TWI824788B - System and method of integrating traffic accident assistance investigation and safety of the intended functionality scene establishment - Google Patents

Abstract

A method of integrating a traffic accident assistance investigation and a Safety Of The Intended Functionality (SOTIF) scene establishment is proposed. The method is applied to a vehicle and includes performing an accident data collecting step, a data analyzing step, an investigation data automatically generating step and a scene database establishing step. The accident data collecting step includes configuring a cloud computing processing unit to collect an on-board diagnostic data, a digital video data and a control data from an on-board diagnostic device, a digital video recorder and a controller. The data analyzing step includes configuring the cloud computing processing unit to analyze the on-board diagnostic data, the digital video data and the control data to generate an accident record message and an action confirmation message. The accident record message includes a vehicle behavior message and a driving intention message. The investigation data automatically generating step includes configuring the cloud computing processing unit to automatically generate an accident assistance investigation data according to the vehicle behavior message, the driving intention message and the action confirmation message. The accident assistance investigation data includes an accident scene picture and a behavior characteristic report. The scene database establishing step includes configuring the cloud computing processing unit to establish an accident scene database according to the action confirmation message. The accident scene database includes a SOTIF scene. Therefore, the method of integrating the traffic accident assistance investigation and the SOTIF scene establishment of the present disclosure can generate the accident assistance investigation data effectively and quickly, reduce the labor cost and clarify the main cause of the accident.

Description

System and method integrating accident auxiliary identification and expected functional safety scenario establishment

The present invention relates to a system and method that integrates accident auxiliary identification and scene establishment, and in particular, relates to a system and method that integrates accident auxiliary identification and expected functional safety scene establishment.

The current method of identifying the causes of road traffic accidents is only for police officers to record post-accident data for analysis and judgment, and use driving recorders for assistance. Police officers must use huge and complex data (such as records, on-site road conditions, car body marks, human injuries, road marks, surveillance videos, driving recording devices, etc.) to deduce and verify the accident process. This makes current accidents The production of manual appraisal reports takes a long time, the labor cost remains high, and it is easy to conceal the truth. In addition, the number of self-driving vehicles is increasing. However, due to the limitations of the system functions of self-driving vehicles, the behavior of self-driving vehicles is different from the initial expectations in some situations. After the accident, the main cause of the accident cannot be clarified. It can be seen that the current market lacks a system and method that can effectively and quickly automatically produce identification reports, reduce labor costs, and clarify the main causes of accidents that integrates accident auxiliary identification and the establishment of expected functional safety scenarios. Therefore, relevant industries are seeking solutions. way.

Therefore, the purpose of the present invention is to provide a system and method that integrates accident auxiliary identification and the establishment of expected functional safety scenarios, which uses on-board diagnostic devices and digital video recorders to timely extract real-time data when a vehicle is involved in a traffic accident, so as to easily reproduce the accident. Focus on the vehicle status, driving intention and weather conditions at the moment of the accident to clarify system failures (controllers), mechanical failures or human misoperations, and provide forensic personnel for evaluation. In addition, the present invention can assist the automatic (assisted) driving controller to clarify the cause, collect expected functional safety scenarios, and provide technical improvement countermeasures to increase the application level and improve marketability. In summary, the present invention can solve the problems in the conventional technology that the production of manual appraisal reports is time-consuming, the labor cost remains high, it is easy to conceal the truth, and the self-driving vehicle cannot clarify the main cause of the accident after the accident.

An embodiment according to the structural aspect of the present invention provides a system that integrates accident auxiliary identification and establishment of expected functional safety scenarios, which is applied to vehicles. The system established by integrating accident auxiliary identification and expected functional safety scenarios includes an on-board diagnostic (OBD) device, a digital video recorder (DVR), a controller and a cloud computing processing unit. The vehicle-mounted diagnostic device is installed in the vehicle and acquires vehicle-mounted diagnostic data. A digital video recorder is installed in the vehicle and captures video data. The controller is installed in the vehicle and generates control data. The cloud computing processing unit signals are connected to the on-board diagnostic device, the digital video recorder and the controller, and is configured to perform operations including the following steps: the accident data collection step, the data analysis step, the automatic identification data production step and the scene database creation step. . The accident data collection step includes driving the cloud computing processing unit to collect vehicle diagnostic data, video data and control data from the vehicle diagnostic device, digital video recorder and controller. The data parsing step includes driving the cloud computing processing unit to parse vehicle diagnostic data, video data and control data into accident record information and action confirmation information. The accident record information includes vehicle behavior information and driving intention information. The step of automatically producing identification data includes driving the cloud computing processing unit to automatically produce accident auxiliary identification data based on vehicle behavior information, driving intention information and action confirmation information. Auxiliary accident identification materials include accident scene diagrams and behavioral characteristics reports. The scene database creation step includes driving the cloud computing processing unit to create an accident scene database based on the action confirmation information. The accident scenario database contains intended functional safety (Safety Of The Intended Functionality; SOTIF) scenarios.

In this way, the system established by integrating accident auxiliary identification and expected functional safety scenarios of the present invention can not only effectively and quickly automatically produce accident auxiliary identification data and reduce labor costs, but also clarify the main cause of the accident.

Other examples of the aforementioned implementation are as follows: the aforementioned cloud computing processing unit is configured to implement an accident judgment step, which includes driving the cloud computing processing unit to receive accident action information of the vehicle to generate an accident judgment result, and the accident judgment result represents the vehicle involved in the accident. Time for accidents.

Other examples of the aforementioned implementation are as follows: the aforementioned accident activation information includes at least one of airbag activation information, acceleration sensor sensing information, and sensor failure information.

