Vehicle collision risk coping method, readable storage medium and program product

Abstract

The invention provides a vehicle collision risk coping method, a readable storage medium and a program product, and the method comprises the steps: determining a target position on a vehicle according to the vehicle motion state information of the vehicle and the object motion state information of the target object under the condition of determining that the vehicle is about to collide with the target object, the vehicle damage degree corresponding to the target position is not higher than the vehicle damage degrees corresponding to other collision positions; and adjusting a driving path of the vehicle to enable the vehicle to collide with the target object at the target position.

Description

Technical Field

[0001] The present invention relates to the automotive field, and in particular to a method for coping with vehicle collision risks, a readable storage medium and a program product. Background Art

[0002] In the field of automobile safety, active safety technology aims to avoid collisions or reduce the probability of accidents, such as automatic emergency braking, electronic stability control, adaptive cruise control, etc., while passive safety technology focuses on protecting occupants after a collision, such as airbags, collision energy absorption structures, etc. In recent years, the coordinated optimization of active and passive safety has gradually become a major development direction in this field. For example, the seat belt pre-tensioning or airbag triggering logic is adjusted in advance through the prediction information of the active safety system to improve the response efficiency of passive safety devices. However, the existing technology is still at the macro level of "predicting whether there will be a collision" or "selecting the general direction of the collision", and has not further considered the specific degree of vehicle damage when a collision occurs, and determined a safer response method based on this. Summary of the invention

[0003] In view of this, the present invention provides a method for dealing with vehicle collision risk, a readable storage medium and a program product to address the deficiencies in the related art.

[0004] Specifically, the present invention is achieved through the following technical solutions: According to a first aspect of the present invention, a method for dealing with vehicle collision risk is provided, the method comprising: In the case where it is determined that the vehicle and the target object are about to collide, determining a target position on the vehicle according to the vehicle motion state information of the vehicle and the object motion state information of the target object, wherein the vehicle damage degree corresponding to the target position is not higher than the vehicle damage degree corresponding to other collision positions; The driving path of the vehicle is adjusted so that the vehicle collides with the target object at the target position.

[0005] According to a second aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the steps of the method described in the first aspect.

[0006] According to a third aspect of the present invention, there is provided a mobile charging device, comprising a control module and an energy storage module, wherein the control module comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the method described in the first aspect are implemented when the processor executes the program through the cooperation between the control module and the energy storage module.

[0007] When the vehicle in this specification is determined to be about to collide with the target object, it can actively select the target position where the vehicle damage is the least, and control the collision point by adjusting the driving path. Specifically, the above-mentioned target position can be determined based on the vehicle motion state information of the vehicle and the object motion state information of the above-mentioned target object, and the vehicle damage degree corresponding to the target position is not higher than the vehicle damage degree corresponding to other collision positions. At the same time, the vehicle can adjust its own driving path so that the above-mentioned vehicle collides with the above-mentioned target object at the previously determined target position, and the collision impact force is guided to the target position where the vehicle damage degree is not higher than other collision positions, thereby reducing the degree of vehicle damage and the injuries to the occupants, and effectively improving the safety of the vehicle when dealing with collision risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 is a flow chart of a method for dealing with vehicle collision risk shown in an embodiment disclosed by the present invention; Figure 2 is a schematic diagram of a safety collision model shown in an embodiment disclosed in the present invention; Figure 3 is a schematic diagram of various collision scenarios shown in the disclosed embodiment of the present invention; Figure 4 It is a schematic diagram of the architecture of a system for coping with vehicle collision risks shown in an embodiment disclosed in the present invention; Figure 5 is a schematic structural diagram of an electronic device shown in an embodiment of the present invention; Figure 6 It is a block diagram of a device for coping with vehicle collision risk shown in an embodiment of the present invention. DETAILED DESCRIPTION

[0010] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are only examples of devices and methods consistent with some aspects of the present invention.

