Method for responding to vehicle collision risk, and electronic device, medium, product, and vehicle

Abstract

A method for responding to a vehicle collision risk. The method comprises: when it is determined that a vehicle is about to collide with a target object, on the basis of vehicle motion state information of the vehicle and object motion state information of the target object, determining a target position on the vehicle, wherein a degree of vehicle damage corresponding to the target position is not higher than a degree of vehicle damage corresponding to any other candidate collision position; and adjusting a traveling path of the vehicle, such that the vehicle collides with the target object at the target position. The present disclosure further relates to an electronic device, a non-transitory computer-readable storage medium, a computer program product, and a vehicle.

Description

Methods for mitigating vehicle collision risks, electronic devices, media, products, and vehicles. Cross-reference to related applications

[0001] This application claims priority to Chinese patent application No. 202510362544.0, filed on March 26, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to, but is not limited to, the field of vehicles, and particularly to a method for dealing with vehicle collision risks, electronic devices, computer-readable storage media, computer program products, and vehicles. Background Technology

[0003] In the field of vehicle safety, active safety technologies aim to avoid collisions or reduce the probability of accidents, such as automatic emergency braking, electronic stability control, and adaptive cruise control; while passive safety technologies focus on protecting occupants after a collision, such as airbags and collision energy-absorbing structures. In recent years, the coordinated optimization of active and passive safety has gradually become a major development direction in this field. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0005] This disclosure provides a method for addressing vehicle collision risks, an electronic device, a computer-readable storage medium, a computer program product, and a vehicle.

[0006] According to a first aspect of the present disclosure, a method for dealing with vehicle collision risk is provided, comprising: when it is determined that a vehicle is about to collide with a target object, determining a target position on the vehicle based on vehicle motion state information of the vehicle and object motion state information of the target object, wherein the degree of vehicle damage corresponding to the target position is not higher than the degree of vehicle damage corresponding to other candidate collision positions; and adjusting the driving path of the vehicle so that the vehicle collides with the target object at the target position.

[0007] According to a second aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein computer-executable instructions are stored on the non-transitory computer-readable storage medium, and when the computer-executable instructions are executed by at least one processor, the method described in the first aspect is implemented.

[0008] According to a third aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by at least one processor, implements the method described in the first aspect.

[0009] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and at least one memory communicatively connected to the at least one processor, wherein the at least one memory stores computer-executable instructions, and the at least one processor is configured to read the computer-executable instructions from the at least one memory and execute the computer-executable instructions to implement the method of the first aspect.

[0010] According to a fifth aspect of the present disclosure, a vehicle is provided, comprising: a non-transitory computer-readable storage medium as described in the second aspect above; or a computer program product as described in the third aspect above; or an electronic device as described in the fourth aspect above; or at least one processor configured to implement the method of the first aspect.

[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Other aspects will become clear after reading and understanding the accompanying drawings and detailed description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of this disclosure, the accompanying drawings used in the description of the embodiments or optional implementations will be briefly introduced below. The drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0013] Figure 1 is a flowchart illustrating a method for dealing with vehicle collision risks according to an embodiment of the present disclosure.

[0014] Figure 2 is a schematic diagram of a safety collision model according to an embodiment of the present disclosure.

[0015] Figure 3 is a schematic diagram illustrating various collision scenarios according to embodiments of the present disclosure.

[0016] Figure 4 is a schematic diagram of the architecture of a vehicle collision risk response system according to an embodiment of the present disclosure.

[0017] Figure 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

[0018] Figure 6 is a block diagram illustrating a vehicle collision risk mitigation device according to an embodiment of the present disclosure. Detailed Implementation

[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same reference numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure.

[0020] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any item or all possible combinations of one or more of the associated listed items.

[0021] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0022] In the field of vehicle safety, active safety technologies aim to avoid collisions or reduce the probability of accidents, such as automatic emergency braking, electronic stability control, and adaptive cruise control; while passive safety technologies focus on protecting occupants after a collision, such as airbags and collision energy-absorbing structures. In recent years, the coordinated optimization of active and passive safety has gradually become a major development direction in this field. For example, by using predictive information from active safety systems to adjust seat belt pretensioning or airbag triggering logic in advance, the response efficiency of passive safety devices can be improved. However, active safety systems are still at a macro level, such as "predicting whether a collision will occur" or "selecting the approximate direction of a collision," without further considering the specific extent of vehicle damage at the time of a collision to determine a safer response method.

