System and method for predicting injuries to vehicle occupants after an event

Abstract

System (100) for predicting injuries to vehicle occupants after an event characterized by: a vehicle event database (208) that contains simulation-based vehicle event metadata associated with a vehicle architecture, wherein the simulation-based generation of vehicle event metadata is based at least partially on the following factors: Determining vehicle event pulses (500A, 500B) for the vehicle architecture; Applying the vehicle event impulses (500A, 500B) to a vehicle simulation model (600) of the vehicle architecture; Collecting injury data (700A, 700B) associated with body regions of a simulated occupant within the vehicle simulation model (600), resulting from the application of the vehicle event impulses (500A, 500B) to the vehicle simulation model (600); and Predictions of the probability of injury for each of the body regions of an actual occupant of a vehicle (10) using the vehicle architecture based on the injury data (700A, 700B); at least one processor (44) that is communicatively connected to the vehicle event database (208); and at least one memory (32) that is communicatively coupled to the at least one processor (44), wherein the at least one memory (32) contains instructions which, when executed by the at least one processor (44), cause the at least one processor (44) to: Receiving a vehicle event message from the vehicle (10) with the vehicle architecture; Receiving vehicle data associated with the vehicle (10) and occupant data associated with the actual occupant of the vehicle (10); Retrieving simulation-based vehicle event metadata associated with the vehicle architecture from the vehicle event database (208); and Prediction of an injury in a first body region of the actual occupant's body regions based on vehicle data, occupant data and simulation-based vehicle event metadata using an injury prediction model (210).

Description

[0001] The technical field generally refers to vehicles and, in particular, to systems and methods for predicting injuries to vehicle occupants after an incident.

[0002] Actual vehicle event data is typically used by statistical analysis models and machine learning models to predict occupant injuries in vehicle event situations. A vehicle event can be a collision between one vehicle and another, or a collision between a vehicle and an object, that may result in injuries to one or more occupants. The availability of actual vehicle event data can be limited for various vehicle event scenarios. Examples of such scenarios include second- and third-row occupants, occupants who are not in the correct position, vulnerable occupants, and new vehicle structures (e.g., electric vehicles and autonomous vehicles).The limitations of actual vehicle incident data can pose challenges for statistical analysis models and machine learning models when it comes to accurately predicting vehicle occupant injuries in vehicle incident situations. First responders and hospital staff often rely on predicting vehicle occupant injuries to effectively triage, prioritize, and transport injured occupants. Inaccuracies in predicting vehicle occupant injuries can impair the ability of first responders and / or hospital staff to adequately support the needs of vehicle occupants and treat their injuries in a timely manner.

[0003] DE 10 2021 132 424 A1 describes a device and a method for controlling a vehicle airbag. The device and the method determine whether an airbag should be deployed based on a post-injury probability for the human, which is calculated using a model for the probability of human injury and the learning of a Bayesian network (feedback learning).The device comprises: a human injury probability calculation unit configured to calculate a human injury condition probability and a human injury prediction probability based on vehicle motion information measured by a sensing device; a learning unit configured to calculate a post-human injury probability by performing probability-based real-time feedback machine learning based on the human injury condition probability and the human injury prediction probability; and an airbag deployment determination unit configured to determine whether an airbag should be deployed based on the post-human injury probability.

[0004] DE 10 2022 104 129 A1 describes a method for determining the health impact of a collision involving a motor vehicle on at least one occupant of that vehicle. A monitoring device evaluates motion data recorded by the vehicle for at least a predetermined period after the collision event, using a predetermined predictive function to determine at least one impact parameter relating to the health impact on the at least one occupant of the vehicle resulting from the movement during that predetermined period. The method further describes the use of a predictive function trained on a training dataset using a predetermined machine learning algorithm. This training dataset comprises simulated motion data and simulated impact parameters.

[0005] German patent DE 10 2022 120 111 A1 describes a monitoring system that can include a memory containing computer-readable instructions and a processor operatively coupled to the memory. The processor can read and execute the computer-readable instructions to perform operations or control their execution. These operations can include receiving, prior to a collision involving a vehicle, sensor data representative of a feature of an internal environment and determining that the collision has occurred. The operations can also include automatically instructing a sensor, based on the collision, to generate other sensor data representative of another feature of the internal environment. Furthermore, the operations can include receiving this other sensor data from the sensor and comparing it with accident data corresponding to previous accidents.The accident data may include a diagnosed injury and the severity of each previous accident. The procedures may include determining the severity of the collision based on comparison.