[0011] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0012] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0013] An embodiment of the method for coping with vehicle collision risk of the present invention is described in detail below with reference to the accompanying drawings.

[0014] Figure 1 This is a flow chart of a method for dealing with vehicle collision risk according to an exemplary embodiment disclosed in the present invention, which may specifically include the following steps: Step 202, when it is determined that the vehicle is about to collide with the target object, determine the target position on the vehicle based on the vehicle motion state information of the vehicle and the object motion state information of the target object, and the vehicle damage degree corresponding to the target position is not higher than the vehicle damage degree corresponding to other collision positions.

[0015] When a vehicle detects that it is about to collide with a target object, the above collision will be determined as an unavoidable risk for the vehicle at present. At this time, the vehicle's own motion state information and the target object's motion state information can be obtained in real time, and the collision contact point whose damage degree is not higher than other collision positions can be determined as the target position. In other words, the target position must satisfy that the corresponding vehicle damage degree is less than or equal to other candidate collision positions, thereby realizing active optimization selection of the collision position. Among them, the above vehicle motion state information and object motion state information can at least include any one of position, speed, acceleration, and heading angle, and the above vehicle motion state information and the above object motion state information can be detected and obtained by the corresponding on-board sensors in the vehicle. Of course, the acquisition operation actually starts in the process of determining whether the vehicle and the target object are about to collide.

[0016] The present application will provide a quantitative judgment standard for determining whether the above-mentioned vehicle and the above-mentioned target object are about to collide.

[0017] In one embodiment, a decision control unit (Domain Control Unit, DCU) or an autonomous driving domain controller in a vehicle may obtain the first motion state information of the vehicle, the second motion state information of the candidate object around the vehicle, and the road environment information according to the vehicle-mounted sensors of the vehicle, and determine the collision probability between the vehicle and the candidate object according to the first motion state information, the second motion state information, and the road environment information, and when the collision probability reaches a preset probability threshold, the candidate object is used as the target object, and it is determined that the vehicle and the target object are about to collide. The vehicle-mounted sensors may include devices such as millimeter wave radars, cameras, laser radars, and inertial measurement units, and the first motion state information collected by the vehicle-mounted sensors may include information such as the vehicle speed, acceleration, yaw rate, heading angle, etc., and the second motion state information may include information such as the real-time position, speed, motion direction, and size characteristics of the corresponding candidate object around the vehicle; in addition, the road environment information may include information such as lane line distribution, curvature, shoulder boundary, traffic sign position, and road friction coefficient.

[0018] After obtaining the first motion state information of the vehicle itself, the second motion state information of the candidate object and the road environment information, at least one drivable path for the vehicle can be generated based on the road environment information. The drivable path covers the set of driving trajectories that the vehicle can reach through braking, steering or acceleration operations in the current motion state. For example, there is a conservative path in the at least one drivable path for the vehicle to decelerate in the current lane, and there is also an aggressive path to perform lane change avoidance. At the same time, the object motion trajectory of the candidate object within a preset time period can be predicted based on the first motion state information and the second motion state information to identify the spatial overlap points between the at least one drivable path for the vehicle and the object motion trajectory within the preset time period, and the number and time distribution characteristics of the spatial overlap points, so as to calculate the collision probability.