[0023] In view of this, embodiments of the present disclosure provide a method for dealing with vehicle collision risks, an electronic device, a computer-readable storage medium, a computer program product, and a vehicle.

[0024] The following describes in detail, with reference to the accompanying drawings, embodiments of the vehicle collision risk mitigation methods, electronic devices, computer-readable storage media, computer program products, and vehicles disclosed herein.

[0025] Figure 1 is a flowchart illustrating a method for addressing vehicle collision risk according to an exemplary embodiment of the present disclosure. The method includes steps 102 and 104.

[0026] In step 102, when it is determined that a collision is about to occur between the vehicle and the target object, the target position on the vehicle is determined based on the vehicle motion state information of the vehicle and the object motion state information of the target object. The degree of vehicle damage corresponding to the target position is not higher than the degree of vehicle damage corresponding to other candidate collision positions.

[0027] When a vehicle detects an impending collision with a target object, the collision is deemed an unavoidable risk for that vehicle. At this point, by acquiring real-time motion information of both the vehicle and the target object, a collision point with a damage level no higher than other collision locations can be identified as the target location. In other words, this target location must satisfy the condition that the corresponding vehicle damage level is less than or equal to the vehicle damage levels corresponding to other candidate collision locations, thus achieving proactive optimization of the collision location selection. The aforementioned vehicle and object motion information can include at least one of position, velocity, acceleration, and heading angle, and this information can be detected and acquired by corresponding onboard sensors within the vehicle. This acquisition operation actually begins during the process of determining whether a collision between the vehicle and the target object is imminent.

[0028] Below, this application will provide a quantitative criterion for determining whether the aforementioned vehicle and the aforementioned target object are about to collide.

[0029] In one embodiment, the Domain Control Unit (DCU) or autonomous driving domain controller in the vehicle can acquire first motion state information of the vehicle, second motion state information of candidate objects around the vehicle, and road environment information based on the vehicle's onboard sensors. Simultaneously, based on the first motion state information, second motion state information, and road environment information, the collision probability between the vehicle and the candidate objects is determined. If the collision probability reaches a preset probability threshold, the candidate object is designated as the target object, and a collision between the vehicle and the target object is determined to occur. In this embodiment, the onboard sensors may include devices such as millimeter-wave radar, cameras, lidar, and inertial measurement units. The first motion state information collected by the onboard sensors may include information such as the vehicle's speed, acceleration, yaw rate, and heading angle. The second motion state information may include information such as the real-time position, speed, direction of motion, and size characteristics of the corresponding candidate objects around the vehicle. Furthermore, the road environment information may include information such as lane line distribution, curvature (e.g., the curvature of the current road centerline or the curvature of the route the vehicle will travel), shoulder boundaries, traffic sign positions, and road surface friction coefficient.

[0030] After obtaining the vehicle's first motion state information, the candidate object's second motion state information, and the road environment information, at least one drivable path can be generated based on the road environment information. This drivable path covers the set of trajectories that the vehicle can reach in its current motion state through braking, steering, or acceleration. For example, among the at least one drivable path, there is a conservative path representing maintaining the current lane and decelerating, and an aggressive path representing performing lane changes to avoid an obstacle. Simultaneously, the candidate object's trajectory within a preset time period can be predicted based on the first and second motion state information to identify spatial overlap points between the at least one drivable path and the candidate object's trajectory within the preset time period. Based on the number and temporal distribution characteristics of these spatial overlap points, the collision probability can be calculated.

