A vehicle control method, device, electronic equipment, and storage medium

Abstract

This application provides a vehicle control method, device, electronic device, and storage medium, comprising: when detecting at least one abnormal behavior of a preceding vehicle, determining the behavioral confidence level of the abnormal behavior; determining a potential risk area based on the motion state information and lane boundary information of the preceding vehicle at the time the abnormal behavior occurs; selecting at least one abnormal event received from an external device according to a preset selection rule, and determining the selected abnormal event as a target abnormal event; performing spatiotemporal correlation matching between the target abnormal event and the potential risk area to obtain a spatiotemporal matching degree; adjusting the behavioral confidence level based on the spatiotemporal matching degree and preset adjustment factors, and determining the adjusted behavioral confidence level as a comprehensive confidence level; and performing corresponding control on the vehicle based on the comprehensive confidence level. The technical solution provided in this application achieves proactive prediction and smooth braking before obstacle exposure, improving driving safety and comfort in obstructed scenarios.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a vehicle control method, device, electronic device, and storage medium. Background Technology

[0002] With the rapid development of autonomous driving technology, driver assistance systems such as Adaptive Cruise Control (ACC) and Automatic Emergency Braking (AEB) have been widely used in mass-produced vehicles. These systems typically rely on onboard sensors (including cameras, millimeter-wave radar, etc.) to perceive the environment ahead in real time and make following control or braking decisions based on detected target objects. In normal scenarios, these systems can effectively identify vehicles and dynamic targets ahead, enabling functions such as deceleration, stopping, and emergency braking, thereby improving driving safety.

[0003] However, in complex traffic environments, especially when obstructed by a vehicle ahead, existing systems have limited ability to perceive potential risks ahead. Specifically, in scenarios where a vehicle ahead is obstructed, when following another vehicle, the preceding vehicle may visually and radar-obstruct stationary or low-speed obstacles (such as accident vehicles, disabled vehicles, or construction areas) in front of it. This prevents the vehicle's sensors from detecting such targets in advance. When the preceding vehicle suddenly changes lanes or swerves, the obstructed obstacle is only exposed to the vehicle's sensor field of view for a very short time, resulting in a severe shortage of time for the system to identify, make decisions, and execute braking. Furthermore, existing AEB systems typically rely on the identification results of directly visible targets and lack the ability to predict potential risks in advance based on the behavior of the vehicle ahead. This makes it difficult to take effective control measures before the target is fully exposed, thus posing a high safety risk in high-speed scenarios. Summary of the Invention

[0004] In view of this, embodiments of this application provide a vehicle control method, device, electronic device, and storage medium, which realizes active prediction and smooth braking before obstacles are exposed, thereby improving driving safety and comfort in obstructed scenarios.

[0005] This application mainly includes the following aspects: In a first aspect, embodiments of this application provide a vehicle control method, the control method comprising: When the vehicle is following the vehicle in front, if at least one abnormal behavior of the vehicle in front is detected, the behavior confidence level of the abnormal behavior is determined. Based on the motion state information of the preceding vehicle at the moment of the abnormal behavior and lane boundary information, the potential risk area is determined. According to the preset selection rules, at least one abnormal event received from the external device is selected, and the selected abnormal event is determined as the target abnormal event. The spatiotemporal correlation matching between the target abnormal event and the potential risk area is performed to obtain the spatiotemporal matching degree; The behavioral confidence level is adjusted based on the spatiotemporal matching degree and preset adjustment factors, and the adjusted behavioral confidence level is determined as a comprehensive confidence level used to characterize the degree of certainty that there are obstacles in the potential risk area; Based on the comprehensive confidence level, the vehicle is controlled accordingly.

[0006] Furthermore, the confidence level of the behavior is obtained based on at least one of the following: the type of all abnormal behaviors, the type of the preceding vehicle, environmental conditions, and the relative relationship between the current vehicle and the preceding vehicle.

[0007] Furthermore, the determination of potential risk areas based on the motion state information of the preceding vehicle at the moment of the abnormal behavior and lane boundary information includes: Based on the motion state information of the preceding vehicle at the moment of the abnormal behavior, determine the longitudinal coordinates of the center point of the potential risk area; The difference between the longitudinal coordinates of the center point and the first preset distance is determined as the lower boundary of the longitudinal range, and the sum of the longitudinal coordinates of the center point and the second preset distance is determined as the upper boundary of the longitudinal range. The difference between the left boundary line of the lane where the vehicle is located and the preset lateral expansion amount is determined as the lower boundary of the lateral range, and the sum of the right boundary line of the lane where the vehicle is located and the preset lateral expansion amount is determined as the upper boundary of the lateral range. The area formed by the lower boundary of the longitudinal range, the upper boundary of the longitudinal range, the lower boundary of the lateral range, and the upper boundary of the lateral range is defined as the potential risk area.

