Environmentally interactive vehicle-cyclist collision mitigation method and device

Abstract

The present invention provides an environment interactive vehicle-rider collision mitigation method and device. The method comprises: obtaining the distance between the rider and the vehicle, triggering a safety warning signal when it is determined that the rider has entered the safety warning area according to the distance, and obtaining the motion sequence of the rider and the motion sequence of the vehicle in the safety warning area; predicting the virtual motion sequence of the rider according to the motion sequence of the rider; predicting the virtual motion sequence of the vehicle according to the motion sequence of the vehicle; judging whether the rider and the vehicle collide according to the virtual motion sequence of the rider and the virtual motion sequence of the vehicle; in the case of predicting a collision, when the rider enters the collision mitigation area, triggering a collision mitigation signal, and adaptively adjusting the driving state of the vehicle according to the collision mitigation signal to avoid a collision. The method improves the protection capability for riders.

Description

Technical Field

[0001] The present invention relates to the technical field of road traffic safety, and in particular to an environment interactive vehicle-rider collision mitigation method and device. Background Art

[0002] In road traffic safety, the safety of cyclists caused by collisions between cyclists and vehicles is a very serious problem. When a collision is about to happen, cyclists often make emergency responses. However, the current protection for traffic participants such as cyclists is only developed for the unchanged state, and cannot be adaptively adjusted according to the emergency response made by cyclists, so the protection ability for cyclists is insufficient. Summary of the invention

[0003] The present invention provides an environment interactive vehicle-rider collision mitigation method and device, which are used to solve the defect in the prior art that adaptive adjustment cannot be made according to the emergency response of the rider.

[0004] The present invention provides an environment interactive vehicle-rider collision mitigation method, comprising:

[0005] Obtain the distance between the cyclist and the vehicle, and determine whether the cyclist has entered the safety warning area based on the distance;

[0006] In the case of entering the safety warning area, a safety warning signal is triggered, and a motion sequence of the rider and the vehicle in the safety warning area is obtained; the motion sequence is a sequence composed of horizontal and vertical coordinate position transformations in space;

[0007] Predicting a virtual motion sequence of the rider based on the motion sequence of the rider; predicting a virtual motion sequence of the vehicle based on the motion sequence of the vehicle;

[0008] Determining whether a collision occurs between the rider and the vehicle according to the rider's virtual motion sequence and the vehicle's virtual motion sequence;

[0009] In the event of a predicted collision, when the rider enters the collision mitigation zone, a collision mitigation signal is triggered, and the driving state of the vehicle is adaptively adjusted based on the collision mitigation signal to avoid a collision.

[0010] According to an environment interactive vehicle-cyclist collision mitigation method provided by the present invention, before obtaining the distance between the cyclist and the vehicle, the method further includes:

[0011] A circular safety space grille is constructed; the circular safety space grille is a concentric circle formed by the safety warning area and the collision mitigation area with the vehicle as the midpoint; the safety warning area is an annular area formed by the safety distance between the vehicle and the rider; the radius of the collision mitigation area is half of the safety distance; the distance between the grille node of the circular safety space grille and the midpoint is the length of the vehicle body.

[0012] According to an environment interactive vehicle-rider collision mitigation method provided by the present invention, controlling the driving state of the vehicle according to the collision mitigation signal to avoid collision includes:

[0013] Get the rider's initial damage status J I And the changing virtual damage stateJ P ; The changing virtual damage state J P When a rider makes an emergency response to a collision, different injury states are determined according to different riding states of the rider at corresponding grid points; the riding states include: the rider's spatial position and riding speed;

[0014] According to the initial injury state of the rider J I And the changing virtual damage state J P , determine the safety score R;

[0015]

[0016] Wherein, L is the regularization coefficient;

[0017] The vehicle state corresponding to the highest score is selected from all safety scores R, and the driving state of the vehicle is continuously adjusted based on the vehicle state until the rider leaves the safety warning area or the safety score R reaches a preset value; the vehicle state includes: the spatial position and speed of the vehicle.