[0031] Specifically, using the first and second motion state information, at least one safe path conforming to the vehicle's motion capabilities can be generated through kinematic models or machine learning trajectory prediction algorithms. The trajectory of each candidate object within a preset time period (e.g., the next 2 to 5 seconds) can be predicted, and key spatiotemporal nodes on the trajectory can be marked. Simultaneously, spatiotemporal conflict detection can be performed on each drivable vehicle path and the predicted trajectory of each candidate object. This can be achieved by calculating the intersection point of the corresponding drivable vehicle path and the object's trajectory using geometric projection, and determining whether the intersection point is a spatial overlap point by judging whether the following conditions are met simultaneously: 1. Time synchronization condition: the time difference between the vehicle's arrival at the path overlap point and the candidate object's arrival at the trajectory overlap point is less than a preset threshold, such as ±0.3 seconds; 2. Spatial overlap condition: there is physical overlap between the areas occupied by the vehicle and the candidate object at the overlap point. In determining whether there is physical overlap between the areas occupied by the vehicle and the candidate object at the overlap point, the outer contour dimensions of the vehicle and the candidate object can be provided. A collision box model can be established based on these dimensions to detect physical overlap. This specification does not impose any limitations on this. Finally, based on the number of spatial overlap points corresponding to each vehicle's drivable path and their temporal distribution characteristics, or combined with the weights of each candidate object, the collision probability value between the vehicle and each candidate object can be calculated. For example, the more overlap points and the closer the time window is to the current moment, the higher the collision probability. The above probability values ​​can be mapped to the range of 0 to 100% using a normalization algorithm, so that when the probability value of a candidate object exceeds a preset threshold, it is determined to be the target object that needs to be optimized for collision.

[0032] In addition to the methods mentioned above, a time-varying vehicle safety path corridor can also be established using the dynamic safety corridor method. The spatiotemporal intersection area of ​​the corridor with the probability trajectory clusters of the candidate objects can be calculated, and the collision risk can be quantified based on the spatiotemporal density of the intersection area. Alternatively, the future spatiotemporal space can be discretized into a three-dimensional probability grid using the probabilistic grid mapping method. A collision probability heatmap can be generated by superimposing the joint probability density of the conflict grid cells to perform spatiotemporal conflict detection. This specification does not impose any restrictions on this method.

[0033] The following examples, using Figure 3 as an example, enumerate scenarios with a high average collision probability. When these scenarios are identified, the vehicle can begin to predict whether a collision with a target object is imminent. As shown in Figure 3, assuming the target object is a vehicle, common collision scenarios include, but are not limited to: (a) The vehicle (hereinafter referred to as vehicle A in the figure) collides with another vehicle (hereinafter referred to as vehicle B in the figure) while changing lanes. During lane changes, the vehicle is susceptible to blind spot interference or misjudgment. If the dynamics of other vehicles in adjacent lanes are not accurately monitored, a side collision is likely to occur if the following vehicle accelerates and the following distance is insufficient; (b) The vehicle collides with another vehicle while on a curve. Due to limited visibility on curves, the vehicle may experience path conflicts due to understeer / oversteer or failure to detect the trajectory of oncoming / same-direction vehicles in time; (c) (d) When a vehicle collides with a guardrail on a curve, if the curve radius is too small or the speed is too high, the vehicle may deviate from the lane and scrape against the guardrail if it does not adjust the steering angle or brake in advance; (e) When a vehicle collides with another vehicle crossing at an intersection, if the vehicle does not anticipate the other vehicle's movement intention through V2X, cameras, or other means when the other vehicle cuts in laterally, a right-angle collision is likely to occur; (f) When a vehicle is in an oncoming traffic situation in urban conditions, if the vehicle and the other vehicle are both in a narrow road or mixed traffic scenario, and the other vehicle's crossing behavior is not recognized in real time, a head-on collision may occur due to insufficient avoidance space.

[0034] As mentioned earlier, there can actually be multiple candidate objects. When the DCU or the autonomous driving domain controller detects vulnerable road users (VRUs) such as pedestrians, cyclists, and electric scooter users among these candidate objects, a targeted protection priority strategy can be designed. This involves obtaining type identification information of the candidate objects through onboard vision sensors or V2X (Vehicle to Everything) communication, such as pedestrian contour recognition and non-motorized vehicle feature classification. If a candidate object is identified as a vulnerable road user, it is removed from the candidate object list, retaining only non-vulnerable objects such as vehicles and fixed obstacles as candidate targets. This process is implemented through a preset weighting algorithm. For example, if the candidate objects include pedestrians and other vehicles, even if the probability of a pedestrian collision is higher than that of a vehicle, the system will still prioritize excluding pedestrians as target objects and instead optimize the collision point with non-vulnerable objects, thereby minimizing the risk of harm to vulnerable groups when a collision cannot be avoided. After the removal operation, the system recalculates the collision probability of the remaining candidate objects and selects the one that causes the least damage to the vehicle from the updated list of candidates as the target object, then performs subsequent collision location decisions and path adjustments. This mechanism ensures that in complex ethical dilemma scenarios, the system's decisions comply with traffic safety ethics and social responsibility requirements.