[0019] Specifically, by using the first motion state information and the second motion state information, at least one safe path that meets the vehicle's motion capability can be generated through a kinematic model or a machine learning trajectory prediction algorithm, and the motion trajectory of each candidate object in a preset time, such as the object in the next 2 to 5 seconds, can be predicted, and the key spatiotemporal nodes on the trajectory can be marked. At the same time, each vehicle's drivable path and the predicted trajectory of each candidate object can be detected in time and space, that is, the intersection of the corresponding vehicle's drivable path and the object trajectory can be calculated by the geometric projection method, and it is determined whether the intersection satisfies the following conditions at the same time to determine it as a spatial overlap point: 1. Time synchronization condition, that is, the time difference between the time when the vehicle arrives at the path overlap point and the time when the candidate object arrives at the trajectory overlap point is less than a preset threshold, such as ±0.3 seconds; 2. Spatial overlap condition: There is a physical overlap between the vehicle and the candidate object in the occupied area of ​​the overlap point. This process can provide the outer dimensions of the vehicle and the object to establish a collision box model for detection, which is not limited in this statement. Finally, the collision probability values ​​between the vehicle and each candidate object can be calculated based on the number of spatial overlap points and their time distribution characteristics corresponding to the drivable paths of each vehicle, or dynamically adjusted in combination with the weights of each candidate object. For example, the more overlap points there are 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 0~100% range through a normalization algorithm, so that when the probability value of a candidate object exceeds the preset threshold, it is determined to be a target object that needs to be collision optimized.

[0020] In addition to the above method, the dynamic safety corridor method can also be used to establish a time-varying vehicle safety path corridor, and the time-space intersection area with the probability trajectory cluster of the alternative object is calculated, and then the collision risk is quantified according to the time-space density of the intersection area, or the future time and space are discretized into a three-dimensional probability grid through the probability grid mapping method, and the collision probability heat map is generated by superimposing the joint probability density of the conflict grid units to perform time-space conflict detection. This is not limited in this manual.

[0021] Combine the following Figure 3 The following are examples of scenarios with high average collision probabilities. The vehicle can start to determine in advance whether the vehicle and the target object are about to collide when the following scenarios are identified. Figure 3As shown, assuming that the target object is a vehicle, common collision scenarios include but are not limited to (a), the ego vehicle (hereinafter referred to as vehicle A in the figure) changes lanes and collides with another vehicle (hereinafter referred to as vehicle B in the figure). In the process of changing lanes, the ego vehicle is easily interfered by blind spots or misjudgments. If the dynamics of the vehicles in the adjacent lanes are not accurately monitored, once the rear vehicle accelerates and the distance between the vehicles is insufficient, a side collision is likely to occur; (b), the ego vehicle collides with another vehicle in a curve. In the curve, due to the limited field of view, the vehicle may understeer / oversteer or fail to detect the trajectory of the oncoming / same-direction vehicle in a timely manner, resulting in a path conflict; (c), the ego vehicle collides with the guardrail in a curve. In the curve, if the radius is too small or the speed is too high, the vehicle may deviate from the lane and collide with the guardrail if the steering angle or brakes are not adjusted in advance; (d), the ego vehicle collides with another vehicle crossing the intersection. In the case of a vehicle cutting in laterally, if the ego vehicle does not predict its movement intention through V2X, cameras, etc., a right-angle collision is likely to occur; (e) When the vehicle is approaching an oncoming vehicle in urban conditions, since the vehicles are on narrow roads or in mixed traffic scenarios, if the vehicle's crossing the line is not identified in real time, a head-on collision may occur due to insufficient avoidance space.

[0022] As mentioned above, the candidate objects can actually be multiple. Then, when the DCU or the autonomous driving domain controller detects that there are vulnerable road users (VRU) such as pedestrians, cyclists, and electric scooter users among the multiple candidate objects, a set of protection priority strategies can be designed specifically, that is, the type identification information of the candidate objects is obtained through the on-board visual sensor or V2X (Vehicle to Everything) communication, such as pedestrian contour recognition, non-motor vehicle feature classification, etc. If a candidate object is determined to be a vulnerable road user, it will be removed from the candidate object list, and only non-vulnerable objects such as vehicles and fixed obstacles will be retained as candidate targets. This process is achieved through a preset weight algorithm. For example, if the candidate objects include pedestrians and other vehicles, even if the probability of collision with pedestrians is higher than that with vehicles, the system still prioritizes pedestrians as target objects and instead chooses to optimize the collision point with non-vulnerable objects, thereby minimizing the risk of injury to vulnerable groups when collision cannot be avoided. After the removal operation, the system recalculates the collision probability of the remaining candidate objects, and can select the candidate object with the least damage to the vehicle as the target object based on the updated candidate list, and perform subsequent collision position decisions and path adjustments. This mechanism can ensure that in complex moral dilemma scenarios, system decisions comply with traffic safety ethics and social responsibility requirements.

