Safety control method, device, electronic device and storage medium for vehicle

Abstract

The present application relates to a safety control method, device, electronic device and storage medium for a vehicle. The method includes: determining the blind spot position and the collidable area of the current vehicle by obtaining the first state information of the current vehicle and the second state information of the target vehicle, calculating the safety distance between the current vehicle and the collidable area, and at the same time determining the current blind spot level of the current vehicle based on the obtained longitudinal relative distance, lateral relative distance between the current vehicle and the target vehicle, and the above-mentioned safety distance. Based on a preset trajectory generation model, a corresponding pedestrian prediction trajectory is generated and input into the trajectory planning module of the current vehicle, so as to control the current vehicle to perform a deceleration action and / or an avoidance action. According to the vehicle safety control method of the embodiments of the present application, by jointly considering the state information of the vehicle and the bus under the platform and performing blind spot grading to deal with it, the initiative of the autonomous vehicle planning in the bus platform scenario is improved, and the driving safety is guaranteed.

Description

Technical Field

[0001] This application relates to the technical field of active safety for autonomous driving, and particularly to a safety control method, device, electronic device and storage medium for a vehicle. Background Art

[0002] Autonomous driving technology has become one of the most popular research topics globally, greatly improving traffic efficiency and driving safety. Limited by the sensor perception range and vehicle occlusion in complex traffic scenarios, especially in the bus stop scenario where large buses block pedestrians, autonomous vehicles cannot timely perceive and predict pedestrians in the blind spot of driving, resulting in ineffective handling of emergencies and serious traffic accidents. Therefore, in the existing technology system, actively avoiding sudden dangerous situations such as "ghost pedestrians" at bus stop scenarios is a feasible technical means to achieve safe and stable driving.

[0003] In related technologies, most blind spot warning systems need to combine the observation history and adopt a "tracking - prediction" mode to determine whether a traffic participant will collide with the host vehicle at a future moment.

[0004] However, this judgment mode cannot obtain the pedestrian trajectory scenario in advance. For example, at a bus stop, due to the large occlusion range, the historical state of pedestrians cannot be collected in most cases, so that autonomous vehicles cannot make effective predictions and judgments based on this. Therefore, in this case, dangerous situations such as "ghost pedestrians" are likely to occur, leading to accidents. Summary of the Invention

[0005] This application provides a safety control method, device, electronic device and storage medium for a vehicle to solve problems in related technologies where the warning system cannot obtain the pedestrian trajectory scenario in advance, so that the vehicle cannot make effective predictions and judgments based on this, resulting in traffic accidents.

[0006] An embodiment of the first aspect of the present application provides a safety control method for a vehicle, including the following steps: obtaining first state information of a current vehicle, second state information of a target vehicle, a longitudinal relative distance and a lateral relative distance between the current vehicle and the target vehicle, and determining a blind area position and a collision area of the current vehicle according to the first state information and the second state information; calculating a safety distance between the current vehicle and the collision area according to the first state information and the second state information, and determining a current blind area level of the current vehicle according to the longitudinal relative distance, the lateral relative distance and the safety distance; and generating a pedestrian prediction trajectory corresponding to the current blind area level based on a preset trajectory generation model, and inputting the pedestrian prediction trajectory corresponding to the current blind area level into a trajectory planning module of the current vehicle, so as to control the current vehicle to perform a deceleration action and / or an avoidance action according to the pedestrian prediction trajectory corresponding to the current blind area level.

[0007] According to the above technical means, by jointly considering the state information of the current vehicle and the target vehicle and performing blind area grading response, the initiative of the current vehicle planning in the target vehicle scenario can be effectively improved, and driving safety can be guaranteed.

[0008] Further, in an embodiment of the present application, the obtaining of the first state information of the current vehicle and the second state information of the target vehicle includes: obtaining a current speed and a current planned trajectory of the current vehicle, and obtaining the first state information according to the current speed and / or the current planned trajectory of the current vehicle; obtaining a current speed, a current acceleration, a length and a width of the target vehicle, and obtaining the second state information according to the current speed, the current acceleration, the length and / or the width of the target vehicle.

[0009] According to the above technical means, by obtaining relevant driving parameters of the current vehicle and the target vehicle, the driving state information during the driving process of the current vehicle and the target vehicle can be improved.

[0010] Further, in an embodiment of the present application, the determining of the blind area position and the collision area of the current vehicle according to the first state information and the second state information includes: taking the projection position of the front edge center of the target vehicle body on a preset map as the blind area position, and projecting the blind area position along the normal direction of the road onto the current planned trajectory; if the projection point is located on the current planned trajectory, taking the projection point as the collision point, otherwise, taking the point on the center line of the current lane where the target vehicle is located as the collision point; and obtaining the collision area with the collision point as the center and the width of the target vehicle as the diameter.

[0011] According to the above technical means, by determining the blind area position and the collision - prone area of the current vehicle, corresponding blind area and collision - prone area processing is performed to improve the driving safety of the user.

[0012] Further, in an embodiment of the present application, calculating the safety distance between the current vehicle and the collision - prone area according to the first state information and the second state information includes: when the target vehicle is in a stationary state, calculating the safety distance between the current vehicle and the collision - prone area based on a first safety - distance formula, where the first safety - distance formula is:

[0013]

[0014] When the target vehicle is in a moving state, calculating the safety distance between the current vehicle and the collision - prone area based on a second safety - distance formula, where the second safety - distance formula is:

[0015]

[0016] where, D s is the safety distance between the current vehicle and the collision area, v ego is the speed of the current vehicle, t s is the response time, a ego is the estimated deceleration value of the current vehicle, v bus is the current speed of the target vehicle, a bus is the current acceleration of the target vehicle.

[0017] According to the above technical means, by determining the collision - prone safety distance, the initiative of vehicle driving to the plan is improved, and driving safety is guaranteed.

[0018] Further, in an embodiment of the present application, determining the current blind - area level of the current vehicle according to the longitudinal relative distance, the lateral relative distance, and the safety distance includes: when the safety distance is greater than the longitudinal relative distance and the longitudinal relative distance is greater than a first preset value, the current blind - area level is a cautious - driving level; when the safety distance is less than the longitudinal relative distance, the current blind - area level is a keep - attention - driving level; when the longitudinal relative distance is less than or equal to the first preset value, or the lateral relative distance is greater than a second preset value, the current blind - area level is a safe - driving level.

[0019] According to the above technical means, by planning the blind - area level of the current vehicle, the initiative of vehicle driving to the plan is improved, and driving safety is guaranteed.