[0018] According to an environment interactive vehicle-cyclist collision mitigation method provided by the present invention, the initial damage state J of the cyclist is obtained. I include:

[0019] Determining, according to the virtual motion sequence of the rider and the virtual motion sequence of the vehicle, a first relative speed and a first relative position of the rider corresponding to a collision between the rider and the vehicle;

[0020] An initial injury state of the rider is determined according to the first relative speed and the first relative position.

[0021] According to an environment interactive vehicle-cyclist collision mitigation method provided by the present invention, the continuously changing virtual damage state J is obtained.P include:

[0022] When the rider makes an emergency response, a first vehicle state corresponding to the vehicle at the current grid point and a first riding state corresponding to the rider at the current grid point are obtained; the first vehicle state includes: right turn, left turn, speed, and acceleration of the vehicle;

[0023] Determine, according to the virtual motion sequence of the ego vehicle, a second ego vehicle state corresponding to when the ego vehicle moves to the next grid point; determine, according to the virtual motion sequence of the rider, a second riding state corresponding to when the rider moves to the next grid point;

[0024] Discretizing the riding state of the rider according to the first riding state and the second riding state, and selecting the riding state corresponding to the maximum value of the speed from the discretized data;

[0025] Discretizing the ego vehicle state according to the first ego vehicle state and the second ego vehicle state, and selecting the ego vehicle state corresponding to the maximum acceleration from the discretized data;

[0026] Combine the riding state corresponding to the maximum value of the speed with the vehicle state corresponding to the maximum acceleration to obtain a second relative position and a second relative vehicle speed between the vehicle and the rider;

[0027] According to the second relative position and the second relative vehicle speed, the initial virtual damage state J is determined P ;

[0028] According to the changing emergency response of the rider, the relative position and relative speed between the vehicle and the rider are continuously obtained, and the continuously changing virtual damage state J is determined according to the relative position and relative speed obtained each time. P .

[0029] According to an environmentally interactive vehicle-rider collision mitigation method provided by the present invention, the initial injury state includes: intracranial pressure, chest compression, and leg strain.

[0030] According to an environmental interactive vehicle-rider collision mitigation method provided by the present invention, the initial damage state is a state predicted by a machine learning model.

[0031] The present invention also provides an environment interactive vehicle-rider collision mitigation device, comprising: an acquisition unit, for acquiring the distance between the rider and the vehicle, and determining whether the rider enters a safety warning area according to the distance;

[0032] A trigger unit, used to trigger a safety warning signal when entering the safety warning area;

[0033] The acquisition unit is further used to acquire a motion sequence of the rider and the vehicle in the safety warning area; the motion sequence is a sequence formed by the transformation of the horizontal and vertical coordinate positions in space;

[0034] A prediction unit, configured to predict a virtual motion sequence of the rider according to the motion sequence of the rider; and predict a virtual motion sequence of the vehicle according to the motion sequence of the vehicle;

[0035] A judgment unit, used for judging whether a collision occurs between the rider and the vehicle according to the virtual motion sequence of the rider and the virtual motion sequence of the vehicle;

[0036] The control unit is used to trigger a collision mitigation signal when the rider enters the collision mitigation zone in the event of a predicted collision, and to adaptively adjust the driving state of the vehicle according to the collision mitigation signal to avoid a collision.

[0037] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the environmental interactive vehicle-rider collision mitigation method as described above is implemented.

[0038] The environmental interactive vehicle-rider collision mitigation method and device provided by the present invention can flexibly adjust the driving state of the own vehicle to avoid collision by judging whether the virtual motion sequence of the rider collides with the virtual motion sequence of the own vehicle. This method improves the protection capability for the rider. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 One of the flow charts of the environmental interactive vehicle-cyclist collision mitigation method provided by the present invention;

[0041] Figure 2 The second flow chart of the environmental interactive vehicle-cyclist collision mitigation method provided by the present invention;

[0042] Figure 3 A structural block diagram of an environment-interactive vehicle-rider collision mitigation device provided by the present invention;

[0043] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Figure 1 One of the flow charts of the environmental interactive vehicle-rider collision mitigation method provided by the present invention is as follows: Figure 1 As shown, the method comprises the following steps:

[0046] Step 101: Obtain the distance between the cyclist and the vehicle, and determine whether the cyclist enters the safety warning area based on the distance.