[0035] At this point, the impending collision between the aforementioned vehicle and the target object has been determined. The solution described in this specification can then efficiently determine the target's position on the vehicle based on a pre-defined safety collision model.

[0036] In one embodiment, the target location is determined based on a safety collision model, vehicle motion state information, and object motion state information. This safety collision model can characterize the relationship between the damage level of each collision area and collision parameters under different collision angles and positions. Specifically, the safety collision model can be constructed based on finite element analysis of the vehicle structure, historical collision test data, and dynamic damage simulation data, thereby providing a parameterized mapping relationship to quantitatively correlate collision parameters (e.g., collision angle, relative speed, and contact area) with the damage level of each area of ​​the vehicle (e.g., passenger compartment intrusion, stress threshold of key components, deformation efficiency of energy-absorbing structures). In the actual determination of the target location, the DCU, the autonomous driving domain controller, or other independent computing modules can first calculate the expected collision parameters at the time of the collision using kinematic equations based on the real-time vehicle motion state information and the object motion state information of the target object. These expected collision parameters may include parameters such as the collision angle deviation and the direction of the contact surface normal vector. Subsequently, these expected collision parameters are input into the safety collision model for damage simulation calculation.

[0037] At this point, the collision location can be traversed across multiple predefined candidate collision areas on the vehicle surface. This collision location can be determined using the center point of the area or other custom points, such as the front energy absorption areas A1 to A3, the side impact beam coverage areas B1 to B6, and the rear crumple zones C1 to C3 shown in Figure 2. The safety collision model dynamically evaluates the damage level of each area under the expected collision parameters, ultimately selecting the area with the lowest damage level as the target location. Furthermore, the aforementioned safety collision model can also have an online update function, adjusting relevant model parameters based on real-time data acquired by onboard sensors, such as changes in vehicle load and battery position, ensuring that the optimized collision location accurately matches the current physical state of the vehicle.

[0038] Of course, if the target object itself, like the vehicle mentioned above, belongs to a conventional vehicle type such as a sedan, sport utility vehicle (SUV), or multi-purpose vehicle (MPV), or a special vehicle type such as a bus or truck, then the model corresponding to the target object can be incorporated into the assessment of the vehicle's damage level, and even additional attention can be paid to the damage level of the target object. For example, when the target object is an SUV, the vehicle can call upon a pre-stored SUV collision characteristic database, which includes parameters such as chassis height, front bumper beam position, and mass distribution, and then combine it with the vehicle's safety collision model for a two-way damage assessment; or, when the target object is a van, after identifying its high-rigidity rear cargo box characteristics, the reinforced B-pillar structure in the vehicle's side collision area can be prioritized as the target location. By actively guiding the collision point to avoid direct impact with the truck's rear bumper, the collision energy can be dispersed to the non-lethal structural areas of both vehicles by utilizing the misaligned contact between the truck's cargo box side panel and the vehicle's B-pillar, thus achieving two-way optimization of occupant protection for both vehicles.

[0039] In some embodiments of this disclosure, during the process of determining the target location, the existing target locations can be further filtered in combination with the situation of the occupants in the vehicle, so as to minimize the impact on the occupants from the target location and ensure the personal safety of the occupants.

[0040] In one embodiment, occupant distribution information can be generated based on the vehicle's onboard sensors, and a candidate target location set can be determined based on this information. Subsequent processes can proceed as described above, determining the target location on the vehicle from the candidate target location set based on the vehicle's motion state information and the target object's motion state information. In this embodiment, the onboard sensors may include devices such as seat pressure sensors, in-cabin camera arrays, and infrared thermal imaging modules to collect occupant distribution information, which may include the precise seat coordinates, seating height, and seatbelt restraint status of the driver and passengers. Based on this, a three-dimensional mapping model of the occupant safety protection zone can be established. Then, based on the vehicle's structural topology data, spatial correlation analysis is performed between each collision area on the vehicle's outer surface and its corresponding location inside the vehicle to generate a candidate target location set. This set is used to exclude all external collision areas that directly overlap with the occupant's location within the vehicle. For example, if there is a passenger on the right rear seat, the right rear side panel area is excluded, ensuring that the internal projection area corresponding to each target location in the candidate target location set is more than a preset safe distance threshold from the nearest occupant. Therefore, the situation where the distance between the internal projection area of ​​any of the above target locations and the nearest occupant represented by the occupant distribution information exceeds a preset safe distance threshold can also be referred to as the occupant distribution information not matching any of the above target locations. Thus, it can be concluded that the occupant distribution information does not match any of the above target locations in the target location set.

