."

[0062] Next, in Figure 3 On the basis of, such as Figure 4 As shown in the figure, this is a flowchart illustrating another risk management method based on an intelligent driving scenario according to an embodiment of the present invention. The method includes the following steps:

[0063] Step S402: Receive emergency operation button signal.

[0064] In one embodiment, the emergency button in the vehicle is pressed by the user. The onboard system captures this electrical signal and sends it as a risk trigger signal to the risk handling platform to initiate subsequent emergency response logic. However, it is necessary to distinguish between a real emergency and an accidental press at this point.

[0065] Step S404: Upload video stream data to the platform and establish a real-time call channel.

[0066] In one embodiment, after receiving the emergency button signal, the vehicle's autonomous driving domain controller can immediately call the onboard camera to collect real-time video stream data. The network connection domain controller is responsible for uploading the video stream data and the emergency button trigger signal to the risk processing platform. At the same time, the real-time dialogue device 308 in the vehicle is activated, establishing a two-way real-time communication channel between the user and the risk processing platform, providing a channel for subsequent interaction and confirmation.

[0067] Step S406: Determine whether the vehicle has been involved in an accident.

[0068] In one embodiment, the risk processing platform combines the received real-time video stream data with AI algorithms for image analysis, such as identifying collision marks, water depth, flames and smoke, suspicious persons, etc., as well as auxiliary sensor data synchronously uploaded by the autonomous driving domain controller, such as accelerometer values, IMU attitude, and water depth sensor readings. Finally, by comprehensively analyzing the above information, it determines whether the vehicle has been involved in an accident. If so, step S408 is executed; otherwise, step S410 is executed.

[0069] Step S408: The platform initiates a confirmation inquiry and handles erroneous operations.

[0070] In an embodiment, the risk processing platform initiates a voice / text prompt to the in-vehicle user through the real-time dialogue device, asking for example: "Emergency button trigger detected, is it a false operation?" If the platform receives feedback information from the user through the real-time dialogue device that it is a false operation, the risk processing platform can issue an instruction. The network connection domain controller is instructed to close the uplink and downlink communication link with the platform. And send a state reset instruction to the autonomous driving domain controller to make it exit the emergency state and restore the vehicle to normal driving mode.

[0071] Step S410, the platform issues an instruction to activate the vehicle emergency mode.

[0072] In an embodiment, after the risk processing platform confirms the real danger, it can immediately issue an "emergency mode activation" instruction to the autonomous driving domain controller through the network connection domain controller. The autonomous driving domain controller executes the instruction and enters a safety priority state. This state can include: automatically turning on the hazard warning flasher (double flasher), taking over the driving control authority, limiting the maximum vehicle speed, turning off unnecessary electrical equipment, and other safety measures.

[0073] Step S412, plan and control the vehicle to drive to the nearest emergency parking area.

[0074] In an embodiment, the above-mentioned platform can retrieve the nearest emergency parking area, such as a highway emergency lane, a service area safety parking area, and a designated risk avoidance point, from a preset database based on the current location of the vehicle. And generate the optimal risk avoidance path to the emergency parking area. At the same time, control the vehicle to autonomously drive to the emergency parking area.

[0075] Step S414, the platform triggers third-party alarm and synchronizes risk avoidance information.

[0076] In an embodiment, the risk processing platform can automatically trigger an alarm process to third-party rescue systems such as 110 alarm platform, 120 emergency center, and road rescue center according to the severity and type of the risk, such as collision severity, personnel trapped, fire, etc. The alarm information can include: the precise location of the vehicle, the type of risk identified, and the current state of the vehicle. At the same time, the platform can synchronize the location of the emergency parking area that the vehicle is going to and the planned risk avoidance route information to the above-mentioned third-party rescue system. This enables rescue forces to directly rush to the risk avoidance endpoint, realizing an efficient closed loop of active risk avoidance of the vehicle and precise response of the rescue forces.

[0077] Figure 5 FIG. 1 is a schematic structural diagram of an electronic device in an exemplary embodiment. Please refer to Figure 5At the hardware level, the electronic device includes a processor 502, an internal bus 510, a network interface 504, a memory 506, and a non-volatile memory 508, and of course, other required hardware. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs, and at the logical level, forms an intelligent driving scene-based risk processing apparatus. Of course, in addition to the software implementation, the present specification does not exclude other implementation manners, such as logic devices or software and hardware combined manners, and the like, that is, the execution subject of the following processing flow is not limited to each logical unit, but can also be hardware or logic devices.