[0020] Further, in an embodiment of the present application, generating the pedestrian prediction trajectory corresponding to the current blind area level based on the preset trajectory generation model includes: when the current blind area level is the cautious driving level, using the blind area position as the starting point of the pedestrian prediction trajectory; translating the collisionable area along the road normal towards the target vehicle according to the width of the current vehicle, and sampling in the translated collisionable area according to the first preset sampling rule, and using the sampling points as the end points of the pedestrian prediction trajectory; based on the preset cubic polynomial trajectory generation model, generating the pedestrian prediction trajectory corresponding to the cautious driving level according to the starting point of the pedestrian prediction trajectory, the end point of the pedestrian prediction trajectory, the speed of the pedestrian at the starting point of the pedestrian prediction trajectory, and the speed of the pedestrian at the end point of the pedestrian prediction trajectory.

[0021] According to the above technical means, by predicting the pedestrian trajectories corresponding to different blind area levels, the safe driving performance of the user in the blind area direction is improved.

[0022] Further, in an embodiment of the present application, generating the pedestrian prediction trajectory corresponding to the current blind area level based on the preset trajectory generation model includes: when the current blind area level is the keep - attention driving level, using the blind area position as the starting point of the pedestrian prediction trajectory; sampling in the collisionable area according to the second preset sampling rule, and using the sampling points as the end points of the pedestrian prediction trajectory; based on the preset second - order polynomial trajectory generation model, generating the pedestrian prediction trajectory corresponding to the keep - attention driving level according to the starting point of the pedestrian prediction trajectory and the end point of the pedestrian prediction trajectory.

[0023] According to the above technical means, by predicting the pedestrian trajectories corresponding to different blind area levels, the safe driving performance of the user in the blind area direction is improved.

[0024] Further, in an embodiment of the present application, generating the pedestrian prediction trajectory corresponding to the current blind area level based on the preset trajectory generation model includes: when the current blind area level is the safe driving level, generating the pedestrian prediction trajectory corresponding to the safe driving level as empty.

[0025] According to the above technical means, by predicting the pedestrian trajectories corresponding to different blind area levels, the safe driving performance of the user in the blind area direction is improved.

[0026] Further, in an embodiment of the present application, before obtaining the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, it further includes: obtaining the current position information of the current vehicle and the position information of the markers in the preset scenario; calculating the distance between the current position information and the position information of the markers in the preset scenario, and when the distance is less than a preset distance, obtaining the first state information of the current vehicle and the second state information of the target vehicle.

[0027] According to the above technical means, by obtaining the position information of the current vehicle and the bus stop and determining the distance therebetween, the accuracy of pedestrian trajectory collection for the user is improved, thereby ensuring safe driving.

[0028] An embodiment of the second aspect of the present application provides a safety control device for a vehicle, including: an acquisition module, configured to acquire the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, and determine the blind area position and the collision area of the current vehicle according to the first state information and the second state information; a calculation module, configured to calculate the safety distance between the current vehicle and the collision area according to the first state information and the second state information, and determine the current blind area level of the current vehicle according to the longitudinal relative distance, the lateral relative distance and the safety distance; and a control module, configured to generate a pedestrian prediction trajectory corresponding to the current blind area level based on a preset trajectory generation model, and input the pedestrian prediction trajectory corresponding to the current blind area level into the trajectory planning module of the current vehicle, so as to control the current vehicle to perform a deceleration action and / or an avoidance action according to the pedestrian prediction trajectory corresponding to the current blind area level.

[0029] Further, in an embodiment of the present application, the acquisition module includes: a first acquisition unit, configured to acquire the current speed and the current planned trajectory of the current vehicle, and obtain the first state information according to the current speed and / or the current planned trajectory of the current vehicle; a second acquisition unit, configured to acquire the current speed, the current acceleration, the length and the width of the target vehicle, and obtain the second state information according to the current speed, the current acceleration, the length and / or the width of the target vehicle.

[0030] Further, in an embodiment of the present application, the obtaining module includes: a projection unit, configured to use the projection position of the center of the front edge of the target vehicle body on a preset map as the blind area position, and project the blind area position along the normal direction of the road onto the current planned trajectory; a judgment unit, configured to, if the projection point is located on the current planned trajectory, use the projection point as the collision point, otherwise, use the point on the center line of the current lane where the target vehicle is located as the collision point; a third obtaining unit, configured to obtain the collision area with the collision point as the center and the width of the target vehicle as the diameter.

[0031] Further, in an embodiment of the present application, the calculation module includes: a first calculation unit, configured to calculate the safety distance between the current vehicle and the collision area based on a first safety distance formula when the target vehicle is in a stationary state, where the first safety distance formula is:

[0032]

[0033] a second calculation unit, configured to calculate the safety distance between the current vehicle and the collision area based on a second safety distance formula when the target vehicle is in a moving state, where the second safety distance formula is:

[0034]

[0035] where D s is the safety distance between the current vehicle and the collision area, v ego is the speed of the current vehicle, t s is the response time, a ego is the estimated deceleration value of the current vehicle, v bus is the current speed of the target vehicle, a bus is the current acceleration of the target vehicle.

[0036] Further, in an embodiment of the present application, the calculation module includes: a first determination unit, configured to, when the safety distance is greater than the longitudinal relative distance and the longitudinal relative distance is greater than a first preset value, the current blind area level is the cautious driving level; a second determination unit, configured to, when the safety distance is less than the longitudinal relative distance, the current blind area level is the keep - attention driving level; a third determination unit, configured to, when the longitudinal relative distance is less than or equal to the first preset value, or the lateral relative distance is greater than a second preset value, the current blind area level is the safe driving level.

[0037] Further, in an embodiment of the present application, the control module includes: a fourth determination unit, configured to use the blind area position as the starting point of the pedestrian prediction trajectory when the current blind area level is the cautious driving level; a first sampling unit, configured to translate the collidable area along the road normal direction towards the target vehicle according to the width of the current vehicle, and sample in the translated collidable area according to a first preset sampling rule, and use the sampling points as the end points of the pedestrian prediction trajectory; a first generation unit, configured to generate the pedestrian prediction trajectory corresponding to the cautious driving level based on a preset cubic polynomial trajectory generation model according to the starting point of the pedestrian prediction trajectory, the end point of the pedestrian prediction trajectory, the speed of the pedestrian at the starting point of the pedestrian prediction trajectory, and the speed of the pedestrian at the end point of the pedestrian prediction trajectory.