[0023] At this point, the situation that the vehicle is about to collide with the target object has been determined. At this point, the solution in this specification can efficiently determine the target position on the vehicle based on the method of the preset safety collision model.

[0024] In one embodiment, the above-mentioned 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 can be used to characterize the corresponding relationship between the damage degree of each collision area and the collision parameters of the above-mentioned vehicle under different collision angles and different collision positions. Specifically, the safety collision model can be constructed based on the finite element analysis of the vehicle structure, historical collision test data and dynamic damage simulation data, and then provide a parameterized mapping relationship to establish collision parameters, which may include collision angle, relative speed and contact area, and quantitatively associate the damage degree of each area of ​​the vehicle such as the intrusion amount of the passenger compartment, the stress threshold of key components, and the deformation efficiency of the energy absorption structure. In the process of actually determining the target position, the above-mentioned DCU or the above-mentioned autonomous driving domain controller or other independent computing module can firstly calculate the expected collision parameters when the collision occurs through the kinematic equation according to the real-time vehicle motion state information of the vehicle and the object motion state information of the target object. The expected collision parameters may include parameters such as the collision angle deviation value and the contact surface normal vector direction, and then the above-mentioned expected collision parameters are input into the safety collision model for damage simulation calculation.

[0025] At this time, the collision positions in multiple candidate collision areas predefined on the vehicle surface can be traversed, and the collision position can be determined by the center point of the area or other custom points, such as Figure 2 The safety collision model is used to dynamically evaluate the damage degree of each area under the expected collision parameters, and finally select the area with the lowest damage degree as the target position. In addition, the above safety collision model can also have an online update function, so as to adjust the relevant model parameters according to the data obtained in real time by the on-board sensors such as vehicle load changes and battery position status, so as to ensure that the collision position optimization result accurately matches the current vehicle physical state.

[0026] Of course, if the target object itself is also a conventional model such as a sedan, a sport utility vehicle (SUV), a multi-purpose vehicle (MPV), or a special model such as a bus or a truck, the model corresponding to the target object can be included in the consideration of the damage degree of the vehicle, and even the damage degree of the target object can be paid extra attention to. For example, when the target object is an SUV model, the vehicle can call the pre-stored SUV collision characteristic database, which contains parameters such as chassis height, front anti-collision beam position, mass distribution, and then combine the vehicle safety collision model to perform 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 lateral collision area of ​​the vehicle can be preferentially selected as the target position, and the collision point can be actively guided to avoid direct collision with the rear bumper of the truck, and the dislocation contact between the side panel of the truck cargo box and the B-pillar of the vehicle can be used to disperse the collision energy to the non-lethal structural areas of both parties, thereby achieving two-way optimization of the protection of the occupants of both vehicles.

[0027] In the process of determining the above-mentioned target positions, this manual can also further screen the existing target positions in combination with the situation of the passengers in the vehicle, thereby avoiding the passengers in the vehicle from being impacted by the target positions to the greatest extent and ensuring the personal safety of the passengers in the vehicle.