Other examples of the aforementioned embodiments are as follows: the aforementioned controller includes one of an automatic driving system (Autonomous Driving System; ADS), an advanced driving assistance system (Advanced Driver Assistance Systems; ADAS), and an electronic control unit (Electronic Control Unit; ECU) .

Other examples of the aforementioned implementation are as follows: when the aforementioned controller includes one of an automatic driving system and an advanced driving assistance system, the operation confirmation information includes abnormal non-operation data and misoperation data. Abnormal non-action data represents the data generated when the controller should act but does not act. Misoperation data represents the data generated by the controller when it should not operate but does. The expected functional safety scenario corresponds to one of abnormal non-action data and mis-action data.

Other examples of the aforementioned embodiments are as follows: the aforementioned on-board diagnostic data includes vehicle load, rotational speed, vehicle speed, throttle position, engine running time, braking signal, steering wheel angle, tire pressure, car horn signal, and Global Positioning System (Global Positioning System); At least one of GPS) position and emergency warning light signal. Control data includes electronic control unit voltage, battery status (State of Charge; SOC), lateral error, longitudinal error, lidar signal, radar signal, diagnostic signal, steering wheel signal, electric/throttle signal, cause of dissociation event, and emergency button At least one of signal and body signal.

Other examples of the aforementioned implementation are as follows: the aforementioned vehicle behavior information includes at least one of snaking behavior, speeding behavior, sudden acceleration and deceleration behavior, and red light running behavior. The driving intention information includes one of a manual driving signal and an automatic driving signal.

Other examples of the foregoing implementation are as follows: the foregoing accident scene map includes the time of the accident, the location of the accident, and on-site processing summary information. The behavioral characteristics report includes the cause of the accident, the environmental conditions at the time of the accident, the process of the accident and the analysis of the accident. The accident analysis includes at least one of driving behavior, supporting information, right-of-way ownership and legal basis. The time of the accident, the location of the accident and on-site processing summary information are provided through the on-board diagnostic device and digital video recorder. The environmental conditions at the time of the accident were provided through a digital video recorder. The cause of the accident, the course of the accident and the analysis of the accident are provided through the on-board diagnostic device, digital video recorder and controller.

Other examples of the foregoing embodiments are as follows: the foregoing system that integrates accident auxiliary identification and expected functional safety scenarios further includes roadside facilities and road signs. The roadside facility signal is connected to the cloud computing processing unit. The roadside facility is installed on the road and detects the road to generate external data. The road signal signal is connected to the cloud computing processing unit, the road signal is installed on the road, and the road signal signal is generated. External data includes map information, and behavioral characteristics reports include external data and signaling signals.

An implementation method according to the method aspect of the present invention provides a method that integrates accident auxiliary identification and establishment of expected functional safety scenarios, which is applied to vehicles. The method that integrates accident auxiliary identification and expected functional safety scenario establishment includes accident data collection steps, data analysis steps, identification data automatic production steps, and scenario database establishment steps. The accident data collection step includes driving the cloud computing processing unit to collect on-board diagnostic data, video data and control data from the on-board diagnostic (On-Board Diagnostic; OBD) device, Digital Video Recorder (DVR) and controller. The data parsing step includes driving the cloud computing processing unit to parse vehicle-mounted diagnostic data, video data and control data into accident record information and action confirmation information. Accident record information includes vehicle behavior information and driving intention information. The step of automatically producing identification data includes driving the cloud computing processing unit to automatically produce accident auxiliary identification data based on vehicle behavior information, driving intention information and action confirmation information. Auxiliary accident identification materials include accident scene diagrams and behavioral characteristics reports. The scene database creation step includes driving the cloud computing processing unit to create an accident scene database based on the action confirmation information. The accident scenario database contains intended functional safety (Safety Of The Intended Functionality; SOTIF) scenarios.

Thus, the method of the present invention that integrates accident auxiliary identification and expected functional safety scenario establishment can not only effectively and quickly automatically produce accident auxiliary identification data and reduce labor costs, but also clarify the main cause of the accident.

Other examples of the foregoing embodiments are as follows: the foregoing method of integrating accident auxiliary identification and expected functional safety scene establishment further includes an accident judgment step, which includes driving the cloud computing processing unit to receive the accident action information of the vehicle to generate an accident judgment result, and the accident judgment result It represents a vehicle that was involved in an accident at the time of the accident.

Other examples of the aforementioned implementation are as follows: the aforementioned accident activation information includes at least one of airbag activation information, acceleration sensor sensing information, and sensor failure information.

Other examples of the aforementioned embodiments are as follows: the aforementioned controller includes one of an automatic driving system (Autonomous Driving System; ADS), an advanced driving assistance system (Advanced Driver Assistance Systems; ADAS), and an electronic control unit (Electronic Control Unit; ECU) .

Other examples of the aforementioned implementation are as follows: when the aforementioned controller includes one of an automatic driving system and an advanced driving assistance system, the operation confirmation information includes abnormal non-operation data and misoperation data. The abnormal non-actuated data represents the data generated when the controller should act but does not act. Misoperation data represents the data generated by the controller when it should not operate but does. The expected functional safety scenario corresponds to one of abnormal non-action data and mis-action data.

Other examples of the aforementioned embodiments are as follows: the aforementioned on-board diagnostic data includes vehicle load, rotational speed, vehicle speed, throttle position, engine running time, braking signal, steering wheel angle, tire pressure, car horn signal, and Global Positioning System (Global Positioning System); At least one of GPS) position and emergency warning light signal. Control data includes electronic control unit voltage, battery status (State of Charge; SOC), lateral error, longitudinal error, lidar signal, radar signal, diagnostic signal, steering wheel signal, electric/throttle signal, cause of dissociation event, and emergency button At least one of signal and body signal.