[0008] Furthermore, determining the longitudinal coordinates of the center point of the potential risk area based on the motion state information of the preceding vehicle at the moment the abnormal behavior occurred includes: Based on the longitudinal position, longitudinal speed, longitudinal acceleration, and preset simulation time of the preceding vehicle at the moment of the abnormal behavior, determine the first longitudinal calculated coordinates of the center point of the potential risk area. Based on the longitudinal position and braking distance of the preceding vehicle at the moment the abnormal behavior occurred, determine the second longitudinal estimated coordinates of the center point of the potential risk area; The first calculated coordinate and the second calculated coordinate are weighted and summed to obtain the longitudinal coordinates of the center point of the potential risk area.

[0009] Furthermore, the step of performing spatiotemporal correlation matching between the target abnormal event and the potential risk area to obtain the spatiotemporal matching degree includes: Based on the location of the target abnormal event and the longitudinal coordinates of the center point, the longitudinal position matching degree and the lateral position matching degree corresponding to the target abnormal event are determined respectively. The comprehensive spatial matching degree is obtained by weighted summation of the vertical and horizontal position matching degrees. Based on the occurrence time of the target abnormal event and the occurrence time of the abnormal behavior of the preceding vehicle, determine the time matching degree corresponding to the target abnormal event; The spatiotemporal matching degree is obtained by weighted summation of the temporal matching degree and the comprehensive spatial matching degree.

[0010] Furthermore, the preset adjustment factors include at least one of the following: the preset range of spatiotemporal matching degree, the event type of the target abnormal event, and at least one information source of the target abnormal event.

[0011] Furthermore, the corresponding control of the vehicle based on the comprehensive confidence level includes: When the overall confidence level is greater than the overall confidence threshold, the vehicle is controlled to issue a warning and the vehicle's onboard sensors are used to obtain the perception confidence level of obstacles in the potential risk area. When the perception confidence level is within the preset perception confidence level range, the vehicle is controlled to perform pre-braking, and the perception confidence level of the vehicle's on-board sensors for obstacles in the potential risk area is acquired again. When the perceived confidence level is obtained again and is greater than the upper limit of the preset perceived confidence level range, and the collision time between the vehicle and the vehicle in front is less than the preset time threshold, the vehicle is controlled to brake.

[0012] Secondly, embodiments of this application also provide a vehicle control device, the control device comprising: The detection module is used to determine the behavioral confidence level of the abnormal behavior when the vehicle in front is detected to have at least one abnormal behavior while the vehicle is following the vehicle in front. The area determination module is used to determine the potential risk area based on the motion state information of the preceding vehicle at the moment of the abnormal behavior and the lane boundary information; The selection module is used to select at least one abnormal event received from an external device according to a preset selection rule, and to determine the selected abnormal event as the target abnormal event. The matching module is used to perform spatiotemporal correlation matching between the target abnormal event and the potential risk area to obtain the spatiotemporal matching degree; The adjustment module is used to adjust the confidence level of the behavior based on the spatiotemporal matching degree and preset adjustment factors, and to determine the adjusted confidence level of the behavior as a comprehensive confidence level that characterizes the degree of certainty that there are obstacles in the potential risk area. The control module is used to perform corresponding control on the vehicle based on the comprehensive confidence level.

[0013] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and the machine-readable instructions are executed by the processor to perform the steps of the vehicle control method described in the first aspect or any possible implementation of the first aspect.

[0014] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the vehicle control method described in the first aspect or any possible implementation of the first aspect.

[0015] This application provides a vehicle control method, device, electronic device, and storage medium. When at least one abnormal behavior of a preceding vehicle is detected, the method determines the behavioral confidence level of the abnormal behavior; based on the motion state information and lane boundary information of the preceding vehicle at the time the abnormal behavior occurs, it determines a potential risk area; according to a preset selection rule, it selects at least one abnormal event received from an external device and determines the selected abnormal event as a target abnormal event; it performs spatiotemporal correlation matching between the target abnormal event and the potential risk area to obtain a spatiotemporal matching degree; it adjusts the behavioral confidence level based on the spatiotemporal matching degree and preset adjustment factors, and determines the adjusted behavioral confidence level as a comprehensive confidence level; and it performs corresponding control on the vehicle based on the comprehensive confidence level.