[0047] Specifically, the ego-car is a car driven by oneself.

[0048] Step 102: When entering the safety warning area, a safety warning signal is triggered, and a motion sequence of the rider and the vehicle in the safety warning area is obtained; the motion sequence is a sequence consisting of horizontal and vertical coordinate position transformations in space.

[0049] Specifically, the motion sequence of the rider is a sequence of changes in the spatial position of the rider during riding, and each element in the sequence is represented by the horizontal and vertical coordinates of the rider's space. The motion sequence of the car is a sequence of changes in the spatial position of the car during driving.

[0050] Step 103: predicting a virtual motion sequence of the rider according to the motion sequence of the rider; and predicting a virtual motion sequence of the vehicle according to the motion sequence of the vehicle.

[0051] Specifically, the virtual motion sequence is a motion sequence obtained by extending the trajectory line according to the position transformation at the previous time to obtain the trajectory at the next time.

[0052] Step 104: determining whether a collision occurs between the rider and the vehicle according to the rider's virtual motion sequence and the vehicle's virtual motion sequence.

[0053] Specifically, the judgment of whether the rider and the vehicle collide is to judge whether the rider's virtual motion sequence and the vehicle's virtual motion sequence intersect. If they intersect, it means that the rider and the vehicle collide. The so-called intersection means that the vehicle and the rider's bicycle overlap in motion sequence, that is, the horizontal and vertical coordinates of the spatial position overlap.

[0054] Step 105: When a collision is predicted, when the rider enters the collision mitigation area, a collision mitigation signal is triggered, and the driving state of the vehicle is adaptively adjusted according to the collision mitigation signal to avoid a collision.

[0055] The environmental interactive vehicle-rider collision mitigation method and device provided by the present invention can flexibly adjust the driving state of the own vehicle to avoid collision by judging whether the virtual motion sequence of the rider collides with the virtual motion sequence of the own vehicle. This method improves the protection capability for the rider.

[0056] Furthermore, before obtaining the distance between the cyclist and the vehicle, the following is also included:

[0057] A circular safety space grille is constructed; the circular safety space grille is a concentric circle formed by the safety warning area and the collision mitigation area with the vehicle as the midpoint; the safety warning area is an annular area formed by the safety distance between the vehicle and the rider; the radius of the collision mitigation area is half of the safety distance; the distance between the grille node of the circular safety space grille and the midpoint is the length of the vehicle body.

[0058] Specifically, the center of the circular safety space grid is the position of the car driven by the user. Concentric circles are constructed with the position of the car as the center, and a grid grid is drawn on the concentric circles. The grid nodes are the points on the grid.

[0059] The following is a detailed introduction on how to control the driving state of the vehicle according to the collision mitigation signal to avoid a collision, which specifically includes the following steps:

[0060] First, obtain the rider’s initial damage state J I And the changing virtual damage stateJ P ; The changing virtual damage state J P When the rider makes an emergency response to a collision, different injury states are determined according to the different riding states of the rider at the corresponding grid points; the riding state includes: the rider's spatial position and riding speed; secondly, according to the rider's initial injury state J I And the changing virtual damage state J P , determine the safety score R; R = L*(J I -J P), L is the regularization coefficient; finally, the vehicle state corresponding to the highest score R is selected from all safety scores, and the driving state of the vehicle is continuously adjusted with the vehicle state until the rider leaves the safety warning area or the safety score R reaches a preset value; the vehicle state includes: the spatial position and speed of the vehicle. The initial injury state includes: intracranial pressure, chest compression, and leg strain.

[0061] Wherein, the initial injury state J of the rider is obtained. I The method comprises: determining, according to a virtual motion sequence of the rider and a virtual motion sequence of the vehicle, a first relative speed and a first relative position of the rider corresponding to a collision between the rider and the vehicle; and determining an initial injury state of the rider according to the first relative speed and the first relative position.