[0038] Further, in an embodiment of the present application, the control module includes: a fifth determination unit, configured to use the blind area position as the starting point of the pedestrian prediction trajectory when the current blind area level is the keep - attention driving level; a second sampling unit, configured to sample in the collidable area according to a second preset sampling rule, and use the sampling points as the end points of the pedestrian prediction trajectory; a second generation unit, configured to generate the pedestrian prediction trajectory corresponding to the keep - attention driving level based on a preset second - order polynomial trajectory generation model according to the starting point of the pedestrian prediction trajectory and the end point of the pedestrian prediction trajectory.

[0039] Further, in an embodiment of the present application, the control module includes: a third generation unit, configured to generate the pedestrian prediction trajectory corresponding to the safe driving level as empty when the current blind area level is the safe driving level.

[0040] Further, in an embodiment of the present application, before obtaining the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, the obtaining module further includes: a fourth obtaining unit, configured to obtain the current position information of the current vehicle and the position information of the markers in the preset scenario; a third calculation unit, configured to calculate the distance between the current position information and the position information of the markers in the preset scenario, and obtain the first state information of the current vehicle and the second state information of the target vehicle when the distance is less than a preset distance.

[0041] An embodiment of the third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the vehicle safety control method as described in the above - mentioned embodiments.

[0042] A fourth aspect embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to implement the vehicle safety control method as described in the above embodiments.

[0043] In the embodiments of the present application, the blind area position and the collidable area of the current vehicle are determined by obtaining the first state information of the current vehicle and the second state information of the target vehicle, and the safety distance between the current vehicle and the collidable area is calculated. At the same time, the current blind area level of the current vehicle is determined based on the longitudinal relative distance, the lateral relative distance between the current vehicle and the target vehicle, and the above safety distance. Based on a preset trajectory generation model, a corresponding pedestrian prediction trajectory is generated and input into the trajectory planning module of the current vehicle, so as to control the current vehicle to execute a deceleration action and / or an avoidance action. Thus, the problems in the related art that the warning system cannot know the pedestrian trajectory scenario in advance, so that the vehicle cannot make effective predictions and judgments accordingly, resulting in traffic accidents, etc. are solved.

[0044] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0045] The above and / or additional aspects and advantages of the present application will become apparent and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0046] Figure 1 is a flowchart of a vehicle safety control method according to an embodiment of the present application;

[0047] Figure 2 is a flowchart of a blind area processing method considering an unknown pedestrian prediction trajectory in a bus stop scenario according to an embodiment of the present application;

[0048] Figure 3 is a schematic diagram of bus stop scenario parameters and blind areas according to an embodiment of the present application;

[0049] Figure 4 is a schematic diagram for generating a careful handling of the blind area and a prediction trajectory of an unknown pedestrian in the blind area that needs attention according to an embodiment of the present application;

[0050] Figure 5 is a block schematic diagram of a vehicle safety control device according to an embodiment of the present application;

[0051] Figure 6 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application.

[0052] Description of the reference numerals: 10 - vehicle safety control device; 100 - acquisition module, 200 - calculation module, 300 - control module. Specific Embodiments

[0053] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, but should not be construed as limiting the present application.

[0054] The vehicle safety control method, device, vehicle and storage medium according to the embodiments of the present application will be described below with reference to the accompanying drawings. In view of the problem in the related art mentioned in the above background art that the warning system cannot obtain the pedestrian trajectory scenario in advance, so that the vehicle cannot make effective predictions and judgments accordingly, resulting in traffic accidents, etc., the present application provides a vehicle safety control method. In this method, by obtaining the first state information of the current vehicle, the second state information of the target vehicle, the blind area position and the collision area of the current vehicle are determined, and the safety distance between the current vehicle and the collision area is calculated. At the same time, based on the obtained longitudinal relative distance, lateral relative distance between the current vehicle and the target vehicle, and the above safety distance, the current blind area level of the current vehicle is determined. Based on a preset trajectory generation model, a corresponding pedestrian prediction trajectory is generated and input into the trajectory planning module of the current vehicle, so as to control the current vehicle to perform deceleration actions and / or avoidance actions. Thereby, the problem in the related art that the warning system cannot obtain the pedestrian trajectory scenario in advance, so that the vehicle cannot make effective predictions and judgments accordingly, resulting in traffic accidents, etc. is solved. By jointly considering the state information of the vehicle and the bus under the platform and performing blind area grading response, the initiative of the autonomous vehicle planning in the bus platform scenario is improved, and driving safety is guaranteed.

[0055] Specifically, Figure 1 is a schematic flowchart of a vehicle safety control method provided by an embodiment of the present application.

[0056] As Figure 1 shown, the vehicle safety control method includes the following steps:

[0057] In step S101, obtain the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, and determine the blind area position and the collision area of the current vehicle according to the first state information and the second state information.

[0058] Specifically, the embodiments of the present application need to obtain the state information of the current vehicle and the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, and determine the blind area position and the collision area of the current vehicle.

[0059] Further, in an embodiment of the present application, before obtaining the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, it further includes: obtaining the current position information of the current vehicle and the position information of the markers in the preset scenario; calculating the distance between the current position information and the position information of the markers in the preset scenario, and when the distance is less than the preset distance, obtaining the first state information of the current vehicle and the second state information of the target vehicle.

[0060] Wherein, the preset distance can be a distance threshold set by those skilled in the art according to actual needs, or a distance threshold obtained through multiple computer simulations; the position information of the markers in the preset scenario can be the position information of markers such as bus stops, buses or trucks, etc. In the embodiment of the present application, the driving trajectory of unknown pedestrians can be predicted among any of the above markers, and no specific limitation is made here.

[0061] Specifically, as Figure 2 shown, taking the bus stop scenario as an example of the preset scenario, in the embodiment of the present application, it is first necessary to obtain the current position information P ego of the current vehicle and the bus stop position information P stop , and calculate the distance dist between the current vehicle position information and the bus stop position information. If dist = ||P stop -P ego ||2 is less than the preset bus stop range R stop , that is, ||P stop -P ego ||2 < R stop , at this time, it is considered that the current vehicle enters the bus stop, and this blind area processing method is enabled to obtain the first state information of the previous vehicle and the second state information of the target vehicle.