Other examples of the aforementioned implementation are as follows: the aforementioned vehicle behavior information includes at least one of snaking behavior, speeding behavior, sudden acceleration and deceleration behavior, and red light running behavior. The driving intention information includes one of a manual driving signal and an automatic driving signal.

Other examples of the foregoing implementation are as follows: the foregoing accident scene map includes the time of the accident, the location of the accident, and on-site processing summary information. The behavioral characteristics report includes the cause of the accident, the environmental conditions at the time of the accident, the process of the accident and the analysis of the accident. The accident analysis includes at least one of driving behavior, supporting information, right-of-way ownership and legal basis. The time of the accident, the location of the accident and on-site processing summary information are provided through the on-board diagnostic device and digital video recorder. The environmental conditions at the time of the accident were provided through a digital video recorder. The cause of the accident, the course of the accident and the analysis of the accident are provided through the on-board diagnostic device, digital video recorder and controller.

Other examples of the foregoing implementation are as follows: the foregoing behavioral characteristics report includes external data and signaling signals. The external data includes map information, and the external data is generated by roadside facilities detecting roads. Signal signals are generated by road signs.

Several embodiments of the present invention will be described below with reference to the drawings. For the sake of clarity, many practical details will be explained together in the following narrative. However, it will be understood that these practical details should not limit the invention. That is to say, in some embodiments of the present invention, these practical details are not necessary. In addition, for the sake of simplifying the drawings, some commonly used structures and components are shown in the drawings in a simple schematic manner; and repeated components may be represented by the same numbers.

In addition, when a certain component (or unit or module, etc.) is "connected" to another component in this article, it may mean that the component is directly connected to the other component, or it may mean that one component is indirectly connected to the other component. , meaning that there are other elements between the said element and another element. When it is stated that an element is "directly connected" to another element, it means that no other elements are interposed between the element and the other element. Terms such as first, second, third, etc. are only used to describe different components without limiting the components themselves. Therefore, the first component can also be renamed the second component. Moreover, the combination of components/units/circuit in this article is not a combination that is generally known, conventional or customary in this field. Whether the component/unit/circuit itself is common knowledge cannot be used to determine whether its combination relationship is easily understood in the technical field. Easily accomplished by the average person with knowledge.

Please refer to Figure 1 . Figure 1 is a schematic diagram of a system 100 that integrates accident auxiliary identification and expected functional safety scenario creation according to the first embodiment of the present invention. The system 100 established by integrating accident auxiliary identification and expected functional safety scenarios is applied to the vehicle 110 and includes an on-board diagnostic (On-Board Diagnostic; OBD) device 200, a digital video recorder (Digital Video Recorder; DVR) 300, a controller 400 and Cloud platform 500. The vehicle-mounted diagnostic device 200 is installed on the vehicle 110 and captures vehicle-mounted diagnostic data. The digital video recorder 300 is installed on the vehicle 110 and captures video data. The controller 400 is disposed on the vehicle 110 and generates control data. The cloud platform 500 includes a cloud computing processing unit 510 and a cloud memory 520 . The cloud computing processing unit 510 is connected to the vehicle diagnostic device 200, the digital video recorder 300 and the controller 400 via signals. First, the cloud computing processing unit 510 collects vehicle-mounted diagnostic data, video data and control data from the vehicle-mounted diagnostic device 200, the digital video recorder 300 and the controller 400. Then, the cloud computing processing unit 510 parses the vehicle diagnostic data, video data and control data into accident record information and action confirmation information. The accident record information includes vehicle behavior information and driving intention information. Then, the cloud computing processing unit 510 automatically generates accident auxiliary identification data based on the vehicle behavior information, driving intention information and action confirmation information. The accident auxiliary identification data includes accident scene diagrams and behavioral characteristics reports. In addition, the cloud computing processing unit 510 establishes an accident scene database based on the action confirmation information. The accident scene database includes expected functional safety (Safety Of The Intended Functionality; SOTIF) scenes. The cloud memory 520 is connected to the cloud computing processing unit 510 via signals, and is used to access vehicle diagnostic data, video data, control data, accident record information, action confirmation information, and accident auxiliary identification data.

In one embodiment (refer to FIG. 6 ), the system 100 that integrates accident auxiliary identification and expected functional safety scenario establishment may further include roadside facilities 610 and road signs 620 . The roadside facility 610 is connected with a signal to the cloud computing processing unit 510. The roadside facility 610 is installed on the road and detects the road to generate external data 612, and transmits the external data 612 to the cloud computing processing unit 510. The road signal 620 signal is connected to the cloud computing processing unit 510. The road signal 620 is installed on the road, generates a signal signal 622, and transmits the signal signal 622 to the cloud computing processing unit 510. The external data 612 includes the map information 612a, and the behavior characteristic report 516b includes the external data 612 and the signaling signal 622.

The above-mentioned cloud computing processing unit 510 can be a processor (Processor), a microprocessor (Microprocessor), an Electronic Control Unit (ECU), a computer, a mobile device processor or other computing processors, but the present invention does not use this is limited. The cloud computing processing unit 510 can execute a method that integrates accident auxiliary identification and establishment of expected functional safety scenarios. In addition, the cloud memory 520 can be a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions for execution by the cloud computing processing unit 510, but the invention is not limited thereto. .