[0006] DE 10 2022 126 318 A1 describes a system for detecting one or more properties of an object inside a motor vehicle, which has one or more sensors mounted inside or on the outside of the vehicle, wherein each sensor is configured to detect the object's location, orientation, size, and / or type, and a controller, which is operationally connected to the one or more sensors and configured to assess whether the object is arranged in a predefined, warning-causing configuration. A method for detecting properties of the object inside the vehicle includes determining the object's location, orientation, size, and / or type using the one or more sensors and assessing whether the object is arranged in a predefined, warning-causing configuration.

[0007] DE 10 2018 118 129 A1 describes an occupant protection system for a motor vehicle, a corresponding operating procedure, and a corresponding motor vehicle. The occupant protection system comprises an active restraint system, a detection device for recording the position of a vehicle occupant, and a corresponding data processing device. The data processing device is configured to simulate, for at least one accident scenario, the movement of the vehicle occupant relative to the active restraint system and the activation of the active restraint system, based on the recorded position, using a predefined simulation model. Furthermore, the data processing device is designed to determine a activation strategy for the active restraint system based on the simulation result, thereby improving the protection of the vehicle occupant.

[0008] It can be considered a task to provide improved methods and systems for predicting injuries to vehicle occupants after an accident using simulation-based vehicle event metadata.

[0009] A system according to the invention for predicting injuries to vehicle occupants after an event comprises a vehicle event database, at least one processor, and at least one memory. The at least one processor is communicatively connected to the vehicle event database. The at least one memory is communicatively connected to the at least one processor. The vehicle event database contains simulation-based vehicle event metadata that is linked to a vehicle architecture.The simulation-based generation of vehicle event metadata is based at least partially on: determining vehicle event pulses for the vehicle architecture; applying the vehicle event pulses to a vehicle simulation model of the vehicle architecture; collecting injury data associated with body regions of a simulated occupant within the vehicle simulation model, resulting from the application of the vehicle event pulses to the vehicle simulation model; and predicting an injury probability for each of the body regions of an actual occupant of a vehicle with the vehicle architecture based on the injury data.The at least one memory contains instructions which, when executed by the at least one processor, cause the at least one processor to receive a vehicle event message from a vehicle with the vehicle architecture; to receive vehicle data associated with the vehicle and occupant data associated with an actual occupant of the vehicle; to retrieve the simulation-based vehicle event metadata associated with the vehicle architecture from the vehicle event database; and to predict an injury to a first body region of the body regions of the actual occupant based on the vehicle data, the occupant data, and the simulation-based vehicle event metadata using an injury prediction model.

[0010] In at least one embodiment, the at least one memory contains further instructions which, when executed by the at least one processor, cause the at least one processor to transmit the predicted injury to the first body region of the actual occupant to at least one device from the group of first responders and hospital devices.

[0011] In at least one embodiment, the vehicle event impulses are vehicle acceleration or vehicle speed event impulses.

[0012] In at least one embodiment, the vehicle event impulses are applied to the vehicle simulation model under a variety of vehicle event conditions, including a variety of impact vehicle speeds, a variety of impact directions, a variety of vehicle seat orientations, a variety of occupant seating positions, a variety of occupant vulnerabilities, a variety of occupant postures, and biometric occupant data.

[0013] In at least one embodiment, one of the several body postures of the occupant is a lying position.

[0014] In at least one embodiment, the body regions comprise a head region, a neck region, a thoracic region, a thigh region, a lower leg region and an abdominal region.

[0015] In at least one embodiment, the simulation-based generation of vehicle event metadata is based at least partially on the prediction of an overall probability of injuries to the simulated occupant based on the injury data.

[0016] In at least one embodiment, the predicted probability of overall injury to the simulated occupant is adjusted in accordance with a parameter for the occupant's frailty.

[0017] In at least one embodiment, the predicted probability of injury for each of the simulated occupant's body regions is adjusted in accordance with a parameter for the occupant's frailty.

[0018] In at least one embodiment, the vehicle event database contains current vehicle event metadata that is linked to the vehicle architecture.

[0019] In at least one embodiment, the injury prediction model is a statistical analysis model or a machine learning model.

[0020] In at least one embodiment, the simulation-based vehicle event metadata includes a plurality of impact directions, the vehicle event impulses, biometric occupant data, a plurality of occupant seating positions, restraint data, the probability of injury for each of the body regions, and a probability of overall injury.

[0021] In at least one embodiment, the vehicle data includes a body type, a vehicle model year, a total delta velocity, a principal force direction, delta velocities along a first and a second axis, a resulting impact delta velocity and delta direction, rollover data, and the orientation of the vehicle seats.

[0022] In at least one embodiment, the occupant data includes the occupant's actual seating position, the occupant's actual posture in relation to a seat and restraint system, the occupant's actual belt data, the occupant's actual weight, the occupant's actual height, the occupant's actual frailty parameter, the occupant's actual gender, the occupant's actual movement, and the occupant's actual position.