[0062] Further, in an embodiment of the present application, obtaining the first state information of the current vehicle and the second state information of the target vehicle includes: obtaining the current speed and the current planned trajectory of the current vehicle, and obtaining the first state information according to the current speed and / or the current planned trajectory of the current vehicle; obtaining the current speed, the current acceleration, the length and the width of the target vehicle, and obtaining the second state information according to the current speed, the current acceleration, the length and / or the width of the target vehicle.

[0063] Specifically, as Figure 2 shown, in the process of obtaining the first state information of the current vehicle and the second state information of the target vehicle in the embodiment of the present application, first, the longitudinal relative distance ΔY and the lateral relative distance ΔX between the current vehicle and the target vehicle, the current speed v ego of the current vehicle and the current planned trajectory T plan, the current speed v of the target vehicle bus , the current acceleration a bus , the length L bus and the width W bus , the current vehicle width W ego , the pedestrian walking speed v ped , and obtain the first state information of the current vehicle according to the current speed and / or the current planned trajectory of the current vehicle, and obtain the second state information of the target vehicle according to the current speed, current acceleration, length and / or width of the target vehicle. Wherein, the current vehicle can be the current autonomous vehicle, and the target vehicle can be a bus.

[0064] Further, in an embodiment of the present application, determining the blind area position and the collision area of the current vehicle according to the first state information and the second state information includes: taking the projection position of the center of the front edge of the target vehicle body on the preset map as the blind area position, and projecting the blind area position along the normal direction of the road onto the current planned trajectory; if the projection point is located on the current planned trajectory, taking the projection point as the collision point, otherwise, taking the point on the center line of the current lane where the target vehicle is currently located as the collision point; using the collision point as the center and the width of the target vehicle as the diameter to obtain the collision area.

[0065] Specifically, determine the blind area position and the collision area of the current vehicle through the first state information of the current vehicle and the second state information of the target vehicle collected above. As Figure 3 shown, assuming there are two target vehicles at the bus stop, first, taking the first target vehicle as an example, set the projection position of the center of the front edge of the first target vehicle body on the map as the blind area position P dz1 , as the starting point of the predicted trajectory of the unknown pedestrian, and then project the blind area position P dz1 along the normal direction of the road onto the current vehicle planned trajectory. If the projection point is located on the current planned trajectory, take this point on the planned trajectory as the collision point P crash1 , if the projection point is located outside the planned trajectory range, take this point on the center line of the current lane where the current vehicle is located as the collision point P crash2 ; Similarly, taking the second target vehicle as an example, set the projection position of the center of the front edge of the second target vehicle body on the map as the blind area position P dz2 , as the starting point of the predicted trajectory of the unknown pedestrian, and then project the blind area position P dz2 along the normal direction of the road onto the current vehicle planned trajectory. If the projection point is located on the current planned trajectory, take this point on the planned trajectory as the collision point P crash1 , if the projection point is located outside the planned trajectory range, take this point on the center line of the current lane where the current vehicle is located as the collision point P crash2 .

[0066] It should be noted that, due to the uncertainty of pedestrian trajectories, in the embodiments of the present application, the possible collision point can be set as the center of a circle, and the current vehicle width W ego is set as the diameter, and the resulting circular area is set as the possible collision area.

[0067] In step S102, the safety distance between the current vehicle and the possible collision area is calculated based on the first state information and the second state information, and the current blind spot level of the current vehicle is determined based on the longitudinal relative distance, the lateral relative distance, and the safety distance.

[0068] Specifically, in the embodiments of the present application, by calculating the safety distance between the current vehicle and the possible collision area and using the safety distance model as the basis for blind spot level assessment, it can effectively ensure that the vehicle does not collide with possible pedestrians.

[0069] It should be noted that the safety distance is estimated in real time dynamically based on the operating states of the current vehicle and the target vehicle and related factors, which is of great significance for the driving safety and comfort of the current vehicle. Among them, the factors affecting the safety distance estimation include the relevant parameters of the current vehicle itself and the target vehicle. Therefore, it is necessary to consider the safety distances in different motion states of the target vehicle that cause blind spots, and the following will be specifically analyzed according to specific embodiments.

[0070] Furthermore, in an embodiment of the present application, calculating the safety distance between the current vehicle and the possible collision area based on the first state information and the second state information includes: when the target vehicle is in a stationary state, calculating the safety distance between the current vehicle and the possible collision area based on the first safety distance formula, where the first safety distance formula is:

[0071]

[0072] When the target vehicle is in a moving state, calculating the safety distance between the current vehicle and the possible collision area based on the second safety distance formula, where the second safety distance formula is:

[0073]

[0074] Among them, D s is the safety distance between the current vehicle and the collision area, v ego is the speed of the current vehicle, t s is the response time, a ego is the estimated deceleration value of the current vehicle, v bus is the current speed of the target vehicle, a bus is the current acceleration of the target vehicle.

[0075] Specifically, as Figure 4The two target vehicles shown. Assume that the first target vehicle is in a stationary state and the second target vehicle is in a moving state. For the first target vehicle, since it is in a stationary state, only the current vehicle speed v needs to be considered. ego and the acceleration a ego , and calculate the safety distance between the current vehicle and the collidable area, that is, the first safety distance. The formula is as follows:

[0076]

[0077] Optionally, for the second target vehicle, according to the current vehicle speed v ego , the acceleration a ego , the target vehicle speed v bus and the acceleration a bus , calculate the safety distance between the current vehicle and the collidable area, that is, the second safety distance. The formula is as follows:

[0078]

[0079] where D s is the safety distance between the current vehicle and the collision area, t s is the response time, that is, the time consumed for the system to perform a state estimation, and a ego is the estimated value of the current vehicle deceleration.

[0080] Furthermore, in an embodiment of the present application, the current blind area level of the current vehicle is determined according to the longitudinal relative distance, the lateral relative distance, and the safety distance, including: when the safety distance is greater than the longitudinal relative distance and the longitudinal relative distance is greater than the first preset value, the current blind area level is the cautious driving level; when the safety distance is less than the longitudinal relative distance, the current blind area level is the keep - attention driving level; when the longitudinal relative distance is less than or equal to the first preset value, or the lateral relative distance is greater than the second preset value, the current blind area level is the safe driving level.

[0081] Among them, the first preset value and the second preset value can be thresholds set by those skilled in the art, or thresholds obtained through multiple computer simulations. And their preset values are different in different preset scenarios, and no specific limitations are made here.