[0041] Those skilled in the art will understand that when all seats in the vehicle are found to be occupied, the exclusion rule based on a single occupant's position can be cancelled. Instead, the comprehensive occupant injury index corresponding to each collision area can be calculated using the aforementioned safety collision model. This includes, for example, the weighted sum of the Head Injury Criterion (HIC) value, chest compression, and peak leg force. Finally, a priority list of candidate positions arranged in ascending order of injury index can be generated. Alternatively, areas with the highest vehicle structural crashworthiness scores, such as the connection between the front longitudinal beam and the chassis, can be prioritized. Even if the associated occupant injury index is not the lowest, active safety linkage can be achieved through actions such as early triggering of the corresponding side airbag inflation or locking of the power seat to compensate for the corresponding protection effect.

[0042] In step 104, the vehicle's driving path is adjusted so that the vehicle collides with the target object at the target location.

[0043] Based on the target location determined in the previous step, a path adjustment command can be generated by the vehicle control system, thereby shifting the vehicle's actual trajectory toward the target location. In this embodiment, the path adjustment operation can be achieved through the coordinated action of vehicle actuators, such as electronic stability program, electric power steering system, drive motor, and other components, ensuring that the vehicle is guided to the target location and contacts the target object before a collision occurs. This allows the vehicle to absorb collision energy using its optimal crashworthiness area, directly reducing vehicle structural damage and occupant safety risks.

[0044] Specifically, the process of adjusting the driving path of the above-mentioned vehicles in this instruction manual can be further broken down.

[0045] In one embodiment, the adjusted path parameters of the vehicle are first determined based on the target location; then, a path adjustment command based on braking, steering, and driving dimensions is generated based on the adjusted path parameters, and the path adjustment command is executed to adjust the driving path. In this embodiment, the adjusted path parameters can be calculated in real time using a vehicle dynamics model, and may include specific values ​​such as target lateral offset, longitudinal velocity change rate, heading angle correction value, and path curvature constraints. These parameters can meet the vehicle's kinematic feasibility and current actual road environment constraints, such as a maximum lateral acceleration not exceeding 0.5g (g represents gravitational acceleration (approximately 9.8 m / s²)) and not crossing solid lane lines or shoulders. The aforementioned path adjustment command based on braking, steering, and driving dimensions can be understood as a multi-dimensional path adjustment command, that is, different commands are proposed for the vehicle's braking system, steering system, and driving system respectively, to ensure that the vehicle can adjust its driving path according to the expected requirements of the path adjustment command, thereby reducing the possibility of accidental collision with the target object.

[0046] Furthermore, as mentioned earlier, "the vehicle is about to collide with the target object" is only a result for the vehicle at a certain moment, but it does not mean that a collision between the vehicle and the target object is inevitable. Therefore, while adjusting the vehicle's driving path, it is possible to periodically determine whether a collision between the vehicle and the target object is imminent. That is, the motion state information of the vehicle and the target object is re-collected at preset intervals, and the latest collision probability between the vehicle and the target object is recalculated based on the updated data. When the recalculated collision probability is detected to be lower than a preset probability threshold, it is determined that the vehicle and the target object are no longer in an unavoidable collision state. At this time, the collision with the target object at the target location can be immediately terminated, and the vehicle's driving path can be adjusted to actively avoid the target object, minimizing the vehicle's risk to the greatest extent. Of course, if the determination result is still that the vehicle and the target object are about to collide, the vehicle can continue to maintain the previously adjusted driving path.