Please refer to Figure 1 and Figure 2 together. Figure 2 is a schematic flowchart illustrating the method S0 of integrating accident auxiliary identification and expected functional safety scenario establishment according to the second embodiment of the present invention. The method S0 that integrates accident auxiliary identification and expected functional safety scenario creation is applied to the vehicle 110 and includes an accident data collection step S02, a data analysis step S04, an identification data automatic production step S06, and a scenario database creation step S08. The accident data collection step S02 includes driving the cloud computing processing unit 510 to collect vehicle diagnostic data 210, video data 310 and control data 410 from the vehicle diagnostic device 200, the digital video recorder 300 and the controller 400. The data parsing step S04 includes driving the cloud computing processing unit 510 to parse the on-board diagnostic data 210, video data 310 and control data 410 into accident record information 512 and action confirmation information 514. The accident record information 512 includes vehicle behavior information 512a and driving intention information 512b. . The step S06 of automatically producing the identification data includes driving the cloud computing processing unit 510 to automatically produce the accident auxiliary identification data 516 based on the vehicle behavior information 512a, the driving intention information 512b and the action confirmation information 514. The accident auxiliary identification data 516 includes the accident scene map 516a and Behavioral Characteristics Report 516b. The scene database creation step S08 includes driving the cloud computing processing unit 510 to create an accident scene database 518 based on the action confirmation information 514 . Incident scenario database 518 contains SOTIF scenarios 518a.

Thus, the system 100 that integrates accident auxiliary identification and expected functional safety scenario establishment and the method S0 that integrates accident auxiliary identification and expected functional safety scenario establishment of the present invention can not only effectively and quickly automatically produce accident auxiliary identification data 516 but also reduce labor costs. , and can also clarify the main cause of the accident.

Please refer to Figures 1, 2 and 3 together. Figure 3 is a schematic flowchart illustrating the method S2 of integrating accident auxiliary identification and expected functional safety scenario creation according to the third embodiment of the present invention. The method S2 that integrates accident auxiliary identification and expected functional safety scenario establishment is applied to the vehicle 110 and includes an accident determination step S20, an accident data collection step S22, a data analysis step S24, an identification data automatic production step S26, and a scenario database creation step S28. .

The accident determination step S20 is "accident occurrence", which includes driving the cloud computing processing unit 510 to receive the accident action information 511 of the vehicle 110 to generate an accident determination result. The accident determination result represents that the vehicle 110 was involved in an accident at the time of the accident. In one embodiment, the accident activation information 511 may include at least one of airbag activation information, acceleration sensor sensing information, and sensor failure information. The airbag activation information represents the information generated by the explosion of the airbag of the vehicle 110, and the acceleration sensor sensing information represents the information generated by the acceleration sensor (G-sensor) activation (the sensing value exceeds a preset value). The sensor failure information represents information generated when the sensor fails, but the present invention is not limited to this.

The accident data collection step S22 is "data collection", which includes driving the cloud computing processing unit 510 to collect vehicle diagnostic data 210, video data 310 and control data 410 from the vehicle diagnostic device 200, the digital video recorder 300 and the controller 400. Specifically, the cloud computing processing unit 510 will collect the on-board diagnostic data 210 from the on-board diagnostic device 200, the video data 310 of the digital video recorder 300, and the control data of the controller 400 when the vehicle 110 has an accident (i.e., the time of the accident). 410. The on-board diagnostic data 210 may include vehicle load, rotational speed, vehicle speed, throttle position, engine running time, braking signal, steering wheel angle, tire pressure, car horn signal, Global Positioning System (GPS) position and emergency warning light signal. At least one of. The video data 310 may have a video frame frequency (eg, one frame per second). The controller 400 may include one of an autonomous driving system (Autonomous Driving System; ADS), an advanced driver assistance system (Advanced Driver Assistance Systems; ADAS), and an electronic control unit (Electronic Control Unit; ECU). The control data 410 may include electronic control unit voltage (ie, ECU voltage), battery state of charge (State of Charge; SOC), lateral error, longitudinal error, lidar signal, radar signal, diagnostic signal, steering wheel signal, electric/throttle signal , at least one of the cause of the dissociation event, the emergency button signal and the body signal.

The data parsing step S24 includes driving the cloud computing processing unit 510 to parse the on-board diagnostic data 210, video data 310 and control data 410 into accident record information 512 and action confirmation information 514. The accident record information 512 includes vehicle behavior information 512a and driving intention information 512b. . Specifically, the vehicle behavior information 512a may include at least one of snaking behavior, speeding behavior, sudden acceleration and deceleration behavior, and red light running behavior. The driving intention information 512b may include one of a manual driving signal and an automatic driving signal. For example, when the vehicle behavior information 512a is the vehicle's head turning left and right (snaking behavior), the on-board diagnostic data 210 is the steering wheel angle. When the vehicle behavior information 512a indicates a sudden increase or decrease in acceleration and deceleration (sudden acceleration and deceleration behavior), the vehicle-mounted diagnostic data 210 includes changes in throttle position, fuel injection amount signal, accelerator pedal signal, and brake signal change. When the vehicle behavior information 512a is the vehicle's steering behavior, the on-board diagnostic data 210 is the turn signal activation signal. In addition, the data analysis step S24 will analyze the causes of each scenario (HW/SW failure analysis) for subsequent judgment. HW represents the cause caused by hardware; SW represents the cause caused by software.