[0082] Specifically, according to the safety distance between the current vehicle and the collision area obtained by the above calculation, when the target vehicle is in a stationary state, at this time the safety distance is greater than the longitudinal relative distance between the target vehicle and the current vehicle, that is, D s > ΔY; when the target vehicle is in a moving state, at this time the safety distance is less than the longitudinal relative distance between the target vehicle and the current vehicle, that is, D s < ΔY.

[0083] Further, in the embodiment of the present application, by determining the safety distance and the longitudinal relative distance between the target vehicle and the current vehicle, the blind area level is further delimited.

[0084] Specifically, when the safety distance is greater than the longitudinal relative distance between the target vehicle and the current vehicle and the longitudinal relative distance is greater than the first preset value (such as 0), that is, D s > ΔY > 0, at this time, this blind area is evaluated as a blind area that requires cautious driving, that is, the blind area level is the cautious driving level; when the safety distance is less than the longitudinal relative distance between the target vehicle and the current vehicle, at this time, the blind area generated by the occlusion of the target vehicle is evaluated as a blind area that requires attention, that is, the blind area level is the attention-maintaining driving level; when the longitudinal relative distance is less than or equal to the first preset value, or the lateral relative distance is greater than the second preset value (such as kR stop , k is the lateral distance coefficient), that is, ΔY ≤ 0 or ΔX > kR stop At this time, there is a sufficient lateral distance between the target vehicle and the current vehicle, so the current blind area is evaluated as an unconcerned blind area, that is, the blind area level is the safe driving level.

[0085] In step S103, based on a preset trajectory generation model, a pedestrian prediction trajectory corresponding to the current blind area level is generated, and the pedestrian prediction trajectory corresponding to the current blind area level is input into the trajectory planning module of the current vehicle, so as to control the current vehicle to perform a deceleration action and / or an avoidance action according to the pedestrian prediction trajectory corresponding to the current blind area level.

[0086] Specifically, as Figure 4 shown, in the embodiment of the present application, through the above-delimited blind area levels, hierarchical response measures are taken according to the blind area levels, and unknown pedestrian prediction trajectories are generated for different attention-level blind areas according to the following method and sent to the autonomous driving vehicle planning module, so as to achieve the active defensive driving of the current vehicle.

[0087] Further, in an embodiment of the present application, generating a pedestrian prediction trajectory corresponding to the current blind area level based on a preset trajectory generation model includes: when the current blind area level is the cautious driving level, using the blind area position as the starting point of the pedestrian prediction trajectory; translating the collisionable area along the road normal direction towards the target vehicle according to the width of the current vehicle, and sampling in the translated collisionable area according to the first preset sampling rule, and using the sampling points as the end points of the pedestrian prediction trajectory; based on a preset cubic polynomial trajectory generation model, generating a pedestrian prediction trajectory corresponding to the cautious driving level according to the starting point of the pedestrian prediction trajectory, the end point of the pedestrian prediction trajectory, the speed of the pedestrian at the starting point of the pedestrian prediction trajectory, and the speed of the pedestrian at the end point of the pedestrian prediction trajectory.

[0088] Among them, the preset trajectory generation model can be a trajectory generation model set by those skilled in the art according to different blind area levels, and no specific limitation is made here.

[0089] Specifically, as Figure 4 shown, if the current blind area level is the cautious driving level, the blind area position is used as the starting point of the predicted trajectory of the unknown pedestrian, and the collidable area is translated along the road normal direction by the width W ego of the autonomous vehicle towards the bus side, and random sampling is performed on the translated collidable area, and the sampling point is taken as the end point of the predicted trajectory. To ensure that the generated predicted trajectory is reasonable and feasible, a cubic polynomial of the path with intermediate points is used as the trajectory generation model, and the constraint conditions include the starting point of the trajectory, the end point of the trajectory, the initial speed at the starting point, and the speed at the end point. Among them, the initial speed of the pedestrian at the starting point is taken as 0, and the end speed is taken as the empirical value of the pedestrian walking speed. Thus, the predicted trajectory equation is obtained, and the discrete trajectory points between the starting point and the end point are used as the predicted trajectory of the unknown pedestrian in this blind area.

[0090] Further, in an embodiment of the present application, based on the preset trajectory generation model, generating a predicted pedestrian trajectory corresponding to the current blind area level includes: when the current blind area level is the keep - attention driving level, using the blind area position as the starting point of the predicted pedestrian trajectory; sampling in the collidable area according to the second preset sampling rule, and using the sampling point as the end point of the predicted pedestrian trajectory; based on the preset second - order polynomial trajectory generation model, generating a predicted pedestrian trajectory corresponding to the keep - attention driving level according to the starting point of the predicted pedestrian trajectory and the end point of the predicted pedestrian trajectory.

[0091] Specifically, if the current blind area level is the keep - attention driving level, taking the blind area position as the starting point of the predicted trajectory of the unknown pedestrian, the speed of the unknown pedestrian at the starting point is 0, discretizing the collidable area, and then obtaining the end point of the predicted trajectory through a random sampling algorithm among the discrete coordinate points. The constraint conditions include the starting point of the trajectory, the end point of the trajectory, and the initial speed at the starting point, and based on the second - order polynomial trajectory generation model, using its interpolation method to generate the predicted trajectory of the unknown pedestrian, and using this section of the trajectory as the predicted trajectory corresponding to this blind area that needs attention.

[0092] Further, in an embodiment of the present application, based on the preset trajectory generation model, generating a predicted pedestrian trajectory corresponding to the current blind area level includes: when the current blind area level is the safe - driving level, the generated predicted pedestrian trajectory corresponding to the safe - driving level is empty.

[0093] Specifically, if the current blind area level is the safe - driving level, the generated predicted pedestrian trajectory corresponding to the safe - driving level is empty, that is, the current vehicle is driving normally and no processing is performed.

[0094] Further, after generating the predicted trajectories of unknown pedestrians for different blind spots of different attention levels according to different methods in the embodiments of the present application, the trajectories are added to the results of the current vehicle prediction module, and the predicted pedestrian trajectories corresponding to the current blind spot level are input into the trajectory planning module of the current vehicle, so that the current vehicle actively generates defensive driving behaviors such as deceleration or avoidance.

[0095] In summary, the embodiments of the present application have the following beneficial effects:

[0096] (1) The present application can strengthen the perception and prediction ability of blind spots without adding additional hardware devices (such as autonomous vehicle perception sensors or roadside perception devices). Compared with the prediction method that needs to track historical trajectories, it is more practical in the bus stop scenario.