[0023] An inventive method for predicting injuries to vehicle occupants after an event is provided. The method comprises providing a vehicle event database with simulation-based vehicle event metadata associated with a vehicle architecture. The simulation-based generation of vehicle event metadata is based at least partially on: determining vehicle event pulses for the vehicle architecture; applying the vehicle event pulses to a vehicle simulation model of the vehicle architecture; collecting injury data associated with body regions of a simulated occupant within the vehicle simulation model, resulting from the application of the vehicle event pulses to the vehicle simulation model; and predicting an injury probability for each of the body regions of an actual occupant of a vehicle with the vehicle architecture based on the injury data.The procedure also includes: receiving a vehicle event message from a vehicle with the vehicle architecture; receiving vehicle data associated with the vehicle and occupant data associated with an actual occupant of the vehicle; retrieving the simulation-based vehicle event metadata associated with the vehicle architecture from the vehicle event database; and predicting an injury to a first body region of the actual occupant's body regions based on the vehicle data, the occupant data, and the simulation-based vehicle event metadata using an injury prediction model.

[0024] In at least one embodiment, the method further comprises transmitting the predicted injury to the first body region of the actual occupant to at least one device from the group of first responders and hospital devices.

[0025] In at least one embodiment, the vehicle event impulses are applied to the vehicle simulation model under a variety of vehicle event conditions, including a variety of impact vehicle speeds, a variety of impact directions, a variety of vehicle seat orientations, a variety of occupant seating positions, a variety of occupant vulnerabilities, a variety of occupant postures, and biometric occupant data.

[0026] In at least one embodiment, the body regions comprise a head region, a neck region, a thoracic region, a thigh region, a lower leg region and an abdominal region.

[0027] In at least one embodiment, the predicted probability of injury for each of the simulated occupant's body regions is adjusted in accordance with a parameter for the occupant's frailty.

[0028] The exemplary embodiments are described below in conjunction with the following figures, where the same numbers denote the same elements: Fig. Figure 1 is a functional block diagram of a vehicle that is communicatively coupled to a system for predicting injuries to vehicle occupants after an event; Fig. Figure 2 is a functional block diagram of a system for predicting injuries to vehicle occupants after an event; Fig. 3 is a system that includes a system for predicting injuries to vehicle occupants after an event; Fig. Figure 4 is a flowchart representation of an exemplary procedure for generating simulation-based vehicle event metadata for storage in the vehicle event database; Fig. 5A-5B are graphical representations of exemplary vehicle event impulses; Fig. Figure 6 is a representation of an exemplary vehicle simulation model; Fig. Figures 7A-7B are graphical representations of exemplary injury data; and Fig. Figure 8 is a flowchart representation of a procedure for predicting injuries to vehicle occupants after an event.

[0029] Fig. Figure 1 shows a functional block diagram of a vehicle 10 which, according to at least one embodiment, is communicatively connected to a system 100 for predicting injuries to vehicle occupants after an event. The system 100 for predicting injuries to vehicle occupants after an event is configured to be communicatively coupled to a device 102 of the first responder. In various embodiments, the system 100 for predicting injuries to vehicle occupants after an event is configured to be communicatively coupled to a device in the hospital. The vehicle 10 generally comprises a chassis 12, a body 14, front wheels 16, and rear wheels 18. While the vehicle 10 is depicted as a passenger car in the embodiment shown, the vehicle 10 can also include other vehicle types such as trucks, sport utility vehicles (SUVs), and motorhomes (RVs).

[0030] In various embodiments, the body 14 is arranged on the chassis 12 and essentially encloses components of the vehicle 10. The body 14 and the chassis 12 can together form a frame. The wheels 16-18 are each rotatably connected to the chassis 12 near a corner of the body 14.

[0031] In various embodiments, the vehicle 10 is an autonomous or semi-autonomous vehicle that is automatically controlled to transport passengers and / or cargo from one place to another. In one exemplary embodiment, the vehicle 10 is a so-called Level 2, Level 3, Level 4, or Level 5 automation system. Level 2 automation means that the vehicle assists the driver with various driving tasks under the driver's supervision. Level 3 automation means that, under certain circumstances, the vehicle can take over all driving functions. All major functions are automated, including braking, steering, and accelerating. At this level, the driver can completely relinquish control until the vehicle instructs them otherwise. A Level 4 system signifies a "high degree of automation," meaning that the vehicle can operate the vehicle independently without any intervention.An automated driving system performs all aspects of the dynamic driving task, even if a human driver does not respond appropriately to a request for intervention. A Level 5 system means "full automation," i.e., an automated driving system fully performs all aspects of the dynamic driving task under all road and environmental conditions that a human driver could handle.