[0047] It's worth noting that the occupant distribution information mentioned earlier can also be used to assist in decision-making regarding the aforementioned driving path. For example, when the occupant distribution information indicates that there is only an occupant in the driver's seat, if there is insufficient space to avoid an oncoming vehicle or a rear-end collision with a truck, the vehicle can make a slight leftward adjustment using electric power steering to guide the point of impact to the passenger side or the right rear door area, and trigger the electronic stability program to assist braking and vehicle rotation, reducing the impact on the driver's side. If encountering a lateral vehicle, such as a right-angle collision at an intersection, the vehicle can use instantaneous acceleration to move the point of impact to the rear crumple zone, reducing the force on the passenger compartment. When there are occupants in both the driver and front passenger seats, the vehicle can eliminate the side panel areas based on the real-time occupant distribution, and control the vehicle's rotation through coordinated steering and braking to lock the point of impact in the rear door or the rear energy-absorbing area, and trigger the side airbags to inflate in advance. Furthermore, when the vehicle is fully loaded, priority is given to collisions at locations corresponding to collision pillars such as the A-pillar and B-pillar, while simultaneously triggering the linkage of all airbags and the seat retraction and locking functions. If road conditions restrict path adjustments, the system will forcibly lock the areas with the highest impact resistance, such as the connection between the front longitudinal beam and the chassis. Then, the occupant injury index will be comprehensively assessed through the aforementioned safety collision model to ensure that energy is dispersed to the maximum extent and occupant safety is protected when a collision is unavoidable.

[0048] The following explanation of the vehicle collision risk mitigation methods, using the architecture diagram of the vehicle collision risk mitigation algorithm shown in Figure 4, will clarify the following regarding the various models and modules in Figure 4: The onboard sensor 402 can be deployed as an independent hardware device, including millimeter-wave radar, cameras, lidar, inertial measurement units, seat pressure sensors, in-cabin camera arrays, infrared thermal imaging modules, etc., directly on the vehicle to collect information on vehicle motion status, object motion status, and road environment. The driving path planning model 404, target location selection model 406, and driving path decision model 408 can be deployed on the DCU, autonomous driving domain controller, or onboard independent computing hardware with computing power, respectively, according to actual needs. As for the path adjustment module 410, it can be deployed on the Electronic Control Unit (ECU) corresponding to the vehicle's actuator equipment to implement its function and execute corresponding path adjustment commands.

[0049] Specifically, Figure 4 shows the architecture diagram of the vehicle collision risk response system. The core function of the on-board sensor 402 in Figure 4 is data collection. On the one hand, it can collect the vehicle's own first motion state information, the second motion state information of surrounding candidate objects, and road environment information, and provide them to the driving path planning model 404. The driving path planning model 404 generates a set of possible driving paths for the vehicle based on the acquired road environment information, makes a preliminary judgment on whether a collision with the target object is imminent, and provides path basis for the collision probability calculation module in the target location selection model 406 and the driving path decision model 408, respectively. As for the collision probability calculation module in the target location selection model 406, it can obtain the motion state information of the vehicle and candidate objects based on the information from the driving path planning model 404, and then calculate the collision probability between the two to determine the target object. The occupant distribution information generation module can use the information provided by the seat pressure sensor, cabin camera and other devices in the on-board sensor 402 to generate occupant distribution information in the vehicle, which is used to filter a set of safe candidate target locations to assist the safety collision model in determining the target location. The safety collision model, based on the target object determined by the collision probability calculation module and the candidate target position set generated by the occupant distribution information generation module, performs vehicle structure analysis and collision test data construction to characterize the relationship between collision angle, position, and vehicle damage degree. Using the vehicle and object motion state information input from the collision probability calculation module, it assesses the damage degree of each collision area, selects the target position with the lowest damage, and outputs it to the driving path decision model 408. The driving path decision model 408 can then select the target position determined by model 406 based on the target position, calculate the adjusted path parameters of the vehicle, generate path adjustment commands in braking, steering, and driving dimensions, and output the planned final driving path to the path adjustment module 410. Finally, the path adjustment module 410 executes the aforementioned path adjustment commands, that is, through the coordinated adjustment of the vehicle trajectory by actuators such as the electronic stability program and steering system, causing the vehicle to deviate towards the target position.

[0050] Figure 5 is a schematic structural diagram of an electronic device in an exemplary embodiment. Referring to Figure 5, at the hardware level, the electronic device includes a processor 502, an internal bus 510, a network interface 504, a memory 506, and a non-volatile memory 508, and may also include other necessary hardware. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a risk code detection device at the logical level. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0051] Figure 6 is a block diagram of a vehicle collision risk mitigation device according to an embodiment of this disclosure. Referring to Figure 6, this device can be applied to the equipment shown in Figure 5 to implement the technical solution described in this disclosure. The device includes a target position determination unit 602 and a driving path adjustment unit 604.