[0097] (2) In the bus stop scenario with mixed traffic of people and vehicles, the present application can classify the attention levels of blind spots and preset possible dangerous situations such as "ghost probes", make judgments in advance and take preventive measures actively, so as to achieve active defensive driving and improve the ability to handle sudden situations in blind spots.

[0098] According to the vehicle safety control method of the embodiments of the present application, the blind spot position and the collidable area of the current vehicle are determined by obtaining the first state information of the current vehicle and the second state information of the target vehicle, and the safety distance between the current vehicle and the collidable area is calculated. At the same time, the current blind spot level of the current vehicle is determined by obtaining the longitudinal relative distance, the lateral relative distance between the current vehicle and the target vehicle, and the above safety distance. Based on the preset trajectory generation model, the corresponding predicted pedestrian trajectory is generated and input into the trajectory planning module of the current vehicle, so as to control the current vehicle to execute deceleration actions and / or avoidance actions. Thereby, the problems in the related art that the warning system cannot obtain the pedestrian trajectory scenario in advance, so that the vehicle cannot make effective predictions and judgments accordingly, resulting in traffic accidents, etc. are solved. By jointly considering the state information of the vehicle and the bus under the platform and performing blind spot level response, the initiative of the autonomous vehicle planning in the bus stop scenario is improved, and the driving safety is ensured.

[0099] Next, a vehicle safety control device according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0100] Figure 5 It is a block diagram of a vehicle safety control device according to an embodiment of the present application.

[0101] As Figure 5 shown, the vehicle safety control device 10 includes: an acquisition module 100, a calculation module 200, and a control module 300.

[0102] Among them, the acquisition module 100 is used to acquire the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, and determine the blind area position and the collision area of the current vehicle according to the first state information and the second state information;

[0103] The calculation module 200 is used to calculate the safety distance between the current vehicle and the collision area according to the first state information and the second state information, and determine the current blind area level of the current vehicle according to the longitudinal relative distance, the lateral relative distance and the safety distance; and

[0104] The control module 300 is used to generate a pedestrian prediction trajectory corresponding to the current blind area level based on a preset trajectory generation model, and input the pedestrian prediction trajectory corresponding to the current blind area level into the trajectory planning module of the current vehicle, so as to control the current vehicle to perform a deceleration action and / or an avoidance action according to the pedestrian prediction trajectory corresponding to the current blind area level.

[0105] Further, in an embodiment of the present application, the acquisition module 100 includes: a first acquisition unit and a second acquisition unit.

[0106] Among them, the first acquisition unit is used to acquire the current speed and the current planned trajectory of the current vehicle, and obtain the first state information according to the current speed and / or the current planned trajectory of the current vehicle;

[0107] The second acquisition unit is used to acquire the current speed, the current acceleration, the length and the width of the target vehicle, and obtain the second state information according to the current speed, the current acceleration, the length and / or the width of the target vehicle.

[0108] Further, in an embodiment of the present application, the acquisition module 100 includes: a projection unit, a judgment unit and a third acquisition unit.

[0109] Among them, the projection unit is used to take the projection position of the center of the front edge of the target vehicle body on the preset map as the blind area position, and project the blind area position along the normal direction of the road onto the current planned trajectory;

[0110] The judgment unit is used to, if the projection point is located on the current planned trajectory, take the projection point as the collision point, otherwise, take the point on the center line of the lane where the target vehicle is currently located as the collision point;

[0111] The third acquisition unit is used to obtain a collision area with the collision point as the center and the width of the target vehicle as the diameter.

[0112] Further, in an embodiment of the present application, the calculation module 200 includes: a first calculation unit and a second calculation unit.

[0113] Among them, the first calculation unit is used to calculate the safety distance between the current vehicle and the collidable area based on the first safety distance formula when the target vehicle is in a stationary state. The first safety distance formula is as follows:

[0114]

[0115] The second calculation unit is used to calculate the safety distance between the current vehicle and the collidable area based on the second safety distance formula when the target vehicle is in a moving state. The second safety distance formula is as follows:

[0116]

[0117] Among them, D s is the safety distance between the current vehicle and the collision area, v ego is the speed of the current vehicle, t s is the response time, a ego is the estimated deceleration value of the current vehicle, v bus is the current speed of the target vehicle, a bus is the current acceleration of the target vehicle.

[0118] Furthermore, in an embodiment of the present application, the calculation module 200 includes: a first determination unit, a second determination unit, and a third determination unit.

[0119] Among them, the first determination unit is used to set the current blind area level to the cautious driving level when the safety distance is greater than the longitudinal relative distance and the longitudinal relative distance is greater than the first preset value;

[0120] The second determination unit is used to set the current blind area level to the keep - attention driving level when the safety distance is less than the longitudinal relative distance;

[0121] The third determination unit is used to set the current blind area level to the safe driving level when the longitudinal relative distance is less than or equal to the first preset value, or the lateral relative distance is greater than the second preset value.

[0122] Furthermore, in an embodiment of the present application, the control module 300 includes: a fourth determination unit, a first sampling unit, and a first generation unit.

[0123] Among them, the fourth determination unit is used to use the blind area position as the starting point of the pedestrian prediction trajectory when the current blind area level is the cautious driving level;

[0124] The first sampling unit is used to translate the collidable area along the road normal direction towards the target vehicle according to the width of the current vehicle, and sample in the translated collidable area according to the first preset sampling rule, and use the sampling points as the end points of the pedestrian prediction trajectory;

[0125] The first generating unit is configured to generate a predicted pedestrian trajectory corresponding to a cautious driving level based on a preset cubic polynomial trajectory generation model according to the starting point of the predicted pedestrian trajectory, the ending point of the predicted pedestrian trajectory, the speed of the pedestrian at the starting point of the predicted pedestrian trajectory, and the speed of the pedestrian at the ending point of the predicted pedestrian trajectory.

[0126] Further, in an embodiment of the present application, the control module 300 includes: a fifth determination unit, a second sampling unit, and a second generating unit.

[0127] Among them, the fifth determination unit is configured to use the blind area position as the starting point of the predicted pedestrian trajectory when the current blind area level is the pay attention driving level;

[0128] The second sampling unit is configured to sample in the collidable area according to a second preset sampling rule and use the sampling point as the ending point of the predicted pedestrian trajectory;

[0129] The second generating unit is configured to generate a predicted pedestrian trajectory corresponding to the pay attention driving level based on a preset second-order polynomial trajectory generation model according to the starting point of the predicted pedestrian trajectory and the ending point of the predicted pedestrian trajectory.