The step S26 of automatically producing the identification data includes driving the cloud computing processing unit 510 to automatically produce the accident auxiliary identification data 516 based on the vehicle behavior information 512a, the driving intention information 512b and the action confirmation information 514. The accident auxiliary identification data 516 includes the accident scene map 516a and Behavioral Characteristics Report 516b. Specifically, the accident scene map 516a may include the time of the accident, the location of the accident, and on-site processing summary information. The behavioral characteristics report 516b can include the cause of the accident (preliminary judgment form), the environmental conditions at the time of the accident (weather, traffic signals), the course of the accident (identification certificate) and the accident analysis. The accident analysis includes driving behavior, supporting information, right-of-way ownership and At least one of the legal basis. Table 1 shows the relationship between the information items of the accident auxiliary identification data 516, the supporting evidence content and the hardware devices. From Table 1, it can be seen that the accident time, accident location and on-site processing summary data of the accident auxiliary identification data 516 are communicated with the digital through the on-board diagnostic device 200. The video recorder 300 provides; the environmental conditions at the time of the accident are provided through the digital video recorder 300; the cause of the accident, the accident process and the accident analysis are provided through the on-board diagnostic device 200, the digital video recorder 300 and the controller 400. Table I Information items Provide supporting content Hardware device Time and location of the accident Vehicle behavior, driving intention, external environment recognition and target trajectory OBD, DVR On-site processing summary information Vehicle behavior, driving intention, external environment recognition and target trajectory OBD, DVR Cause of the accident Vehicle behavior, driving intention, external environment recognition, controller action status OBD, DVR, controller Environmental conditions at the time of the accident External environment identification DVR What happened after the accident Vehicle behavior, driving intention, external environment recognition, controller action status OBD, DVR, controller Accident analysis Vehicle behavior, driving intention, external environment recognition, controller action status OBD, DVR, controller

The scene database creation step S28 includes driving the cloud computing processing unit 510 to create an accident scene database 518 based on the action confirmation information 514 . Incident scenario database 518 contains SOTIF scenarios 518a. Thereby, the method S2 of the present invention that integrates accident auxiliary identification and expected functional safety scene establishment uses the on-board diagnostic device 200, the digital video recorder 300, the controller 400, the roadside facilities 610 and the road signs 620 to timely propose when an accident occurs in the vehicle 110 Using real-time data, simple reconstruction of the accident focuses on the vehicle status, driving intention and weather conditions at the moment of the accident to clarify system failures, mechanical failures or human misoperations, and provide forensic personnel for evaluation. In addition, the present invention can assist the automatic (assisted) driving controller 400 to clarify the cause, collect SOTIF scenarios 518a, and provide technical improvement countermeasures to increase the application level and improve marketability. Therefore, the present invention can solve the problems in the conventional technology that the production of manual appraisal reports is time-consuming, the labor cost remains high, it is easy to conceal the truth, and the self-driving vehicle 110 cannot clarify the main cause of the accident after the accident.

Please refer to Figures 1, 2, 3, 4 and 5 together. Figure 4 illustrates the method S2 of Figure 3 that integrates accident auxiliary identification and expected functional safety scenario creation. An example flow chart; and Figure 5 is a schematic diagram illustrating the action confirmation and scene database creation step S28a of the controller 400 (ADS/ADAS) in Figure 4 . As shown in the figure, the method S2 that integrates accident auxiliary identification and expected functional safety scenario creation includes an accident judgment step S20, an accident data collection step S22, a data analysis step S24, an identification data automatic production step S26, and a scenario database creation step S28a. The scene database creation step S28a is an embodiment of the scene database creation step S28 in Figure 3 . The scene database creation step S28a includes the action confirmation step S282, and drives the cloud computing processing unit 510 to create the accident scene database 518 based on the action confirmation information 514. Incident scenario database 518 contains SOTIF scenarios 518a. The controller 400 signals connect the sensor and the actuator. When the controller 400 includes one of an automated driving system (ADS) and an advanced driving assistance system (ADAS), the operation confirmation information 514 includes abnormal non-operation data 514a and misoperation data 514b. The abnormal non-actuation data 514a represents data generated when the controller 400 should act but does not act (sensor misjudgment). The misoperation data 514b represents data generated when the controller 400 operates when it should not operate but does (actuator misjudgment). The SOTIF scene 518a corresponds to one of the abnormal non-action data 514a and the malfunction data 514b. The action confirmation step S282 is "action confirmation", which includes the drive controller 400 confirming whether the control data 410 belongs to the action confirmation information 514 and generating an action confirmation result. When the action confirmation result is yes, the control data 410 represents abnormal non-action or misoperation. The cloud computing processing unit 510 will establish an accident scene database 518 based on the action confirmation information 514; when the accident confirmation result is no, the control data 410 represents normal operation. Action. It is also worth mentioning that the SOTIF scenario 518a of the accident scene database 518 can be used for subsequent on-road and verification tests (allowing on-road and verification test scenarios and reports); in other words, the information of the SOTIF scenario 518a can be transmitted to the sensor The manufacturer (manufacturing end) of the device, actuator or controller 400 allows the manufacturer to conduct on-road and verification tests based on the information of the SOTIF scenario 518a.

Please refer to Figure 1, Figure 2, Figure 3, Figure 4 and Figure 6 together. Figure 6 is a schematic diagram illustrating the data analysis step S24 and the automatic identification data generation step S26 of Figure 4. As shown in the figure, the data analysis step S24 includes various state parameters of the incoming vehicle (vehicle 110), people, and roads; performs vehicle behavior identification, which uses vehicle speed, gyroscope, and accelerometer as various driving status identifications of the vehicle 110; execute Driving intention analysis, which is based on the judgment of braking, accelerator, vehicle speed, rotation speed and direction lights, fully presents the driving intention; performs external environment recognition and target trajectory, which is connected to road signs 620, Vehicle 110 and roadside facilities 610, and then obtain external data 612. The target object trajectory represents the driving trajectory of a target object other than the vehicle 110 (another vehicle at the time of the accident) through the accident, which can be obtained by the digital video recorder 300 or the roadside facility 610 . In addition, the accident scene map 516a in the identification data automatic production step S26 is a dynamic collision trajectory restored image, which can provide the accident process one minute before and after the collision of the vehicle 110 (providing the dynamic vehicle 110 driving trajectory and the process before and after the collision, as mentioned above The time before and after collision (1 minute each) and the sampling interval (per second) can be adjusted according to needs). Behavioral characteristics report 516b includes external data 612 and signaling signals 622. The external data 612 includes map information 612a, and the external data 612 is generated by the roadside facility 610 detecting the road. Signal signal 622 is generated by road sign 620 . Thereby, the data analysis step S24 and the identification data automatic production step S26 of the present invention can automatically produce the accident collision type, time, vehicle type, etc. based on the imported data, and combine it with the map information 612a (such as Google Map) to geographically Geographic Information System (GIS) for location analysis.