[0028] In one embodiment, the occupant distribution information of the occupants in the vehicle can be generated according to the vehicle-mounted sensors of the above-mentioned vehicle, and the candidate target position set can be determined according to the occupant distribution information. The subsequent process can be as described above, and the target position on the above-mentioned vehicle can be determined from the above-mentioned candidate target position set according to the vehicle motion state information of the vehicle and the object motion state information of the target object. In this embodiment, the vehicle-mounted sensors can include seat pressure sensors, in-cabin camera arrays, infrared thermal imaging modules and other devices to collect occupant distribution information, which can include the precise seat coordinates, sitting heights and safety shoulder belt restraint states of the driver and passengers. On this basis, a three-dimensional mapping model of the occupant safety protection zone can be established. Then, based on the vehicle structure topology data, the collision areas on the outer surface of the vehicle are spatially correlated with the corresponding positions in the vehicle to generate a candidate target position set, which is used to exclude all external collision areas that have direct spatial projection overlaps with the position in the vehicle where the occupant is located. For example, if there is a passenger on the right side of the rear row, the right rear side panel area of ​​the vehicle is excluded, ensuring that the internal projection area corresponding to each target position in the candidate target position set is more than the preset safety distance threshold from the nearest occupant. Therefore, the situation where the internal projection area of ​​any of the above-mentioned target positions is more than a preset safety distance threshold from the nearest occupant represented by the occupant distribution information can be called a mismatch between the occupant distribution information and any of the above-mentioned target positions, and it can be concluded that the above-mentioned occupant distribution information does not match any of the target positions in the above-mentioned target position set.

[0029] Those skilled in the art can understand that when it is detected that all seats in the car are occupied, the exclusion rule based on a single occupant position can be cancelled, and the above-mentioned safety collision model can be used to calculate the comprehensive injury index of the occupants in the car corresponding to each collision area, such as the weighted sum of the head injury criterion HIC value, chest compression, leg force peak, etc., and finally generate a priority list of candidate positions arranged in ascending order of injury index. Alternatively, the area with the highest vehicle structure crashworthiness score, such as the connection between the front longitudinal beam and the chassis, can be given priority. Even if its associated occupant injury index is not the lowest, active safety linkage can be achieved by, for example, triggering the corresponding side airbag inflation in advance, locking the electric seat backward, etc., thereby compensating for the corresponding protection effect.

[0030] Step 204: Adjust the driving path of the vehicle so that the vehicle collides with the target object at the target position.

[0031] Based on the target position determined in the previous step, the vehicle control system can generate a path adjustment instruction, thereby shifting the actual motion trajectory of the vehicle toward the target position. The adjustment operation of the driving path can be achieved through the coordinated action of vehicle actuators, such as the electronic stability program, electric power steering system, drive motor and other components, to ensure that the vehicle is guided to the target position and contacts the target object before the collision occurs, thereby utilizing the optimal area of ​​the vehicle's collision resistance to absorb the collision energy, directly reducing vehicle structural damage and occupant safety risks.

[0032] Specifically, the adjustment process of the driving path of the above-mentioned vehicle in this specification can be further divided.

[0033] In one embodiment, the adjusted path parameters of the vehicle can be determined based on the target position; then, the path adjustment instructions based on the braking, steering and driving dimensions are generated based on the adjusted path parameters of the vehicle, and the path adjustment instructions are executed to adjust the driving path. The adjusted path parameters of the vehicle can be calculated in real time by the vehicle dynamics model, which may include specific values ​​such as the target lateral offset, the longitudinal speed change rate, the heading angle correction value and the path curvature constraint conditions. The above parameters can meet the vehicle kinematic feasibility and the current actual road environment constraints, such as the maximum lateral acceleration does not exceed 0.5g and does not cross the solid lane or the shoulder. As for the above path adjustment instructions based on the braking, steering and driving dimensions, they can be understood as multi-dimensional path adjustment instructions, that is, different instructions are respectively proposed to the vehicle braking system, steering system and driving system to ensure that the vehicle can adjust the driving path according to the expected requirements of the path adjustment instructions, thereby reducing the possibility of accidental collision with the target object.

[0034] In addition, as mentioned above, "the vehicle itself 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 the vehicle and the target object will actually collide. Therefore, it is possible to regularly determine whether the vehicle and the target object are about to collide while adjusting the driving path of the vehicle, that is, re-collect the motion state information of the vehicle and the target object at each preset period, and recalculate the latest collision probability between the vehicle and the target object based on the updated data, and when it is detected that the recalculated collision probability is lower than the preset probability threshold, it is determined that the vehicle and the target object are out of the inevitable collision state. At this time, the collision with the target object at the target position can be immediately terminated, and the driving path of the vehicle can be adjusted to actively avoid the target object, thereby minimizing the risk of the vehicle. Of course, if the judgment 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.