[0016] This enables proactive prediction and smooth braking before obstacles are exposed, improving driving safety and comfort in obstructed scenarios.

[0017] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This application provides a flowchart of one of the vehicle control methods according to an embodiment of the present application. Figure 2 A second flowchart of a vehicle control method provided in an embodiment of this application is shown; Figure 3 A third flowchart of a vehicle control method provided in an embodiment of this application is shown; Figure 4 A flowchart of a vehicle control method provided in an embodiment of this application is shown as fourth; Figure 5 The fifth flowchart of a vehicle control method provided in this application embodiment is shown; Figure 6 This invention provides a schematic diagram of the structure of a vehicle control device according to an embodiment of the present application. Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0021] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] The methods, apparatus, electronic devices, or computer-readable storage media described in this application can be applied to any scenario requiring vehicle control. This application does not limit specific application scenarios, and any scheme using the vehicle control methods and apparatus provided in this application is within the protection scope of this application.

[0023] It is worth noting that with the rapid development of autonomous driving technology, driver assistance systems such as adaptive cruise control (ACC) and automatic emergency braking (AEB) have been widely used in mass-produced vehicles. These systems typically rely on onboard sensors (including cameras, millimeter-wave radar, etc.) to perceive the environment ahead in real time and make following control or braking decisions based on detected target objects. In normal scenarios, these systems can effectively identify vehicles and dynamic targets ahead, and realize functions such as deceleration, stopping, and emergency braking, thereby improving driving safety.

[0024] However, in complex traffic environments, especially when obstructed by a vehicle ahead, existing systems have limited ability to perceive potential risks ahead. Specifically, in scenarios where a vehicle ahead is obstructed, when following another vehicle, the preceding vehicle may visually and radar-obstruct stationary or low-speed obstacles (such as accident vehicles, disabled vehicles, or construction areas) in front of it. This prevents the vehicle's sensors from detecting such targets in advance. When the preceding vehicle suddenly changes lanes or swerves, the obstructed obstacle is only exposed to the vehicle's sensor field of view for a very short time, resulting in a severe shortage of time for the system to identify, make decisions, and execute braking. Furthermore, existing AEB systems typically rely on the identification results of directly visible targets and lack the ability to predict potential risks in advance based on the behavior of the vehicle ahead. This makes it difficult to take effective control measures before the target is fully exposed, thus posing a high safety risk in high-speed scenarios.

[0025] To address the aforementioned issues, this application proposes a vehicle control method, device, electronic equipment, and storage medium, which enables proactive prediction and smooth braking before obstacles are exposed, thereby improving driving safety and comfort in obstructed scenarios.

[0026] To facilitate understanding of this application, the technical solutions provided in this application will be described in detail below with reference to specific embodiments.

[0027] Please see Figure 1 , Figure 1 This is one of the flowcharts for a vehicle control method provided in an embodiment of this application.

[0028] like Figure 1 As shown in the figure, the vehicle control method provided in this application embodiment includes the following steps: Step S101: When the vehicle is following the vehicle in front, if at least one abnormal behavior is detected in the vehicle in front, determine the behavior confidence level of the abnormal behavior.

[0029] Here, the vehicle in front is the target vehicle that is in the same lane as this vehicle, located at the closest distance directly in front of this vehicle, and is being directly followed by this vehicle. Abnormal behavior may include, but is not limited to: abnormal deceleration, sudden deceleration, lateral movement without turn signals, and emergency lane changes. Behavioral confidence is used to characterize the credibility of the abnormal behavior of the vehicle in front.

[0030] In this embodiment, the abnormal behavior of the preceding vehicle is determined based on its motion state information. This motion state information is collected in real time by onboard sensors such as millimeter-wave radar and cameras. The motion state information includes vehicle speed, acceleration, and lateral displacement. Specifically, the behavior of the preceding vehicle is detected and judged according to preset abnormal behavior judgment conditions. For example, the abnormal deceleration judgment condition is that the deceleration exceeds the normal following threshold; the rapid deceleration judgment condition is that the deceleration exceeds the emergency threshold; the lateral deviation judgment condition without turn signals is that the lateral displacement exceeds the deviation threshold and the turn signal is not activated; and the emergency lane change judgment condition is that the lateral speed exceeds the speed threshold and the turn signal is activated.