[0130] Further, in an embodiment of the present application, the control module 300 includes:

[0131] The third generating unit is configured to generate an empty predicted pedestrian trajectory corresponding to the safe driving level when the current blind area level is the safe driving level.

[0132] Further, in an embodiment of the present application, before obtaining the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, the obtaining module 100 further includes: a fourth obtaining unit and a third calculating unit.

[0133] Among them, the fourth obtaining unit is configured to obtain the current position information of the current vehicle and the position information of the markers in the preset scenario;

[0134] The third calculating unit is configured to calculate the distance between the current position information and the position information of the markers in the preset scenario, and obtain the first state information of the current vehicle and the second state information of the target vehicle when the distance is less than a preset distance.

[0135] The safety control device of a vehicle according to an embodiment of the present application determines the blind area position and the collidable area of the current vehicle by obtaining the first state information of the current vehicle and the second state information of the target vehicle, calculates the safety distance between the current vehicle and the collidable area, and determines the current blind area level of the current vehicle based on the obtained longitudinal relative distance, lateral relative distance between the current vehicle and the target vehicle, and the above-mentioned safety distance. Based on a preset trajectory generation model, a corresponding pedestrian prediction trajectory is generated and input into the trajectory planning module of the current vehicle, so as to control the current vehicle to perform a deceleration action and / or an avoidance action. Thereby, the problems in the related art that the warning system cannot know the pedestrian trajectory scenario in advance, so that the vehicle cannot make effective predictions and judgments accordingly, resulting in traffic accidents, etc. are solved. By jointly considering the state information of the vehicle and the bus under the platform and coping with blind area classification, the initiative of the autonomous vehicle planning in the bus platform scenario is improved, and the driving safety is ensured.

[0136] Figure 6 The following is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may include:

[0137] A memory 601, a processor 602, and a computer program stored on the memory 601 and executable on the processor 602.

[0138] When the processor 602 executes the program, it implements the vehicle safety control method provided in the above embodiment.

[0139] Further, the electronic device further includes:

[0140] A communication interface 603 for communication between the memory 601 and the processor 602.

[0141] The memory 601 is used to store a computer program executable on the processor 602.

[0142] The memory 601 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0143] If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the communication interface 603, the memory 601, and the processor 602 can be interconnected via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 only a thick line is used in Figure 6 , but this does not mean that there is only one bus or one type of bus.

[0144] Optionally, in a specific implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a single chip, the memory 601, the processor 602, and the communication interface 603 can communicate with each other via an internal interface.

[0145] The processor 602 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0146] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned vehicle safety control method is implemented.

[0147] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0148] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0149] Any process or method description shown in the flowchart or described otherwise herein may be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of the present application includes additional implementations in which functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0150] It should be understood that the various parts of the present application may be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art may be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays, field programmable gate arrays, etc.

[0151] Those of ordinary skill in the art of the present technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0152] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A safety control method for a vehicle, characterized in that, Including the following steps: Obtain the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, and determine the blind area position and the collision - prone area of the current vehicle according to the first state information and the second state information; Calculate the safety distance between the current vehicle and the collision - prone area according to the first state information and the second state information, and determine the current blind area level of the current vehicle according to the longitudinal relative distance, the lateral relative distance and the safety distance; And Based on a preset trajectory generation model, generate a pedestrian prediction trajectory corresponding to the current blind area level, and input the pedestrian prediction trajectory corresponding to the current blind area level into the trajectory planning module of the current vehicle, so as to control the current vehicle to perform a deceleration action and / or an avoidance action according to the pedestrian prediction trajectory corresponding to the current blind area level.

2. The method according to claim 1, characterized in that, The obtaining the first state information of the current vehicle and the second state information of the target vehicle includes: Obtain the current speed and the current planned trajectory of the current vehicle, and obtain the first state information according to the current speed and / or the current planned trajectory of the current vehicle; Obtain the current speed, the current acceleration, the length and the width of the target vehicle, and obtain the second state information according to the current speed, the current acceleration, the length and / or the width of the target vehicle.

3. The method according to claim 2, wherein The determining the blind area position and the collision - prone area of the current vehicle according to the first state information and the second state information includes: Take the projection position of the center of the front edge of the target vehicle body on a preset map as the blind area position, and project the blind area position along the normal direction of the road onto the current planned trajectory; If the projection point is located on the current planned trajectory, take the projection point as the collision - prone point, otherwise, take the point on the center line of the current lane where the target vehicle is located as the collision - prone point; Take the collision - prone point as the center and the width of the target vehicle as the diameter to obtain the collision - prone area.

4. The method according to claim 2, wherein The calculating the safety distance between the current vehicle and the collision - prone area according to the first state information and the second state information includes: When the target vehicle is in a stationary state, calculate the safety distance between the current vehicle and the collision - prone area based on a first safety distance formula, where the first safety distance formula is: When the target vehicle is in a moving state, calculate the safety distance between the current vehicle and the collision - prone area based on a second safety distance formula, where the second safety distance formula is: Among them, D s is the safety distance between the current vehicle and the collision area, v ego is the speed of the current vehicle, t s is the response time, a ego is the estimated deceleration value of the current vehicle, v bus is the current speed of the target vehicle, a bus is the current acceleration of the target vehicle.

5. The method according to claim 4, characterized in that The determining the current blind area level of the current vehicle according to the longitudinal relative distance, the lateral relative distance and the safety distance includes: When the safety distance is greater than the longitudinal relative distance and the longitudinal relative distance is greater than a first preset value, the current blind area level is the cautious driving level; When the safety distance is less than the longitudinal relative distance, the current blind area level is the keep - attention driving level; When the longitudinal relative distance is less than or equal to the first preset value, or the lateral relative distance is greater than the second preset value, the current blind zone level is the safe driving level.

6. The method according to claim 1, characterized in that Generating the pedestrian prediction trajectory corresponding to the current blind zone level based on a preset trajectory generation model includes: When the current blind zone level is the cautious driving level, using the blind zone position as the starting point of the pedestrian prediction trajectory; Translating the collidable area along the road normal direction towards the target vehicle according to the width of the current vehicle, sampling in the translated collidable area according to a first preset sampling rule, and using the sampling points as the end points of the pedestrian prediction trajectory; Based on a preset cubic polynomial trajectory generation model, generating the pedestrian prediction trajectory corresponding to the cautious driving level according to the starting point of the pedestrian prediction trajectory, the end point of the pedestrian prediction trajectory, the speed of the pedestrian at the starting point of the pedestrian prediction trajectory, and the speed of the pedestrian at the end point of the pedestrian prediction trajectory.