[0035] It is worth mentioning that the occupant distribution information mentioned above can also be used to assist in the decision-making of the above-mentioned driving path. For example, when the occupant distribution information indicates that there are only occupants in the main driving position, if there is insufficient space to avoid the oncoming vehicle or the rear-end truck, the electric power steering can be used to fine-tune the direction to the left, guide the collision point to the co-pilot side or the right rear door area, and trigger the electronic stability program to coordinate braking to assist the vehicle rotation to reduce the impact on the main driver's side; if a lateral vehicle is encountered, such as a right-angle collision at an intersection, the collision point can be moved back to the rear crumple zone through instantaneous acceleration to reduce the force on the passenger compartment. When there are occupants in both the main and co-pilot seats in the front row, the vehicle can exclude the side panel areas according to the real-time occupant distribution, and control the vehicle rotation through steering and braking coordination, so that the collision point is locked on the rear door or the rear energy absorption area, and the side airbags are linked to inflate in advance. Furthermore, when the vehicle is fully loaded, priority is given to collisions at positions corresponding to collision pillars such as the A-pillar and B-pillar, triggering the linkage of the airbags of the entire vehicle and the rearward locking function of the seats; if the road environment restricts the path adjustment, the areas with the highest anti-collision performance, such as the connection between the front longitudinal beam and the chassis, are forcibly locked, and the occupant injury index is comprehensively evaluated through the above-mentioned safety collision model to ensure that energy is dispersed to the maximum extent and occupant safety is protected when a collision is inevitable.

[0036] Combine the following Figure 4 The schematic diagram of the architecture of the algorithm for dealing with vehicle collision risk shown in FIG. 1 explains the method for dealing with the above-mentioned vehicle collision risk. Figure 4 It should be noted in advance that the vehicle-mounted sensor 402 can be used as an independent hardware device, including millimeter wave radar, camera, laser radar, inertial measurement unit, seat pressure sensor, in-cabin camera array, infrared thermal imaging module, etc., which is directly deployed on the vehicle and is responsible for collecting vehicle motion state, object motion state and road environment information. The driving path planning model 404, the target position selection model 406, and the driving path decision model 408 can be deployed on the DCU, the autonomous driving domain controller or the vehicle-mounted independent computing hardware with computing power 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 actuator device to realize the function and then execute the corresponding path adjustment instruction.

[0037] Specifically, Figure 4The diagram shows the architecture of the vehicle collision risk response system. The core function of the vehicle-mounted sensor 402 in the diagram is to collect data. On the one hand, it can collect the first motion state information of the vehicle itself, the second motion state information of the surrounding candidate objects, and the road environment information and provide them to the driving path planning model 404, so that the vehicle-mounted sensor model 404 generates a set of vehicle drivable paths based on the acquired road environment information, preliminarily determines whether the vehicle and the target object are about to collide, and provides path basis for the collision probability calculation module in the target position selection model 406 and the driving path decision model 408. As for the collision probability calculation module in the target position selection model 406, it can obtain the motion state information of the vehicle and the candidate object based on the information of the driving path planning model 404, and then calculate the collision probability between the two and determine the target object; the occupant distribution information generation module can use the information provided by the seat pressure sensor, the cabin camera and other equipment in the vehicle-mounted sensor 402 to generate the occupant distribution information in the vehicle, which is used to screen a safe set of candidate target positions to assist the safe collision model in determining the target position. The safety collision model is based on the target object determined by the collision probability calculation module and the candidate target position set of the occupant distribution information generation module, and performs vehicle structure analysis and collision test data construction to characterize the relationship between the collision angle, position and the degree of vehicle damage. Through the vehicle and object motion state information input by the collision probability calculation module, the damage degree of each collision area is evaluated, and the target position with the lowest damage is selected and output to the driving path decision model 408, so that the driving path decision model 408 can calculate the adjusted path parameters of the vehicle according to the target position determined by the target position selection model, generate path adjustment instructions in the 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 above path adjustment instructions, that is, the vehicle trajectory is adjusted in coordination through the actuators such as the electronic stability program and the steering system, so that the vehicle is offset to the target position.