Please refer to Figure 1, Figure 2, Figure 3, Figure 4, Figure 5, Figure 6 and Figure 7 together. Figure 7 shows the integrated accident auxiliary identification and anticipatory functions of Figure 4. A schematic flowchart of the method S2 for establishing a safety scenario applied to an accident state. The accident state is that the first vehicle (front vehicle) and the second vehicle (rear vehicle) are running on the road. The first vehicle is equipped with an automatic emergency braking (Autonomous Emergency Braking; AEB) system, that is, the controller 400 of the first vehicle includes ADAS. . Maintain a safe driving distance between the first vehicle and the second vehicle. The first vehicle's AEB malfunctioned (sharp braking despite no obstacles ahead), causing a collision with the second vehicle. Based on the above accident status, the method S2 of the present invention that integrates accident auxiliary identification and expected functional safety scene establishment uses information from the on-board diagnostic device 200, the digital video recorder 300 and the controller 400 to learn that the characteristics of the accident process include: the first vehicle is equipped with AEB The system and functions are turned on, the external environment is sunny, no backlighting, smooth roads, the speed limit is 70kph, no red lights are run, there are no obstacles in front of the car, the first vehicle brakes suddenly and according to the control data 410, it is known that AEB does have a start message, so it is determined It is AEB misoperation (actuator misjudgment), so it is simultaneously included in SOTIF scenario 518a, as shown in the thick box and thick line in Figure 7. In terms of determining the fault of the accident, due to the sudden and sudden deceleration of the vehicle in front, the vehicle in front shared 70% of the fault and the vehicle behind shared 30% of the fault. In this way, the real cause of the accident can be clarified through the method S2 of the present invention that integrates accident auxiliary identification and expected functional safety scenario establishment, and the vehicle behind can reduce the liability (originally the vehicle behind has to bear 100% responsibility).

Please refer to Figures 1, 2, 3 and 8 together. Figure 8 illustrates the process of the second example of the method S2 of integrating accident auxiliary identification and expected functional safety scenario creation in Figure 3. Schematic diagram. As shown in the figure, the method S2 that integrates accident auxiliary identification and expected functional safety scenario creation includes an accident judgment step S20, an accident data collection step S22, a data analysis step S24, an identification data automatic production step S26, and a scenario database creation step S28b. The scene database creation step S28b is another embodiment of the scene database creation step S28 in Figure 3 . The scene database creation step S28b includes driving the cloud computing processing unit 510 to create an accident scene database 518 based on the action confirmation information 514. When the controller 400 includes an electronic control unit (ECU), the operation confirmation information 514 includes on-board diagnostic data 210 generated by the on-board diagnostic device 200 , video data 310 generated by the digital video recorder 300 , and control data 410 generated by the ECU. In this way, the present invention can record the scene of the vehicle 110 accident through the ECU of the controller 400 combined with the on-board diagnostic device 200 and the digital video recorder 300, and automatically generate the accident auxiliary identification data 516 as a basis for accident analysis.

It is understandable that the methods S0 and S2 of the present invention that integrate accident auxiliary identification and expected functional safety scenario establishment can be implemented through computer program products. The order of the implementation steps described in the above embodiments can be adjusted, combined or omitted according to actual needs. The above embodiments may be implemented using a computer program product, which may include a machine-readable medium storing a plurality of instructions that can program a computer to perform the steps in the above embodiments. Machine-readable media may be, but are not limited to, floppy disks, optical disks, CD-ROMs, magneto-optical disks, read-only memory, random access memory, erasable programmable read-only memory (EPROM), electronically erasable Except programmable read-only memory (EEPROM), optical or magnetic card, flash memory, or any machine-readable medium suitable for storing electronic instructions. Furthermore, embodiments of the present invention can also be downloaded as computer program products, which can transfer the computer program of the present invention from a remote computer by using data signals of a communication connection (such as a network connection or the like). Products to request computer.

It can be seen from the above embodiments that the present invention has the following advantages: First, through the on-board diagnostic device and the digital video recorder, real-time data when the vehicle is involved in a traffic accident can be extracted in a timely manner, and the accident can be easily reproduced focusing on the vehicle status and driving intention at the moment of the accident. and weather conditions to clarify system failures, mechanical failures or human errors and provide forensic personnel for evaluation. Secondly, the present invention can assist the automatic (assisted) driving controller to clarify the cause, collect SOTIF scenarios, and provide technical improvement countermeasures to increase the application level, improve marketability, and can solve the problem of manual identification report production in the conventional technology. It takes a long time, high labor costs, easy concealment, and the inability of self-driving vehicles to clarify the main cause of an accident after an accident occurs. Third, by recording the driving process information in detail through the equipment on the vehicle, in addition to clarifying the responsibility for the accident, streamlining the certification work schedule and reducing labor costs, it can also provide the operating conditions of the autonomous vehicle in the accident to the competent authorities. and reference for subsequent improvements by the car manufacturer.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Anyone skilled in the art can make various modifications and modifications without departing from the spirit and scope of the present invention. Therefore, the protection of the present invention is The scope shall be determined by the appended patent application scope.