[0032] As shown, the vehicle 10 generally comprises a drive system 20, a transmission system 22, a steering system 24, a braking system 26, a sensor system 28, an actuator system 30, at least one data storage device 32, at least one control unit 34, and a communication system 36. The control unit 34 is configured to implement an automated driving system (ADS). The drive system 20 is configured to generate energy for propelling the vehicle. In various embodiments, the drive system 20 may include an internal combustion engine, an electric machine such as a traction motor, a fuel cell propulsion system, and / or any other type of drive configuration. The transmission system 22 is configured to transmit the power of the drive system 20 to the vehicle wheels 16-18 according to selectable gear ratios.According to various embodiments, the transmission system 22 can comprise a continuously variable automatic transmission, a continuously variable transmission, or another suitable transmission. The braking system 26 is configured to apply a braking torque to the vehicle wheels 16-18. In various embodiments, the braking system 26 can comprise friction brakes, wire brakes, a regenerative braking system such as an electric motor, and / or other suitable braking systems.

[0033] The steering system 24 is configured to influence the position of the vehicle wheels 16. Although a steering wheel and steering column are shown for illustrative purposes, in some embodiments considered within the scope of this description, the steering system 24 may not include a steering wheel and / or steering column. The steering system 24 comprises a steering column coupled to an axle 50, which is connected to the front wheels 16, for example, via a rack and pinion or another mechanism (not shown). Alternatively, the steering system 24 may comprise a steering wheel system with actuators connected to each of the front wheels 16.

[0034] The sensor system 28 comprises one or more devices 40a-40n that detect observable conditions of the external environment and / or the internal environment of the vehicle 10. The devices 40a-40n may include, but are not limited to, radars, lidar, global positioning systems, optical cameras, thermal cameras, ultrasonic sensors and / or other sensors.

[0035] The vehicle dynamics sensors provide data on vehicle dynamics, including longitudinal speed, yaw rate, lateral acceleration, longitudinal acceleration, etc. The vehicle dynamics sensors can include wheel sensors that measure information about one or more wheels of the vehicle 10. In one embodiment, the wheel sensors have wheel speed sensors connected to each of the wheels 16-18 of the vehicle 10. Furthermore, the vehicle dynamics sensors can include one or more accelerometers (as part of an inertial measurement unit (IMU)) that measure information about the acceleration of the vehicle 10. In various embodiments, the accelerometers measure one or more acceleration values ​​for the vehicle 10, including lateral and longitudinal acceleration and yaw rate.

[0036] The actuation system 30 comprises one or more devices 42a-42n that control one or more vehicle functions, such as, but not limited to, the drive system 20, the transmission system 22, the steering system 24, and the braking system 26. In various embodiments, the vehicle features may also include interior and / or exterior features of the vehicle, such as doors, a trunk, and cabin features such as air conditioning, music, lighting, etc. (not numbered).

[0037] The communication system 36 is configured to wirelessly transmit information to and from other units 48, such as, but not limited to, other vehicles (“V2V” communication), infrastructure (“V2I” communication), remote systems, and / or personal devices. In at least one embodiment, the communication system 36 is configured to communicate wirelessly with the system 100 for predicting injuries to vehicle occupants after an event. In an exemplary embodiment, the communication system 36 is a wireless communication system configured to communicate via a wireless local area network (WLAN) using IEEE 802.11 standards or using cellular data communication. However, additional or alternative communication methods, such as a dedicated short-range communication channel (DSRC), are also considered within the scope of this description.DSRC channels refer to one- or two-way short- to medium-range wireless communication channels specifically designed for use in motor vehicles, as well as a range of protocols and standards.

[0038] The device 32 stores data for use in the ADS of the vehicle 10. In various embodiments, the device 32 stores defined maps of the navigable environment. In various embodiments, the defined maps can be predefined by and obtained from a remote system. For example, the defined maps can be compiled by the remote system and transmitted to the vehicle 10 (wirelessly and / or via a wired connection) and stored in the data storage device 32. As can be seen, the device 32 can be part of the control unit 34, separate from the control unit 34, or part of the control unit 34 and part of a separate system.

[0039] The control unit 34 comprises at least one processor 44 and a computer-readable device or medium 46. The processor 44 can be any custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor among several processors connected to the control unit 34, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, any combination thereof, or generally any device for executing instructions. The computer-readable devices or media 46 can include volatile and non-volatile memory, such as read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM). KAM is a persistent or non-volatile memory that can be used to store various operating variables while the processor 44 is powered off.The computer-readable storage device or media 46 can be implemented using any number of known storage devices such as PROMs (programmable read-only memory), EPROMs (electrically erasable PROMs), EEPROMs (electrically erasable PROMs), flash memory, or other electrical, magnetic, optical, or combined storage devices capable of storing data, some of which represent executable instructions used by the control unit 34 in controlling the vehicle 10.