[0078] Figure 6 The embodiment of the present application shows a block diagram of an intelligent driving scene-based risk processing apparatus. Please refer to Figure 6 The apparatus can be applied to the device as shown in Figure 5 to realize the technical solutions described in the present application, and the apparatus is applied to a vehicle; the apparatus includes:

[0079] An unexpected accident judgment unit 602 is configured to judge whether an unexpected accident occurs to the vehicle in response to a risk trigger signal for the vehicle.

[0080] An emergency treatment area confirmation unit 604 is configured to acquire current vehicle position information of the vehicle and determine a corresponding emergency treatment area according to the vehicle position information in a case where the judgment result represents that the unexpected accident occurs to the vehicle.

[0081] A vehicle control unit 606 is configured to control the vehicle to travel to the emergency treatment area.

[0082] Optionally, the risk trigger signal is generated in any of the following ways:

[0083] A passenger in the vehicle performs an alarm operation;

[0084] An alarm request from an external device is received;

[0085] Sensing data collected by an environment sensor of the vehicle meets a preset alarm condition.

[0086] Optionally, the unexpected accident judgment unit 602 is specifically configured to:

[0087] identify based on image data collected by the vehicle, and judge whether the unexpected accident occurs according to an identification result; and / or,

[0088] establish a voice interaction channel with the passenger in the vehicle, and judge whether the unexpected accident occurs according to voice feedback information.

[0089] Optionally, the emergency processing area confirmation unit 604 is specifically used for:

[0090] obtaining a plurality of alternative emergency areas, and respectively planning alternative paths from the vehicle to each alternative area based on the vehicle position information;

[0091] determining a corresponding path selection condition according to the accident type of the unexpected accident;

[0092] selecting a path matched with the path selection condition from the alternative paths as an emergency path based on the path selection condition, and determining the alternative area corresponding to the emergency path as the emergency processing area.

[0093] Optionally, the device further comprises:

[0094] a vehicle warning unit, configured to control the vehicle to stop nearby and start a vehicle warning device to perform a warning operation in a case where none of the alternative paths matches the path selection condition.

[0095] Optionally, the vehicle control unit 606 is specifically used for:

[0096] in a case where the vehicle is configured with an auxiliary driving system, directly controlling the vehicle to drive to the emergency processing area through the auxiliary driving system; or,

[0097] providing navigation information for driving to the emergency processing area to guide a driver of the vehicle to control the vehicle to drive to the emergency processing area.

[0098] Optionally, the device further comprises:

[0099] an emergency processing area adjustment unit, configured to periodically obtain the accident severity of the unexpected accident in a case where the vehicle drives to the emergency processing area;

[0100] dynamically adjusting the corresponding emergency processing area based on a change trend of the accident severity.

[0101] Optionally, the emergency processing area at least includes any of the following types:

[0102] an emergency lane;

[0103] a shoulder area;

[0104] an end-of-road area;

[0105] a right-turn-only lane area;

[0106] a lane splitting area;

[0107] an emergency escape lane;

[0108] Service area parking area.

[0109] The implementation process of the functions and roles of each unit in the above device is specifically described in the implementation process of the corresponding steps in the above method, which will not be repeated here.

[0110] For the device embodiment, since it basically corresponds to the method embodiment, the relevant part can be referred to the part of the method embodiment. The device embodiments described above are only illustrative, and the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place or distributed on multiple network units. Some or all modules can be selected to achieve the purpose of the scheme of the present specification according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0111] Based on the same idea as the above method, the present specification also provides a computer readable storage medium, which stores computer instructions, and the instructions are executed by a processor to realize the steps of the method according to any one of the above embodiments.

[0112] Based on the same idea as the above method, the present specification also provides a computer program product, which includes computer program / instructions, and the computer program / instructions are executed by a processor to realize the steps of the method according to any one of the above embodiments.