100: A system that integrates accident auxiliary identification and expected functional safety scenarios 110:Vehicle 200: On-board diagnostic device 210: On-board diagnostic data 300:Digital video recorder 310:Video data 400:Controller 410:Control data 500:Cloud platform 510: Cloud computing processing unit 511:Accident action information 512:Accident record information 512a: Vehicle behavior information 512b: Driving intention information 514: Action confirmation information 514a: Abnormal unaction data 514b: Malfunction data 516: Auxiliary identification information for accidents 516a: Accident scene map 516b: Behavioral Characteristics Report 518:Accident scene database 518a:SOTIF scene 520:Cloud memory 610:Roadside facilities 612:External information 612a:Map information 620:Road Signal 622: Signal signal S0, S2: Method of integrating accident auxiliary identification and establishment of expected functional safety scenarios S02, S22: Accident data collection steps S04, S24: Data analysis steps S06, S26: Automatic production steps of identification data S08, S28, S28a, S28b: Scenario database creation steps S20: Accident judgment steps S282: Action confirmation steps

Figure 1 is a schematic diagram illustrating a system that integrates accident auxiliary identification and expected functional safety scenario establishment according to the first embodiment of the present invention; Figure 2 is a schematic flowchart illustrating a method for integrating accident auxiliary identification and expected functional safety scenario establishment according to the second embodiment of the present invention; Figure 3 is a schematic flowchart illustrating a method for integrating accident auxiliary identification and expected functional safety scenario establishment according to the third embodiment of the present invention; Figure 4 is a flow diagram illustrating a first example of the method of integrating accident auxiliary identification and expected functional safety scenario establishment in Figure 3; Figure 5 is a schematic diagram illustrating the steps of controller action confirmation and scene database creation in Figure 4; Figure 6 is a schematic diagram illustrating the data analysis steps and the automatic production steps of identification data in Figure 4; Figure 7 is a schematic process diagram illustrating the application of the method of integrating accident auxiliary identification and expected functional safety scenario creation in Figure 4 to an accident state; and FIG. 8 is a flow chart illustrating a second example of the method of integrating accident auxiliary identification and expected functional safety scenario creation in FIG. 3 .

210: On-board diagnostic data

310:Video data

410:Control data

512:Accident record information

512a: Vehicle behavior information

512b: Driving intention information

514: Action confirmation information

516: Auxiliary identification information for accidents

516a: Accident scene map

516b: Behavioral Characteristics Report

518:Accident scene database

518a:SOTIF scene

S0: A method that integrates accident auxiliary identification and establishment of expected functional safety scenarios

S02: Accident data collection steps

S04: Data analysis steps

S06: Steps for automatic production of identification data

S08: Steps to create scene database

Claims (16)