[0040] The instructions can include one or more separate programs, each containing an ordered list of executable instructions for implementing logical functions. When executed by the processor 44, the instructions receive and process signals from the sensor system 28, perform logic, calculations, methods, and / or algorithms for the automatic control of the vehicle 10 components, and generate control signals for the actuator system 30 to automatically control the vehicle 10 components based on the logic, calculations, methods, and / or algorithms. Although in Fig. While only one control unit 34 is shown in Figure 1, embodiments of the vehicle 10 may include any number of control units 34 that communicate via any suitable communication medium or combination of communication media and cooperate to process the sensor signals, perform logic, calculations, methods and / or algorithms, and generate control signals to automatically control features of the vehicle 10. In various embodiments, the control unit(s) 34 are configured to implement ADS.

[0041] In Fig. Figure 2 shows a functional block diagram of a system 100 for predicting vehicle occupant injuries after an event according to at least one embodiment. The system 100 for predicting vehicle occupant injuries after an event comprises at least one processor 200 and at least one memory 202. The processor(s) 200 is / are communicatively connected to the at least one memory 202. The processor(s) 200 is / are a programmable device containing one or more instructions that are stored in or connected to the at least one memory 202. The at least one memory 202 contains instructions that the processor(s) 200 is / are configured to execute. The at least one memory 202 contains a vehicle data module 204, an occupant data module 206, a vehicle event database 208, and an injury prediction model 210.

[0042] A vehicle event (also referred to as an event) encompasses contact between one vehicle and another vehicle, or contact between the vehicle and an object, that may result in injury to one or more occupants of the vehicle. The vehicle data module 204 is configured to receive a vehicle event message from a vehicle 10 involved in a vehicle event, along with vehicle data associated with that vehicle 10. The occupant data module 206 is configured to receive occupant data associated with the actual occupants of the vehicle 10. The vehicle event database 208 is configured to store simulation-based vehicle event metadata associated with the vehicle architecture of the vehicle 10.The injury prediction model 210 is configured to predict injuries to one or more body regions of the actual vehicle occupants based on vehicle data, occupant data, and simulation-based vehicle event metadata. The System 100 for predicting vehicle occupant injuries after an event can include additional components that facilitate the operation of the System 100 for predicting vehicle occupant injuries after an event.

[0043] In Fig. Figure 3 is a system 300 comprising a system 100 for predicting injuries to vehicle occupants after an event, as described in at least one embodiment. The system 300 includes a vehicle 10 with a specific vehicle architecture, the system 100 for predicting injuries to vehicle occupants after an event, and a device 102 for first responders. In various embodiments, the system 300 includes a vehicle 10 with a specific vehicle architecture, the system 100 for predicting injuries to vehicle occupants after an event, and a device for the hospital. When the vehicle 10 is involved in an event, the vehicle 10 is configured to establish a communication channel with the system 100 for predicting injuries to vehicle occupants after an event and to transmit a vehicle event message 302 to the system 100 for predicting injuries to vehicle occupants after an event.A vehicle incident (also referred to as an incident) includes contact between one vehicle and another vehicle or contact between the vehicle and an object that may result in injury to one or more vehicle occupants.

[0044] Vehicle 10 is configured to transmit vehicle data 304 to system 100 for predicting injuries to vehicle occupants after a crash. Examples of vehicle data 304 include, but are not limited to, body type, vehicle model year, total delta velocity, principal force direction, delta velocities along a first and second axis, resulting impact delta velocity and direction, rollover data, and vehicle seat orientation. As referenced in Fig. As described in Figure 1, the vehicle 10 comprises a sensor system 28. In various embodiments, the vehicle 10 can transmit the vehicle data 304 acquired by the sensor system 38 to the system 100 for predicting injuries to the vehicle occupants after an accident.

[0045] Vehicle 10 is configured to transmit occupant data 306 to system 100 for predicting occupant injuries following an event. Vehicle 10 can have multiple actual occupants. Vehicle 10 is configured to transmit occupant data 306 associated with each actual occupant to system 100 for predicting occupant injuries following an event. Examples of occupant data 306 include, but are not limited to, the occupant's actual seating position, occupant's actual posture in relation to a seat and restraint system, occupant's actual seatbelt data, occupant's actual weight, occupant's actual height, occupant's actual frailty parameter, occupant's actual gender, occupant's actual movement, and occupant's actual position.In various embodiments, the vehicle 10 can transmit the occupant data 306 acquired by the sensor system 38 to the system 100 for predicting vehicle occupant injuries after an event. An example of an actual occupant position is a reclined position. The actual frailty of the occupant may depend on age and / or gender.