[0031] In this embodiment of the application, when one or more abnormal behaviors of the vehicle in front are detected, the type, severity and time of occurrence of the abnormal behavior of the vehicle in front are recorded for behavior confidence calculation.

[0032] As one possible implementation, the behavioral confidence level is obtained based on at least one of the following: the type of all abnormal behaviors, the type of the preceding vehicle, environmental conditions, and the relative relationship between the current vehicle and the preceding vehicle. Preferably, firstly, a corresponding baseline confidence level is determined based on the type of each detected abnormal behavior and the severity of that type. As an example, the baseline confidence levels corresponding to the types of abnormal behaviors are shown in Table 1: Table 1. Baseline confidence levels corresponding to different types of anomalous behavior.

[0033] If multiple abnormal behaviors are detected simultaneously, a combined enhancement value is added to the sum of the base confidence scores for each abnormal behavior to obtain the combined confidence score. For example, when a single abnormal behavior is detected, no combined enhancement value is added (i.e., the combined enhancement value is 0), such as when only abnormal deceleration occurs. When two abnormal behaviors are detected simultaneously, a combined enhancement value is added to the sum of the base confidence scores; for example, when both lateral deviation without turn signals and abnormal deceleration are detected, the combined enhancement value is 0.1. Then, the combined confidence score is corrected based on the preceding vehicle type, environmental conditions, and the relative relationship between the current vehicle and the preceding vehicle, and the corrected combined confidence score is determined as the behavior confidence score. For example, the correction values ​​corresponding to the preceding vehicle type are shown in Table 2, the correction values ​​corresponding to environmental conditions are shown in Table 3, and the correction values ​​corresponding to the relative relationship between the current vehicle and the preceding vehicle are shown in Table 4.

[0034] Table 2 Correction values ​​for the preceding vehicle type

[0035] Table 3 Correction values ​​for environmental conditions

[0036] Table 4 Correction values ​​corresponding to the relative relationship between this vehicle and the vehicle in front

[0037] Step S102: Based on the motion state information of the preceding vehicle at the moment of the abnormal behavior and the lane boundary information, determine the potential risk area.

[0038] Here, lane boundary information refers to the position parameters of the left and right side boundary lines of the lane currently occupied by the vehicle in the vehicle coordinate system. The potential risk area is the spatial range in which the predicted obstacle ahead is most likely to exist.

[0039] The following is combined Figure 2 This will illustrate how to identify potential risk areas based on the motion status information of the vehicle in front and lane boundary information.

[0040] Please see Figure 2 , Figure 2 This is a second flowchart of a vehicle control method provided in an embodiment of this application.

[0041] like Figure 2 As shown, regarding step S102, in a specific implementation, as an example, the following steps may be included: Step S1021: Based on the motion state information of the preceding vehicle, determine the longitudinal coordinates of the center point of the potential risk area.

[0042] Here, the longitudinal direction refers to the direction of travel of this vehicle. Based on the motion state information of the preceding vehicle at the moment the abnormal behavior was triggered, the longitudinal coordinates of the center point of the potential risk area are calculated using two weighted methods (based on the historical trajectory of the preceding vehicle and based on braking distance prediction). The potential risk area is located ahead of the preceding vehicle's trajectory and on the extension line of this lane. The longitudinal coordinates of the center point of the potential risk area represent the location where the obstacle is most likely to exist.

[0043] The following is combined Figure 3 This will illustrate how to determine the longitudinal coordinates of the center point of a potential risk area based on the motion status information of the vehicle in front.

[0044] Please see Figure 3 , Figure 3 This is a third flowchart of a vehicle control method provided in an embodiment of this application.

[0045] like Figure 3 As shown, regarding step S1021, in a specific implementation, as an example, the following steps may be included: Step S10211: Determine the first calculated coordinates of the center point of the potential risk area based on the longitudinal position, longitudinal speed, longitudinal acceleration and preset simulation time of the preceding vehicle at the moment the abnormal behavior occurs.