[0062] Specifically, the present invention calculates the initial injury state (intracranial pressure, chest compression, and leg strain) of the rider according to the predicted relative speed and relative position at the intersection position. The calculation method is: using the relative speed and relative position as boundary conditions, the intracranial pressure, chest compression, and leg strain of the rider after the collision are calculated by finite element method. At the same time, in order to improve the real-time calculation efficiency, an injury database can be established after multiple calculations, and a machine learning model can be established. With the relative speed and relative position as input, the intracranial pressure, chest compression, and leg strain of the rider are predicted.

[0063] Next, we will discuss how to obtain the constantly changing virtual damage state J P Detailed explanation:

[0064] First, when the rider makes an emergency response, the first self-vehicle state corresponding to the self-vehicle at the current grid point and the first riding state corresponding to the rider at the current grid point are obtained; the first self-vehicle state includes: right turn, left turn, speed, and acceleration of the self-vehicle; secondly, according to the virtual motion sequence of the self-vehicle, the second self-vehicle state corresponding to the self-vehicle when the self-vehicle moves to the next grid point is determined; according to the virtual motion sequence of the rider, the second riding state corresponding to the rider when the rider moves to the next grid point is determined; thirdly, according to the first riding state and the second riding state, the riding state of the rider is discretized, and the riding state corresponding to the maximum value of the speed pair is selected from the discretized data; thirdly, according to the first self-vehicle state and the second self-vehicle state, the self-vehicle state is discretized, and the self-vehicle state corresponding to the maximum acceleration is selected from the discretized data; thirdly, the riding state corresponding to the maximum value of the speed pair and the self-vehicle state corresponding to the maximum acceleration are combined to obtain the second relative position and the second relative speed between the self-vehicle and the rider; thirdly, according to the second relative position and the second relative speed, the initial virtual damage state J is determined. PFinally, according to the rider's changing emergency response, the relative position and relative speed between the vehicle and the rider are continuously obtained, and the continuously changing virtual damage state J is determined according to the relative position and relative speed obtained each time. P .

[0065] Specifically, when facing a collision, the rider makes an emergency response and controls the wheel angle to change continuously, resulting in a continuous change in the relative position between the rider and the vehicle. While the rider makes an emergency response, the state of the vehicle moving to the next spatial grid position is discretized, including right turn, braking, left turn, and acceleration. The discretized braking and acceleration intervals are the variable intervals of the vehicle in the current time domain.

[0066] The relative position is obtained through the laser radar, and the speed of the two vehicles is obtained through the speedometer to calculate the relative speed. The relative position is the contact angle and contact position between the bicycle and the car when the car collides with the cyclist's bicycle.

[0067] Discrete means initializing the next action of the car. Since we don't know what the next action of the car will be, we first list all the car states (including acceleration, braking, etc.). Discrete braking and acceleration intervals refer to the maximum acceleration or braking speed limit that can be generated under the current vehicle state. For example, if the maximum braking acceleration is 50, the discrete braking is the braking acceleration of 10, 20, 30, 40, and 50 respectively. The acceleration interval refers to the upper limit of the acceleration that can be generated by the accelerator pedal under the current road scene and the vehicle speed. The current time domain refers to the time required for the car to move to the next spatial grid position at the current speed.

[0068] The method provided by the present invention is generally introduced below. Figure 2 The second flow chart of the environmental interactive vehicle-cyclist collision mitigation method provided by the present invention is as follows: Figure 2 As shown, the method comprises the following steps:

[0069] Step 1: construct a circular safety space grid with the vehicle as the midpoint;

[0070] Step 2: Detect the surrounding environment through the on-board laser radar, and trigger a safety warning signal when a rider enters the safety warning range;

[0071] Step 3, obtaining the motion sequence of the rider within the safety warning range and the motion sequence of the vehicle;

[0072] Step 4: predict the virtual motion sequence of the cyclist at the same distance based on the motion sequence of the cyclist within the safety warning range, and determine whether there is an intersection with the motion sequence of the vehicle;

[0073] Step 4: If there is an intersection, a collision mitigation signal is triggered when the rider enters the collision mitigation range;