[0046] System 100 for predicting vehicle occupant injuries after an event is configured to receive vehicle event message 302 from vehicle 10. System 100 for predicting vehicle occupant injuries after an event comprises vehicle data module 204, occupant data module 206, vehicle event database 208, and injury prediction model 210. Vehicle data module 204 is configured to receive vehicle data 304 from vehicle 10. Occupant data module 206 is configured to receive occupant data 306 from vehicle 10.

[0047] The vehicle event database 208 is configured to store simulation-based vehicle event metadata. In at least one embodiment, the vehicle event database 208 is configured to store simulation-based vehicle event metadata associated with different vehicle architectures. Examples of simulation-based vehicle event metadata associated with a vehicle architecture include, but are not limited to, a variety of impact directions, vehicle event impulses, biometric occupant data, a variety of occupant seating positions within the vehicle architecture, restraint data, the probability of injury to body regions of actual occupants in vehicle 10, and the probability of overall injury to actual occupants in vehicle 10.In at least one embodiment, the vehicle event database contains actual vehicle event metadata associated with the vehicle architecture. The manner in which the simulation-based vehicle event metadata is generated is described below with reference to [reference to relevant document]. Fig. 4 described in more detail.

[0048] In at least one embodiment, the injury prediction model 210 is a statistical analysis model. In at least one embodiment, the injury prediction model 210 is a machine learning model. In at least one embodiment, the simulation-based vehicle event metadata is used to train the machine learning model. The injury prediction model 210 is configured to receive the vehicle data 304, which is received by the vehicle 10 via the vehicle data module 204, and the occupant data 306, which is received by the vehicle 10 via the occupant data module 206. In various embodiments, the injury prediction module 210 identifies the vehicle architecture of the vehicle 10 involved in the vehicle event based on the received vehicle data 304.The injury prediction model 210 is configured to retrieve the simulation-based vehicle event metadata associated with the identified vehicle architecture of vehicle 10 from the vehicle event database 208.

[0049] The injury prediction model 210 is configured to predict injuries to one or more body regions of individual actual occupants in vehicle 10 based on vehicle data, occupant data, and retrieved simulation-based vehicle event metadata associated with the vehicle architecture of vehicle 10 involved in the vehicle event. Examples of body regions include the head, neck, thorax, thigh, lower leg, and abdomen. In various embodiments, the injury prediction model 210 is configured to predict the total injury of individual actual occupants in vehicle 10 based on the vehicle data, occupant data, and retrieved simulation-based vehicle event metadata associated with the vehicle architecture of vehicle 10 involved in the vehicle event.

[0050] In at least one embodiment, the system 100 for predicting injuries to vehicle occupants after an event is configured to transmit the injury prediction 308 generated by the injury prediction model 210 to the first responder's device 102. In at least one embodiment, the system 100 for predicting injuries to vehicle occupants after an event is configured to transmit the injury prediction 308 generated by the injury prediction model 210 to a device in the hospital.

[0051] In at least one embodiment, the injury prediction 308 includes the prediction of injuries in one or more body regions of each actual occupant of the vehicle 10. In at least one embodiment, the injury prediction 308 includes the prediction of total injuries of individual actual occupants of the vehicle 10. In at least one embodiment, the injury prediction 308 includes the prediction of injuries in one or more body regions of each actual occupant of the vehicle 10 and the prediction of total injuries of each actual occupant of the vehicle 10. In at least one embodiment, receiving the injury prediction 308 enables first responders to efficiently identify and treat the injuries of the actual occupants of the vehicle 10.In at least one embodiment, receiving the injury prognosis 308 enables hospital staff to efficiently identify and treat the injuries of the actual occupants of the vehicle 10.

[0052] Fig. Figure 4 shows a flowchart representation of an exemplary method 400 for generating simulation-based vehicle event metadata for storage in the vehicle event database 208 in accordance with at least one embodiment. Vehicle event simulations are performed using vehicle simulation models and simulated occupants for different vehicle architectures to generate the simulation-based vehicle event metadata for the different vehicle architectures for storage in the vehicle event database 208. As can be seen from the description, the sequence of steps within method 400 is not limited to those shown in Figure 4. Fig. The sequential execution shown in step 4 is limited, but can be carried out in one or more varying sequence(s), depending on applicability and in accordance with the present description.

[0053] In section 402, the vehicle event impulses for a vehicle architecture are determined. Different vehicle architectures have different vehicle event impulses. Examples of vehicle event impulses are vehicle acceleration impulses and vehicle speed event impulses. Examples of vehicle architectures include electric vehicle sedans, internal combustion engine sedans, EV pickups, ICG pickups, EV sport utility vehicles (SUVs), and ICG SUVs. Other examples of vehicle architectures include traditional and non-traditional vehicle seat layouts and orientations.