[0038] Figure 5 is a schematic structural diagram of an electronic device in an exemplary embodiment. 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 required 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 the software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0039] Figure 6A block diagram of a device for dealing with vehicle collision risk is shown in an embodiment of the present invention. Figure 6 , the device can be applied to Figure 5 In the device shown, to implement the technical solution described in the present invention, the device includes: A target position determination unit 602 is used to determine a target position on the vehicle according to vehicle motion state information of the vehicle and object motion state information of the target object when it is determined that the vehicle and the target object are about to collide, wherein the vehicle damage degree corresponding to the target position is not higher than the vehicle damage degree corresponding to other collision positions; The driving path adjustment unit 604 is used to adjust the driving path of the vehicle so that the vehicle collides with the target object at the target position.

[0040] Optionally, the device further comprises: a collision probability processing unit, configured to obtain first motion state information of the vehicle, second motion state information of candidate objects around the vehicle, and road environment information according to an onboard sensor of the vehicle; Determining a collision probability between the vehicle and the candidate object according to 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 used as the target object, and it is determined that the vehicle is about to collide with the target object.

[0041] Optionally, the collision probability processing unit is specifically used for: Generate at least one drivable path for the vehicle based on the road environment information; Predicting the object motion trajectory of the candidate object within a preset time period according to the first motion state information and the second motion state information, so as to identify a spatial coincidence point between the at least one drivable path of the vehicle and the object motion trajectory within the preset time period; The collision probability is calculated according to the number of the spatial coincidence points and the time distribution characteristics.

[0042] Optionally, the method further includes: The vulnerable group removing unit is used to remove the vulnerable road user group from the candidate objects when there are multiple candidate objects and there is a vulnerable road user group among the multiple candidate objects.

[0043] Optionally, the target position determining unit 602 is specifically configured to: The target position is determined 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 degree of damage to each collision area and the collision parameters of the vehicle under different collision angles and different collision positions.

[0044] Optionally, the target position determining unit 602 is specifically configured to: generating occupant distribution information of occupants in the vehicle according to the vehicle-mounted sensors of the vehicle; determining a candidate target position set according to the occupant distribution information, wherein the occupant distribution information does not match any target position in the target position set; The target position on the vehicle is determined from the candidate target position set according to the vehicle motion state information of the vehicle and the object motion state information of the target object.

[0045] Optionally, the transposition further includes: a driving path readjustment unit, configured to periodically determine whether a collision between the vehicle and a target object is about to occur while adjusting the driving path of the vehicle; When the judgment result is negative, the driving path of the vehicle is adjusted to avoid a collision between the vehicle and the target object.

[0046] Optionally, the driving path adjustment unit 604 is specifically configured to: Determining adjusted path parameters of the vehicle according to the target position; Generate path adjustment instructions for braking, turning and driving dimensions according to the adjusted path parameters of the vehicle, and execute the path adjustment instructions to adjust the driving path.

[0047] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0048] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this specification. Ordinary technicians in this field can understand and implement it without paying creative work.

[0049] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing processor executable instructions; wherein the processor implements the steps of the method described in any of the above embodiments by running the executable instructions.

[0050] Based on the same concept as the above method, this specification also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0051] Based on the same concept as the above method, this specification also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any of the above embodiments when executed by a processor.