A system that integrates accident auxiliary identification and the establishment of expected functional safety scenarios is applied to a vehicle. The system that integrates accident auxiliary identification and the establishment of expected functional safety scenarios includes: an on-board diagnostic (On-Board Diagnostic; OBD) device, which is provided in the The vehicle captures on-board diagnostic data; a Digital Video Recorder (DVR) is mounted on the vehicle and captures video data; a controller is mounted on the vehicle and generates control data; and a cloud A computing processing unit, the signal is connected to the on-board diagnostic device, the digital video recorder and the controller, and is configured to perform an operation including the following steps: an accident data collection step, including driving the cloud computing processing unit to collect data from the on-board diagnosis The on-board diagnostic data, the video data and the control data of the device, the digital video recorder and the controller; a data analysis step includes driving the cloud computing processing unit to process the on-board diagnostic data, the video data and the control data Parsed into an accident record information and an action confirmation information, the accident record information includes a vehicle behavior information and a driving intention information; an identification data automatic production step includes driving the cloud computing processing unit according to the vehicle behavior information, the driving intention information; The intention information and the action confirmation information are automatically generated into an accident auxiliary identification data. The accident auxiliary identification data includes an accident scene diagram and a behavior characteristic report; and a scene database creation step includes driving the cloud computing processing unit. The element establishes an accident scene database based on the action confirmation information; wherein the action confirmation information includes: an abnormal non-action data, which represents data generated when the controller should act but does not act; and an error Action data represents data generated by the controller when it should not act but does act. Among them, the accident scenario database contains an expected functional safety (Safety Of The Intended Functionality; SOTIF) scenario. The expected functional safety The scene corresponds to one of the abnormal non-action data and the erroneous action data. The system that integrates accident auxiliary identification and expected functional safety scenario establishment as described in claim 1, wherein the cloud computing processing unit is configured to implement further includes: an accident determination step, including driving the cloud computing processing unit to receive an The accident action information is used to generate an accident judgment result, and the accident judgment result represents that the vehicle was involved in an accident at an accident time. The system established by integrating accident auxiliary identification and expected functional safety scenarios as described in claim 2, wherein the accident operation information includes at least one of an airbag operation information, an acceleration sensor sensing information and a sensor failure information. By. Fusion of accident-assisted identification and anticipation as described in request 1 A system established in a functional safety scenario, in which the controller includes one of an autonomous driving system (Autonomous Driving System; ADS) and an advanced driver assistance system (Advanced Driver Assistance Systems; ADAS). The system established by integrating accident auxiliary identification and expected functional safety scenarios as described in claim 1, wherein the on-board diagnostic data includes a vehicle load, a rotational speed, a vehicle speed, a throttle position, an engine running time, a braking signal, At least one of a steering wheel angle, a tire pressure, a car horn signal, a Global Positioning System (GPS) position and an emergency warning light signal; and the control data includes an electronic control unit voltage and a battery power State of Charge (SOC), lateral error, longitudinal error, a radar signal, a radar signal, a diagnostic signal, a steering wheel signal, an electric/throttle signal, a dissociation event cause, and an emergency button signal and at least one of a body signal. The system established by integrating accident auxiliary identification and expected functional safety scenarios as described in claim 1, wherein the vehicle behavior information includes at least one of a snaking behavior, a speeding behavior, a sudden acceleration and deceleration behavior, and a red light running behavior; and The driving intention information includes one of a manual driving signal and an automatic driving signal. The system established by integrating accident auxiliary identification and expected functional safety scenarios as described in request 1, wherein the accident scene map includes an accident time, an accident location, and an on-site processing summary information; and the behavioral characteristics report includes an accident The cause, the environmental conditions at the time of the accident, the course of the accident, and the accident analysis. The accident analysis includes at least one of a driving behavior, supporting information, ownership of the right of way, and a legal basis; among them, the time of the accident, the location of the accident And the on-site processing summary information is provided through the on-board diagnostic device and the digital video recorder, the environmental conditions at the time of the accident are provided through the digital video recorder, the cause of the accident, the course of the accident and the accident analysis are provided through the on-board diagnostic device, The digital video recorder and the controller are provided. The system established by integrating accident auxiliary identification and expected functional safety scenarios as described in claim 1 further includes: a roadside facility, the signal is connected to the cloud computing processing unit, the roadside facility is installed on a road, and detects the road to generate An external data; and a road sign, the signal is connected to the cloud computing processing unit, the road sign is installed on the road, and a traffic signal signal is generated; wherein, the external data includes a map information, and the behavior characteristic report includes The external data and the semaphore signal. A scenario that integrates accident auxiliary identification and expected functional safety The established method is applied to a vehicle. The method that integrates accident auxiliary identification and expected functional safety scenario establishment includes: an accident data collection step, including driving a cloud computing processing unit to collect data from an on-board diagnosis (On-Board Diagnostic; OBD) a device, a digital video recorder (DVR) and a controller, a vehicle-mounted diagnostic data, a recording data and a control data; a data parsing step including driving the cloud computing processing unit to process the vehicle-mounted diagnostic data, The video data and the control data are parsed into an accident record information and an action confirmation information. The accident record information includes a vehicle behavior information and a driving intention information; an identification data automatic production step includes driving the cloud computing processing unit based on The vehicle behavior information, the driving intention information and the action confirmation information are automatically generated into an accident auxiliary identification data. The accident auxiliary identification data includes an accident scene map and a behavior characteristic report; and a scene database creation step, including Driving the cloud computing processing unit to establish an accident scene database based on the action confirmation information; wherein the action confirmation information includes: an abnormal non-action data, which represents the controller generated under the situation that it should act but does not act. data; and a misoperation data, which represents the data generated by the controller when it should not operate but does operate; wherein the accident scenario database includes an expected functional safety (Safety Of The Intended Functionality; SOTIF) scenario , the The expected functional safety scenario corresponds to one of the abnormal non-action data and the malfunction data. The method of integrating accident auxiliary identification and expected functional safety scenario establishment as described in claim 9 further includes: an accident judgment step, including driving the cloud computing processing unit to receive an accident action information of the vehicle to generate an accident judgment result, The accident determination result means that the vehicle was involved in an accident at the time of the accident. The method of integrating accident auxiliary identification and expected functional safety scenario establishment as described in claim 10, wherein the accident action information includes at least one of an airbag activation information, an acceleration sensor sensing information and a sensor failure information. By. The method of integrating accident assistance identification and expected functional safety scenario establishment as described in claim 9, wherein the controller includes an automatic driving system (Autonomous Driving System; ADS) and an advanced driver assistance system (Advanced Driver Assistance Systems; ADAS) one of. The method of integrating accident auxiliary identification and expected functional safety scenario establishment as described in claim 9, wherein the on-board diagnostic data includes a vehicle load, a rotational speed, a vehicle speed, a throttle position, an engine running time, a braking signal, One wheel turns Angle, a tire pressure, a car horn signal, a Global Positioning System (GPS) position and at least one of an emergency warning light signal; and the control data includes an electronic control unit voltage, a battery power status ( State of Charge (SOC), a lateral error, a longitudinal error, a lidar signal, a radar signal, a diagnostic signal, a steering wheel signal, an electric/throttle signal, a dissociation event cause, an emergency button signal and a At least one of the body signals. The method of integrating accident auxiliary identification and expected functional safety scenario establishment as described in claim 9, wherein the vehicle behavior information includes at least one of a snaking behavior, a speeding behavior, a sudden acceleration and deceleration behavior, and a red light running behavior; and The driving intention information includes one of a manual driving signal and an automatic driving signal. The method of integrating accident auxiliary identification and expected functional safety scenario establishment as described in request item 9, wherein the accident scene map includes an accident time, an accident location, and an on-site processing summary information; and the behavioral characteristics report includes an accident The cause, the environmental conditions at the time of the accident, the course of the accident, and the accident analysis. The accident analysis includes at least one of a driving behavior, supporting information, right-of-way ownership, and a legal basis; Among them, the time of the accident, the location of the accident and the on-site processing summary information are provided through the on-board diagnostic device and the digital video recorder, the environmental conditions at the time of the accident are provided through the digital video recorder, the cause of the accident, the process of the accident and The accident analysis is provided through the on-board diagnostic device, the digital video recorder and the controller. The method of integrating accident auxiliary identification and expected functional safety scenario establishment as described in claim 9, wherein the behavioral characteristic report includes: an external data, including a map information, the external data is generated by a roadside facility detecting a road ; and a sign signal, generated by a road sign.

Images