[0054] In Fig. 5A and Fig. Figure 5B shows graphical representations of exemplary vehicle event impulses 500A, 500B in accordance with at least one embodiment. Fig. Figure 5A shows a graphical representation of an example of an acceleration vehicle event pulse 500A for a specific vehicle architecture. Figure B shows a graphical representation of an example of a velocity vehicle event pulse 500B for the specific vehicle architecture.

[0055] Back to Fig. 4: In section 404, the determined vehicle event pulses 500A, 500B for the specific vehicle architecture are applied to a vehicle simulation model of this vehicle architecture. Different vehicle architectures have different vehicle simulation models. In at least one embodiment, the vehicle event pulses 500A, 500B applied to the vehicle simulation model of the specific vehicle architecture are acceleration vehicle event pulses 500A. In at least one embodiment, the vehicle event pulses applied to the vehicle simulation model of the specific vehicle architecture are velocity vehicle event pulses 500B.

[0056] Vehicle event pulses 500A and 500B are applied to the vehicle simulation model under a variety of different vehicle event conditions. Examples of these conditions include multiple impact speeds, impact directions, seat configurations and orientations, occupant seating positions, occupant vulnerabilities, occupant postures, and occupant biometric data. Occupant vulnerabilities include those of infants and the elderly. An example of an occupant posture is a reclined position.

[0057] In Fig. Figure 6 shows an exemplary vehicle simulation model 600 in accordance with at least one embodiment. The vehicle simulation model 600 contains two simulated occupants. The vehicle event pulses 500A, 500B are applied to the vehicle simulation model under a variety of different vehicle event conditions.

[0058] Back to Fig. 4: At 406, injury data associated with different body regions of the simulated occupants inside the vehicle simulation vehicle 600 are collected under a variety of different vehicle event conditions. Examples of body regions include the head, neck, thorax, thigh, lower leg, and abdomen.

[0059] In Fig. 7A and Fig. Figure 7B shows graphical representations of exemplary injury data 700A, 700B in accordance with at least one embodiment. Fig. Figure 7A shows a graphical representation of an example of the head acceleration of a simulated occupant as a function of time 700A. The head acceleration as a function of time 700A is an example of the collected injury data related to the head region. Fig. Figure 7B shows a graphical representation of an example of chest compression as a function of time 700B. Chest compression as a function of time 700B is an example of the collected injury data related to the thoracic region.

[0060] Back to Fig. 4: In 408, the probability of injury for each body region of the actual occupants of a vehicle 10 with the specific vehicle architecture is predicted based on the collected injury data using an injury prediction model 210. Examples of injury prediction models include statistical analysis models and machine learning models. In 410, the probability of injury for each body region is adjusted in accordance with an occupant frailty parameter. Occupant frailty parameters can increase the probability of injury for various body regions of the occupant. Examples of occupant frailty parameters include elderly people, young children, and sick occupants. In various embodiments, the occupant frailty parameters can be based on the occupant's age and / or sex.In at least one embodiment, the resident's frailty parameters can be generated by artificial intelligence (AI).

[0061] In 412, the probability of total injury to the actual occupants of a vehicle 10 with the specific architecture is predicted based on the collected injury data using the injury prediction model 210. In 414, the probability of total injury is adjusted in accordance with a frailty parameter. In various embodiments, the frailty parameters of the occupants can be based on the age and / or gender of an occupant. In at least one embodiment, the occupant frailty parameters can be generated by artificial intelligence (AI). In various embodiments, the simulation-based vehicle event metadata is supplemented with actual event data associated with vehicles 10 with the specific architecture.The vehicle event database 208 contains actual vehicle event metadata associated with the specific vehicle architecture.

[0062] The vehicle event database 208 is configured to store simulation-based vehicle event metadata associated with the specific vehicle architecture. Examples of simulation-based vehicle event metadata include, but are not limited to, multiple impact directions, vehicle event impulses, biometric occupant data, multiple occupant locations within the vehicle architecture, restraint data, the probability of injury to body regions of actual occupants in vehicle 10, and an overall probability of injury for actual occupants in vehicle 10.

[0063] In Fig. Figure 8 is a flowchart of a method 800 for predicting injuries to vehicle occupants after an event according to at least one embodiment. The method 800 is implemented by an embodiment of the system 100 for predicting injuries to vehicle occupants after an event. As can be seen from the description, the sequence of the method 800 is not limited to the one shown in Figure 8. Fig. The sequential execution shown in step 8 is limited, but can be carried out in one or more varying sequence(s), depending on applicability and in accordance with the present description.