[0052] The target position determination unit 602 is configured to determine the target position on the vehicle based on the vehicle motion state information and the object motion state information of the target object when it is determined that a collision is about to occur between the vehicle and the target object, wherein the degree of vehicle damage corresponding to the target position is not higher than the degree of vehicle damage corresponding to other candidate collision positions.

[0053] The driving path adjustment unit 604 is configured to adjust the driving path of the vehicle so that the vehicle collides with the target object at the target location.

[0054] Optionally, the device may further include a collision probability processing unit.

[0055] The collision probability processing unit is configured to: acquire first motion state information of the vehicle, second motion state information of candidate objects around the vehicle, and road environment information based on the vehicle's on-board sensors; determine the collision probability between the vehicle and the candidate objects based on the first motion state information, the second motion state information, and the road environment information; and, if the collision probability reaches a preset probability threshold, designate the candidate objects as the target objects and determine that a collision between the vehicle and the target objects is imminent.

[0056] Optionally, the collision probability processing unit is specifically configured to: generate at least one drivable path for a vehicle based on the road environment information; predict the trajectory of the candidate object within a preset time period based on the first motion state information and the second motion state information, so as to identify the spatial overlap points between the at least one drivable path for a vehicle and the trajectory of the object within the preset time period; and calculate the collision probability based on the number and time distribution characteristics of the spatial overlap points.

[0057] Optionally, the device may also include a vulnerable group removal unit.

[0058] The vulnerable group removal unit is configured to remove the vulnerable road user group from the candidate group when there are multiple candidate groups and the vulnerable road user group exists among the multiple candidate groups.

[0059] Optionally, the target position determination unit 602 is specifically configured to: determine the target position based on a safety collision model, vehicle motion state information, and object motion state information. The safety collision model is used to characterize the correspondence between the damage degree of each collision area and the collision parameters under different collision angles and different collision positions of the vehicle.

[0060] Optionally, the target location determination unit 602 is specifically configured to: generate occupant distribution information of the occupants inside the vehicle based on the vehicle's on-board sensors; determine a set of candidate target locations based on the occupant distribution information, wherein the occupant distribution information does not match any target location in the target location set; and determine the target location on the vehicle from the set of candidate target locations based on the vehicle's motion state information and the target object's object motion state information.

[0061] Optionally, the device further includes a travel path readjustment unit.

[0062] The driving path readjustment unit is configured to periodically determine whether a collision between the vehicle and a target object is imminent when adjusting the driving path of the vehicle; if the determination result is that a collision between the vehicle and the target object is not imminent, the driving path of the vehicle is adjusted to avoid a collision between the vehicle and the target object.

[0063] Optionally, the driving path adjustment unit 604 is specifically configured to: determine the vehicle's adjusted path parameters based on the target position; generate path adjustment instructions for braking, turning, and driving dimensions based on the vehicle's adjusted path parameters; and execute the path adjustment instructions to adjust the driving path.

[0064] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0065] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the solution in this specification according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0066] Based on the same concept as the above methods, embodiments of this application also provide an electronic device, including: at least one processor; at least one memory, communicatively connected to the at least one processor, and storing computer-executable instructions; wherein the at least one processor is configured to read the computer-executable instructions from the at least one memory and execute the computer-executable instructions to implement the method as described in any of the above embodiments.

[0067] Based on the same concept as the above methods, this application also provides a non-transitory computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are executed by at least one processor, they implement the method described in any of the above embodiments.

[0068] Based on the same concept as the methods described above, this application also provides a computer program product, including a computer program / instructions that, when executed by at least one processor, implement the methods described in any of the above embodiments.

[0069] Based on the same concept as the above methods, embodiments of this application also provide a vehicle, including: the above-described electronic device; or a non-transitory computer-readable storage medium; or a computer program product; or at least one processor configured to implement the method as described in any of the above embodiments.

[0070] In this embodiment, when a vehicle is determined to be about to collide with a target object, it can proactively select a target location that minimizes vehicle damage and control the collision point by adjusting its driving path. Specifically, the target location can be determined based on the vehicle's motion state information and the target object's motion state information, ensuring that the degree of vehicle damage at this target location is no higher than that at other candidate collision locations. Simultaneously, the vehicle can adjust its driving path to ensure that it collides with the target object at the previously determined target location, guiding the impact force to the target location where the degree of vehicle damage is no higher than that at other candidate collision locations. This reduces the extent of vehicle damage and occupant injury, effectively improving the vehicle's safety when dealing with collision risks.