[0113] Embodiments of the subject matter and the functional operations described in this specification can be implemented in digital electronic circuitry, in tangibly-embodied computer software or firmware, in computer hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible non-transitory program carrier to be executed by, or to control the operation of, data processing apparatus. Alternatively or additionally, the program instructions can be encoded on an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal that is generated to encode information for transmission to suitable receiver apparatus for execution by a data processing apparatus. The computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0114] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit), and / or by programmable data processing apparatuses, which can be portion of hardware processing circuitry that executes specific tasks as described. Apparatuses can also be implemented as a combination of special purpose logic circuitry, e.g., an FPGA or an ASIC, and / or one or more programmable data processing apparatuses.

[0115] Computers suitable for the execution of a computer program include, by way of example, general and / or special purpose microprocessors, or any other kind of central processing unit. Generally, a central processing unit will receive instructions and data from a read-only memory and / or a random access memory. The essential elements of a computer are a central processing unit for performing or executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer need not have such devices. Moreover, a computer can be embedded in another device, e.g., a mobile telephone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a GPS receiver, a portable memory stick, or any other device that is

[0116] Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0117] While this specification contains many specifics, these should not be construed as limitations on the scope of any invention or on the required scope of patentable subject matter, but rather as descriptions of features specific to particular embodiments. Certain features that are described in this specification in the context of separate embodiments can also combine in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments or in any suitable sub-combination. Moreover, although features can be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination and the claimed combination can be directed to a sub-combination or a variation of a sub-combination.

[0118] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring such order nor limiting of all illustrations to that order, nor requiring that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing can be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0119] Accordingly, particular embodiments of the subject matter have been described. Further, the processes depicted in the accompanying figures do not require the particular order shown, or sequential order, to achieve desirable results. In certain implementations, multitasking and parallel processing can be advantageous.

[0120] The above description is merely illustrative of the exemplary embodiments of this description. It is not intended to limit the description in any way. Modifications, equivalent replacements, improvements, and the like that are made within the spirit and principle of the description should be included in the scope of the description.

Claims

1. A method for processing risk based on intelligent driving scene, characterized in that, The method comprises: in response to a risk trigger signal for a vehicle, determining whether the vehicle has an accident; if the determination result indicates that the vehicle has an accident, obtaining current vehicle position information of the vehicle, and determining a corresponding emergency processing area according to the vehicle position information; controlling the vehicle to travel to the emergency processing area; the determination of the corresponding emergency processing area according to the vehicle position information comprises: obtaining a plurality of alternative emergency areas, and respectively planning alternative paths of the vehicle to each alternative emergency area based on the vehicle position information; determining a corresponding path selection condition according to the accident type of the accident; based on the path selection condition, selecting a path matched with the path selection condition from the alternative paths as an emergency path, and determining the alternative emergency area corresponding to the emergency path as the emergency processing area.

2. The method of claim 1, wherein, The risk trigger signal is generated in any of the following ways: a passenger in the vehicle performs an alarm operation; receiving an alarm request from an external device; the sensing data collected by the environmental sensor of the vehicle meets the preset alarm condition.

3. The method of claim 1, wherein, The determination of whether the vehicle has an accident comprises: based on the image data collected by the vehicle, identifying and determining whether the accident occurs according to the identification result; and / or, establishing a voice interaction channel with the passenger in the vehicle, and determining whether the accident occurs according to the voice feedback information.

4. The method of claim 1, wherein, The method further comprises: if none of the alternative paths matches the path selection condition, controlling the vehicle to stop nearby and starting a vehicle warning device to perform a warning operation.

5. The method of claim 1, wherein, The control of the vehicle to travel to the emergency processing area comprises: if the vehicle is equipped with an auxiliary driving system, directly controlling the vehicle to travel to the emergency processing area through the auxiliary driving system; or providing navigation information for traveling to the emergency processing area to guide the driver of the vehicle to control the vehicle to travel to the emergency processing area.

6. The method of claim 1, wherein, The method further comprises: if the vehicle travels to the emergency processing area, periodically obtaining the severity of the accident; based on the change trend of the severity of the accident, dynamically adjusting the corresponding emergency processing area.

7. The method according to any one of claims 1 to 6, characterized in that, The emergency processing area at least comprises any of the following types: emergency lane; auxiliary lane area; road end area; right turn dedicated lane area; lane shunting area; emergency escape lane; service area parking area.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the steps of the method of any one of claims 1-7.

9. A computer program product, characterised in that, The computer program / instructions are executed by the processor to realize the steps of the method of any one of claims 1-7.

Images