[0052] The embodiments of the subject matter and functional operations described in this specification may be implemented in the following: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. The embodiments of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules in computer program instructions encoded on a tangible non-temporary program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagation signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by a data processing device. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0053] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by special-purpose logic circuits, such as FPGAs (field programmable gate arrays) or ASICs (application-specific integrated circuits), and the apparatus can also be implemented as special-purpose logic circuits.

[0054] Computers suitable for executing computer programs include, for example, general and / or special microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read-only memory and / or a 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 large-capacity storage devices for storing data, such as a disk, a magneto-optical disk, or an optical disk, or the computer will be operably coupled to this large-capacity storage device to receive data from it or to transmit data to it, or both. However, a computer does not necessarily have such a device. In addition, 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.

[0055] Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including, for example, semiconductor memory devices (e.g., EPROM, EEPROM and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0056] Although this specification includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of the specific embodiments of specific inventions. Certain features described in multiple embodiments in this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claim protection, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of a sub-combination.

[0057] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or requiring that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0058] Thus, specific embodiments of the subject matter have been described. Furthermore, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0059] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.

Claims

1. A method for dealing with vehicle collision risk, characterized in that: The method comprises: In the case where it is determined that the vehicle and the target object are about to collide, determining a target position on the vehicle according to the vehicle motion state information of the vehicle and the object motion state information of the target object, wherein the vehicle damage degree corresponding to the target position is not higher than the vehicle damage degree corresponding to other collision positions; The driving path of the vehicle is adjusted so that the vehicle collides with the target object at the target position.

2. The method according to claim 1, characterized in that Determining that the vehicle is about to collide with the target object includes: Acquire first motion state information of the vehicle, second motion state information of candidate objects around the vehicle, and road environment information according to an onboard sensor of the vehicle; Determining a collision probability between the vehicle and the candidate object according to 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 used as the target object, and it is determined that the vehicle is about to collide with the target object.

3. The method according to claim 2, characterized in that The determining the collision probability between the vehicle and the candidate object according to the first motion state information, the second motion state information and the road environment information includes: Generate at least one drivable path for the vehicle based on the road environment information; Predicting the object motion trajectory of the candidate object within a preset time period according to the first motion state information and the second motion state information, so as to identify a spatial coincidence point between the at least one drivable path of the vehicle and the object motion trajectory within the preset time period; The collision probability is calculated according to the number of the spatial coincidence points and the time distribution characteristics.

4. The method according to claim 2, characterized in that: The method further comprises: In the case that there are multiple candidate objects and there is a vulnerable road user group among the multiple candidate objects, the vulnerable road user group is removed from the candidate objects.

5. The method according to claim 1, characterized in that The determining the target position on the vehicle according to the vehicle motion state information of the vehicle and the object motion state information of the target object comprises: The target position is determined 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 degree of damage to each collision area and the collision parameters of the vehicle under different collision angles and different collision positions.

6. The method according to claim 1, characterized in that The determining the target position on the vehicle according to the vehicle motion state information of the vehicle and the object motion state information of the target object comprises: generating occupant distribution information of occupants in the vehicle according to the vehicle-mounted sensors of the vehicle; determining a candidate target position set according to the occupant distribution information, wherein the occupant distribution information does not match any target position in the target position set; The target position on the vehicle is determined from the candidate target position set according to the vehicle motion state information of the vehicle and the object motion state information of the target object.

7. The method according to claim 1, characterized in that The method further comprises: In case of adjusting the driving path of the vehicle, periodically determining whether the vehicle is about to collide with a target object; When the judgment result is negative, the driving path of the vehicle is adjusted to avoid a collision between the vehicle and the target object.

8. The method according to claim 1, characterized in that The adjusting the driving path of the vehicle includes: Determining adjusted path parameters of the vehicle according to the target position; A path adjustment instruction based on braking, steering and driving dimensions is generated according to the vehicle adjusted path parameters, and the path adjustment instruction is executed to adjust the driving path.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 8 are implemented.

10. A computer program product, characterized in that The method comprises a computer program / instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 8.

Images