[0074] Step 5, calculating the initial injury state (intracranial pressure, chest compression, and leg strain) of the rider through a rider injury calculation module according to the predicted relative speed and relative position at the crossing position;

[0075] Step 6: When facing a collision, the rider responds by controlling the wheel angle to change continuously, causing the relative position between the rider and the vehicle to change continuously;

[0076] Step 7, while the rider makes an emergency response, the state of the vehicle moving to the next spatial grid position is discretized, including right turn, braking, left turn, and acceleration, and the discretized braking and acceleration intervals are variable intervals of the vehicle in the current time domain;

[0077] Step 8, combining the emergency response of the rider and the discretized vehicle state to obtain the virtual relative position and relative vehicle speed, and calculating the changed virtual damage state through the damage module;

[0078] Step 9: Establish a damage penalty module based on the initial damage state J I And the virtual damage state J P The safety score R is determined. When the damage state decreases, the safety score is positive, and when the damage state increases, the safety score is negative.

[0079] Step 10, selecting the vehicle state corresponding to the highest safety factor to control the vehicle, wherein the control includes controlling the left and right directions through the steering wheel, controlling the braking torque through the brake pedal, and controlling the acceleration through the accelerator pedal;

[0080] Step 11, repeat steps 6-10, and control the vehicle to continuously move to the next space grid until the rider leaves the circular safety space grid range, or the damage status is 0.

[0081] The environment interactive vehicle-rider collision mitigation device provided by the present invention is described below. The environment interactive vehicle-rider collision mitigation device described below and the environment interactive vehicle-rider collision mitigation method described above can be referred to each other.

[0082] Figure 3 The present invention also provides a structural block diagram of an environment-interactive vehicle-rider collision mitigation device, such as Figure 3 As shown, including:

[0083] The acquisition unit 301 is used to acquire the distance between the rider and the vehicle, and determine whether the rider enters the safety warning area according to the distance;

[0084] A trigger unit 302 is used to trigger a safety warning signal when entering the safety warning area;

[0085] The acquisition unit 301 is further used to acquire a motion sequence of the rider and the vehicle in the safety warning area; the motion sequence is a sequence formed by the transformation of the horizontal and vertical coordinate positions in space;

[0086] The prediction unit 303 is used to predict the virtual motion sequence of the rider according to the motion sequence of the rider; and predict the virtual motion sequence of the vehicle according to the motion sequence of the vehicle;

[0087] A judgment unit 304 is used to judge whether the rider and the vehicle collide with each other according to the virtual motion sequence of the rider and the virtual motion sequence of the vehicle;

[0088] The control unit 305 is used to trigger a collision mitigation signal when the rider enters the collision mitigation area in the event of a predicted collision, and adaptively adjust the driving state of the vehicle according to the collision mitigation signal to avoid a collision.

[0089] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 830 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the environment interactive vehicle-rider collision mitigation method.

[0090] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0091] The device embodiments described above are merely illustrative, 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 embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0092] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An environmentally interactive vehicle-rider collision mitigation method, characterized in that: include: Obtain the distance between the cyclist and the vehicle, and determine whether the cyclist has entered the safety warning area based on the distance; In the case of entering the safety warning area, a safety warning signal is triggered, and a motion sequence of the rider and the vehicle in the safety warning area is obtained; the motion sequence is a sequence composed of horizontal and vertical coordinate position transformations in space; Predicting a virtual motion sequence of the rider based on the motion sequence of the rider; predicting a virtual motion sequence of the vehicle based on the motion sequence of the vehicle; Determining whether a collision occurs between the rider and the vehicle according to the rider's virtual motion sequence and the vehicle's virtual motion sequence; In the event of a predicted collision, when the rider enters the collision mitigation zone, a collision mitigation signal is triggered, and the driving state of the vehicle is adaptively adjusted according to the collision mitigation signal to avoid a collision; Before obtaining the distance between the cyclist and the vehicle, it also includes: Construct a circular safety space grid; the circular safety space grid is a concentric circle formed by the safety warning area and the collision mitigation area with the vehicle as the midpoint; the safety warning area is an annular area formed by the safety distance between the vehicle and the rider; the radius of the collision mitigation area is half of the safety distance; the distance between the grid node of the circular safety space grid and the midpoint is the length of the vehicle body; The controlling the driving state of the vehicle according to the collision mitigation signal to avoid a collision includes: Get the rider's initial damage status J I And the changing virtual damage stateJ P ; The changing virtual damage state J P When a rider makes an emergency response to a collision, different injury states are determined according to different riding states of the rider at corresponding grid points; the riding states include: the rider's spatial position and riding speed; According to the initial injury state of the rider J I And the changing virtual damage state J P , determine the safety score R; R=L*(J I -J P ) Wherein, L is the regularization coefficient; The vehicle state corresponding to the highest score is selected from all safety scores R, and the driving state of the vehicle is continuously adjusted based on the vehicle state until the rider leaves the safety warning area or the safety score R reaches a preset value; the vehicle state includes: the spatial position and speed of the vehicle.