[0071] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0072] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0073] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0074] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0075] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any disclosure or the scope of the claims, but rather are primarily intended to describe the features of specific embodiments of particular disclosures. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation of a sub-combination.

[0076] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0077] Therefore, specific embodiments of the subject matter have been described. Furthermore, the processes depicted in the figures are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0078] The above description is merely an exemplary embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this specification should be included within the scope of protection of this specification.

Claims

1. A method for addressing vehicle collision risk, comprising: When it is determined that a collision is about to occur between a vehicle and a target object, the target position on the vehicle is determined based on the vehicle motion state information and the target object motion state information. The degree of vehicle damage corresponding to the target position is not higher than the degree of vehicle damage corresponding to other candidate collision positions. The vehicle's travel path is adjusted so that the vehicle collides with the target object at the target location.

2. The method according to claim 1, wherein, The determination that a collision between the vehicle and the target object is imminent includes: The vehicle's first motion state information, the second motion state information of candidate objects around the vehicle, and road environment information are obtained from the vehicle's onboard sensors. The collision probability between the vehicle and the candidate object is determined based on the first motion state information, the second motion state information, and the road environment information. When the collision probability reaches a preset probability threshold, the candidate object is selected as the target object, and it is determined that the vehicle and the target object are about to collide.

3. The method of claim 2, wherein, Determining the collision probability between the vehicle and the candidate object based on the first motion state information, the second motion state information, and the road environment information includes: At least one drivable path for a vehicle is generated based on the road environment information. Based on the first motion state information and the second motion state information, predict the motion trajectory of the candidate object within a preset time period, so as to identify the spatial overlap point between the at least one drivable vehicle path and the object motion trajectory within the preset time period; The collision probability is calculated based on the number and temporal distribution characteristics of the spatially overlapping points.

4. The method of claim 2, wherein, The number of candidate objects is multiple, and among the multiple candidate objects there is a vulnerable road user group. The method further includes: The vulnerable road user group is removed from the multiple candidate groups.

5. The method according to claim 1, wherein, Determining the target position on the vehicle based on the vehicle's motion state information and the target object's motion state information includes: The target position is determined based on the safety collision model, the vehicle motion state information, and the object motion state information. The safety collision model is configured to characterize the correspondence between the damage degree of each collision area of ​​the vehicle and the collision parameters under different collision angles and different collision positions.

6. The method according to claim 1, wherein, Determining the target position on the vehicle based on the vehicle's motion state information and the target object's motion state information includes: The vehicle's onboard sensors generate occupant distribution information within the vehicle. A set of candidate target locations is determined based on the occupant distribution information, wherein the occupant distribution information does not match any candidate target location in the set of candidate target locations; The target position on the vehicle is determined from the candidate target position set based on the vehicle motion state information and the target object motion state information.

7. The method according to claim 1, further comprising: While adjusting the vehicle's driving path, periodically determine whether the vehicle is about to collide with the target object; If the determination result indicates that the vehicle and the target object are not about to collide, the vehicle's driving path is adjusted to avoid a collision.

8. The method of claim 1, wherein, Adjusting the vehicle's driving path includes: Determine the adjusted path parameters of the vehicle based on the target location; Based on the adjusted path parameters of the vehicle, a path adjustment command based on braking, steering, and driving dimensions is generated, and the path adjustment command is executed to adjust the driving path.

9. An electronic device, comprising: At least one processor; At least one memory, communicatively connected to the at least one processor, the at least one memory storing computer-executable instructions. The at least one processor is configured to read the computer-executable instructions from the at least one memory and execute the computer-executable instructions to implement the method as described in any one of claims 1 to 8.

10. A non-transitory computer-readable storage medium, wherein, The non-transitory computer-readable storage medium stores computer-executable instructions that, when executed by at least one processor, implement the method as described in any one of claims 1 to 8.

11. A computer program product comprising a computer program that, when executed by at least one processor, implements the method as described in any one of claims 1 to 8.

12. A vehicle comprising: The electronic device as described in claim 9, or The non-transitory computer-readable storage medium as described in claim 10, or The computer program product as described in claim 11, or At least one processor, the at least one processor being configured to implement the method as described in any one of claims 1 to 8.

Images