7. The method according to claim 1, wherein Generating the pedestrian prediction trajectory corresponding to the current blind zone level based on a preset trajectory generation model includes: When the current blind zone level is the keep - attention driving level, using the blind zone position as the starting point of the pedestrian prediction trajectory; Sampling in the collidable area according to a second preset sampling rule, and using the sampling points as the end points of the pedestrian prediction trajectory; Based on a preset second - order polynomial trajectory generation model, generating the pedestrian prediction trajectory corresponding to the keep - attention driving level according to the starting point of the pedestrian prediction trajectory and the end point of the pedestrian prediction trajectory.

8. The method according to claim 1, wherein Generating the pedestrian prediction trajectory corresponding to the current blind zone level based on a preset trajectory generation model includes: When the current blind zone level is the safe driving level, generating the pedestrian prediction trajectory corresponding to the safe driving level as empty.

9. The method according to claim 1, characterized in that, Before obtaining the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, it further includes: Obtaining the current position information of the current vehicle and the position information of the markers in the preset scenario; Calculating the distance between the current position information and the position information of the markers in the preset scenario, and when the distance is less than a preset distance, obtaining the first state information of the current vehicle and the second state information of the target vehicle.

10. A safety control device for a vehicle, characterized in that, Includes: An acquisition module, configured to acquire the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, and determine the blind zone position and the collidable area of the current vehicle according to the first state information and the second state information; A calculation module, configured to calculate the safe distance between the current vehicle and the collidable area according to the first state information and the second state information, and determine the current blind zone level of the current vehicle according to the longitudinal relative distance, the lateral relative distance and the safe distance; And The control module is used to generate a pedestrian prediction trajectory corresponding to the current blind spot level based on a preset trajectory generation model, and input the pedestrian prediction trajectory corresponding to the current blind spot level into the trajectory planning module of the current vehicle, so as to control the current vehicle to perform a deceleration action and / or an avoidance action according to the pedestrian prediction trajectory corresponding to the current blind spot level.

11. The device according to claim 10, characterized in that, The acquisition module includes: The first acquisition unit is used to acquire the current speed and current planned trajectory of the current vehicle, and obtain the first state information according to the current speed and / or current planned trajectory of the current vehicle; The second acquisition unit is used to acquire the current speed, current acceleration, length and width of the target vehicle, and obtain the second state information according to the current speed, current acceleration, length and / or width of the target vehicle.

12. The device according to claim 11, wherein The acquisition module includes: The projection unit is used to use the projection position of the front center of the target vehicle body on a preset map as the blind spot position, and project the blind spot position along the normal direction of the road onto the current planned trajectory; The judgment unit is used to, if the projection point is located on the current planned trajectory, use the projection point as the collision point, otherwise, use the point on the center line of the current lane where the target vehicle is located as the collision point; The third acquisition unit is used to obtain the collision area with the collision point as the center and the width of the target vehicle as the diameter.

13. The device according to claim 11, wherein, The calculation module includes: The first calculation unit is used to calculate the safety distance between the current vehicle and the collision area based on the first safety distance formula when the target vehicle is in a stationary state, where the first safety distance formula is: The second calculation unit is used to calculate the safety distance between the current vehicle and the collision area based on the second safety distance formula when the target vehicle is in a moving state, where the second safety distance formula is: Among them, D s is the safety distance between the current vehicle and the collision area, v ego is the current vehicle speed, t s is the response time, a ego is the estimated value of the current vehicle deceleration, v bus is the current speed of the target vehicle, a bus is the current acceleration of the target vehicle.

14. The device according to claim 13, characterized in that, The calculation module includes: The first determination unit is used to, when the safety distance is greater than the longitudinal relative distance and the longitudinal relative distance is greater than a first preset value, the current blind spot level is the cautious driving level; The second determination unit is used to, when the safety distance is less than the longitudinal relative distance, the current blind spot level is the keep - attention driving level; The third determination unit is used to, when the longitudinal relative distance is less than or equal to the first preset value, or the lateral relative distance is greater than a second preset value, the current blind spot level is the safe driving level.

15. The device according to claim 10, wherein The control module includes: The fourth determination unit is used to, when the current blind spot level is the cautious driving level, use the blind spot position as the starting point of the pedestrian prediction trajectory; The first sampling unit is used to translate the collision area along the road normal direction towards the target vehicle according to the width of the current vehicle, and sample in the translated collision area according to a first preset sampling rule, and use the sampling point as the end point of the pedestrian prediction trajectory; A first generation unit, configured to generate a predicted pedestrian trajectory corresponding to the cautious driving level based on a preset cubic polynomial trajectory generation model according to the starting point of the predicted pedestrian trajectory, the ending point of the predicted pedestrian trajectory, the speed of the pedestrian at the starting point of the predicted pedestrian trajectory, and the speed of the pedestrian at the ending point of the predicted pedestrian trajectory.

16. The device according to claim 10, wherein The control module includes: A fifth determination unit, configured to use the blind area position as the starting point of the predicted pedestrian trajectory when the current blind area level is the level of maintaining attention driving. A second sampling unit, configured to sample in the collidable area according to a second preset sampling rule, and use the sampling point as the ending point of the predicted pedestrian trajectory. A second generation unit, configured to generate a predicted pedestrian trajectory corresponding to the level of maintaining attention driving based on a preset second-order polynomial trajectory generation model according to the starting point of the predicted pedestrian trajectory and the ending point of the predicted pedestrian trajectory.

17. The device according to claim 10, characterized in that, The control module includes: A third generation unit, configured to generate an empty predicted pedestrian trajectory corresponding to the safe driving level when the current blind area level is the safe driving level.

18. The device according to claim 10, characterized in that, Before obtaining the first state information of the current vehicle, the second state information of the target vehicle, the longitudinal relative distance and the lateral relative distance between the current vehicle and the target vehicle, the obtaining module further includes: A fourth obtaining unit, configured to obtain the current position information of the current vehicle and the position information of the markers in the preset scenario. A third calculation unit, configured to calculate the distance between the current position information and the position information of the markers in the preset scenario, and obtain the first state information of the current vehicle and the second state information of the target vehicle when the distance is less than a preset distance.

19. A vehicle, characterized in that, It includes: A memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the vehicle safety control method according to any one of claims 1-9.

20. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used to implement the vehicle safety control method according to any one of claims 1-9.

Images