2. The environmentally interactive vehicle-rider collision mitigation method according to claim 1, characterized in that: The initial injury state J of the rider is obtained. I include: Determining, according to the virtual motion sequence of the rider and the virtual motion sequence of the vehicle, a first relative speed and a first relative position of the rider corresponding to a collision between the rider and the vehicle; An initial injury state of the rider is determined according to the first relative speed and the first relative position.

3. The environmentally interactive vehicle-rider collision mitigation method according to claim 1, characterized in that: Obtain the changing virtual damage state J P include: When the rider makes an emergency response, a first vehicle state corresponding to the vehicle at the current grid point and a first riding state corresponding to the rider at the current grid point are obtained; the first vehicle state includes: right turn, left turn, speed, and acceleration of the vehicle; Determine, according to the virtual motion sequence of the ego vehicle, a second ego vehicle state corresponding to when the ego vehicle moves to the next grid point; determine, according to the virtual motion sequence of the rider, a second riding state corresponding to when the rider moves to the next grid point; discretize the riding state of the rider according to the first riding state and the second riding state, and select the riding state corresponding to the maximum speed from the discretized data; Discretizing the ego vehicle state according to the first ego vehicle state and the second ego vehicle state, and selecting the ego vehicle state corresponding to the maximum acceleration from the discretized data; Combining the riding state corresponding to the maximum speed with the vehicle state corresponding to the maximum acceleration to obtain a second relative position and a second relative vehicle speed between the vehicle and the rider; According to the second relative position and the second relative vehicle speed, the initial virtual damage state J is determined P ; According to the changing emergency response of the rider, the relative position and relative speed between the vehicle and the rider are continuously obtained, and the continuously changing virtual damage state J is determined according to the relative position and relative speed obtained each time. P .

4. The environmentally interactive vehicle-rider collision mitigation method according to claim 1, characterized in that: The initial injury status includes: intracranial pressure, chest compression, and leg strain.

5. The environmentally interactive vehicle-rider collision mitigation method according to claim 1, characterized in that: The initial damage state is a state predicted by a machine learning model.

6. A device for executing the environmental interactive vehicle-rider collision mitigation method of claim 1, characterized in that: include: An acquisition unit, used to acquire the distance between the rider and the vehicle, and determine whether the rider enters the safety warning area according to the distance; A trigger unit, used to trigger a safety warning signal when entering the safety warning area; The acquisition unit is further used to acquire a motion sequence of the rider and the vehicle in the safety warning area; the motion sequence is a sequence formed by the transformation of the horizontal and vertical coordinate positions in space; A prediction unit, configured to predict a virtual motion sequence of the rider according to the motion sequence of the rider; and predict a virtual motion sequence of the vehicle according to the motion sequence of the vehicle; A judgment unit, used for judging whether a collision occurs between the rider and the vehicle according to the virtual motion sequence of the rider and the virtual motion sequence of the vehicle; The control unit is used to trigger a collision mitigation signal when the rider enters the collision mitigation zone in the event of a predicted collision, and to adaptively adjust the driving state of the vehicle according to the collision mitigation signal to avoid a collision.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the environment interactive vehicle-rider collision mitigation method as described in any one of claims 1 to 5 is implemented.

Images