Claims

[1] System (100) for predicting injuries to vehicle occupants after an event that exhibits the following: a vehicle event database (208) that contains simulation-based vehicle event metadata associated with a vehicle architecture, wherein the simulation-based generation of vehicle event metadata is based at least partially on the following factors: Determining vehicle event pulses (500A, 500B) for the vehicle architecture; Applying the vehicle event impulses (500A, 500B) to a vehicle simulation model (600) of the vehicle architecture; Collecting injury data (700A, 700B) associated with body regions of a simulated occupant within the vehicle simulation model (600), resulting from the application of the vehicle event impulses (500A, 500B) to the vehicle simulation model (600); and Predictions of the probability of injury for each of the body regions of an actual occupant of a vehicle (10) using the vehicle architecture based on the injury data (700A, 700B); at least one processor (44) that is communicatively connected to the vehicle event database (208); and at least one memory (32) that is communicatively coupled to the at least one processor (44), wherein the at least one memory (32) contains instructions which, when executed by the at least one processor (44), cause the at least one processor (44) to: Receiving a vehicle event message from the vehicle (10) with the vehicle architecture; Receiving vehicle data associated with the vehicle (10) and occupant data associated with the actual occupant of the vehicle (10); Retrieving simulation-based vehicle event metadata associated with the vehicle architecture from the vehicle event database (208); and Prediction of an injury in a first body region of the actual occupant's body regions based on vehicle data, occupant data and simulation-based vehicle event metadata using an injury prediction model (210). [2] System (100) according to claim 1, wherein the at least one memory (32) has further instructions which, when executed by the at least one processor (44), cause it to transmit the predicted injury of the first body regions of the actual occupant to a first responder device and / or a hospital device. [3] System (100) according to claim 1, wherein the vehicle event impulses (500A, 500B) are applied to the vehicle simulation model (600) under a plurality of vehicle event conditions, which include a plurality of impact vehicle speeds, a plurality of impact directions, a plurality of vehicle seat orientations, a plurality of occupant seating positions, a plurality of occupant vulnerabilities, a plurality of occupant postures and biometric occupant data. [4] System (100) according to claim 1, wherein the body regions comprise a head region, a neck region, a thoracic region, a thigh region, a lower leg region and an abdominal region. [5] System (100) according to claim 1, wherein the predicted probability of injury for each of the body regions of the simulated occupant is adapted in accordance with a parameter for the frailty of the occupant. [6] System (100) according to claim 1, wherein the injury prediction model (210) comprises either a statistical analysis model or a machine learning model. [7] System (100) according to claim 1, wherein the simulation-based vehicle event metadata includes a plurality of impact directions, the vehicle event impulses (500A, 500B), biometric occupant data, a plurality of occupant seating positions, restraint data, the probability of injury for each of the body regions and a probability of overall injury. [8] System (100) according to claim 1, wherein the vehicle data includes a body type, a vehicle model year, a total delta velocity, a principal force direction, delta velocities along a first and a second axis, a resulting impact delta velocity and delta direction, rollover data and the vehicle seat orientation. [9] System (100) according to claim 1, wherein the occupant data includes an actual seating position of the occupant, an actual posture of the occupant in relation to a seat and a restraint system, actual belt data of the occupant, an actual weight of the occupant, an actual size of the occupant, an actual frailty parameter of the occupant, an actual gender of the occupant, an actual movement of the occupant and an actual position of the occupant. [10] Method (800) for predicting injuries to vehicle occupants after an event which has the following characteristics: Providing a vehicle event database (208) that includes simulation-based vehicle event metadata associated with a vehicle architecture, wherein the simulation-based generation of vehicle event metadata is based at least partially on the following factors: Determining vehicle event pulses (500A, 500B) for the vehicle architecture; Applying the vehicle event impulses (500A, 500B) to a vehicle simulation model (600) of the vehicle architecture; Collecting injury data (700A, 700B) associated with body regions of a simulated occupant within the vehicle simulation model (600), resulting from the application of the vehicle event impulses (500A, 500B) to the vehicle simulation model (600); and Predictions of the probability of injury for each of the body regions of an actual occupant of a vehicle (10) using the vehicle architecture based on the injury data (700A, 700B); Receiving a vehicle event message from a vehicle (10) with the vehicle architecture; Receiving vehicle data associated with the vehicle (10) and occupant data associated with the actual occupant of the vehicle (10); Retrieving simulation-based vehicle event metadata associated with the vehicle architecture from the vehicle event database (208); and Prediction of an injury to a first body region of the body regions of the actual occupant based on vehicle data, occupant data and simulation-based vehicle event metadata using an injury prediction model (210).

Images