[0046] Here, the preset simulation time refers to the time used for forward trajectory simulation, and its value ranges from 0.5 seconds to 1.0 seconds, increasing with the speed of the preceding vehicle. This step uses a forward simulation method based on the historical trajectory of the preceding vehicle to predict the longitudinal coordinates of the center point of the potential risk area, based on the premise that the obstacle is most likely located on the extension line of the preceding vehicle's trajectory.

[0047] As an example, the formula for calculating the first calculated coordinate can be shown in formula (1).

[0048] (1), in, The first calculated coordinate of the center point in the longitudinal direction. This represents the longitudinal position at the moment the abnormal behavior of the vehicle in front occurred. Let V be the longitudinal velocity of the vehicle ahead at the moment the abnormal behavior occurred. Let be the longitudinal acceleration at the moment the abnormal behavior of the vehicle in front occurs. The simulation time is preset.

[0049] Step S10212: Based on the longitudinal position and braking distance of the preceding vehicle at the moment the abnormal behavior occurred, determine the second longitudinal calculated coordinates of the center point of the potential risk area.

[0050] Here, braking distance is the shortest longitudinal distance required for the vehicle in front to decelerate from its current speed to a stop with maximum braking deceleration. This step uses a braking distance prediction method to predict the longitudinal coordinates of the center point of the potential risk area. The basis for this is that the vehicle in front performs emergency braking or avoidance maneuvers because its driver has perceived a hazard ahead (such as a stationary accident vehicle or a slow-moving disabled vehicle). Therefore, the obstacle is located near a position where the vehicle in front can safely brake to a stop.

[0051] As an example, the formula for calculating the second calculated coordinate can be shown in formula (2).

[0052] (2), in, The second calculated coordinate of the center point in the longitudinal direction. For example, the formula for calculating the braking distance is as shown in formula (3).

[0053] (3), in, This is the driver's reaction time (generally taken as 0.5 seconds to 1 second). The maximum braking deceleration (generally taken as 7-9 m / s²) 2 ).

[0054] Step S10213: The first calculated coordinates and the second calculated coordinates are weighted and summed to obtain the longitudinal coordinates of the center point of the potential risk area.

[0055] As an example, the longitudinal coordinates of the center point of the potential risk area can be calculated using formula (4).

[0056] (4), in, , These are the weights corresponding to the first and second estimated coordinates, respectively. Both weights are dynamically adjusted based on the type of abnormal behavior. For example, when abnormal deceleration is the primary abnormal behavior... =0.4、 =0.6; when lateral offset or lane changing is the main cause. =0.7、 =0.3.

[0057] See again Figure 2 In step S1022, the difference between the longitudinal coordinate of the center point and the first preset distance is determined as the lower boundary of the longitudinal range, and the sum of the longitudinal coordinate of the center point and the second preset distance is determined as the upper boundary of the longitudinal range.

[0058] Here, the longitudinal range refers to the longitudinal interval where obstacles may exist. The first preset distance is the distance extended from the center point towards the vehicle (rear), used to determine the lower boundary of the longitudinal range. The second preset distance is the distance extended from the center point towards the vehicle (front), used to determine the upper boundary of the longitudinal range. As an example, the longitudinal range... pass To determine, among which, The first preset distance can be 0.5 to 1.0 times the vehicle length. The second preset distance can be 1.0 to 2.0 times the vehicle length. In this application, as one possible implementation, the longitudinal range can also be adjusted in real time according to the speed of the vehicle in front and the degree of lane change. For example, the higher the speed of the vehicle in front, the larger the longitudinal range (increased uncertainty), and the more abrupt the lane change of the vehicle in front, the smaller the longitudinal range (more certain obstacle position).

[0059] Step S1023: Determine the difference between the left boundary line of the lane where the vehicle is located and the preset lateral expansion amount as the lower boundary of the lateral range, and determine the sum of the right boundary line of the lane where the vehicle is located and the preset lateral expansion amount as the upper boundary of the lateral range.

[0060] Here, the lateral range refers to the lateral interval where obstacles may exist. The preset lateral extension amount is the distance value used to extend outwards to the left and right boundaries of the lane.

[0061] As an example, horizontal range pass To determine, among which, The preset lateral expansion amount can be 0.5 to 1.0 meters. In this application, as a possible implementation, the lateral range can also be corrected according to the lateral movement state of the preceding vehicle (obvious lateral deviation or emergency lane change). Specifically, when obvious lateral deviation behavior of the preceding vehicle is detected (e.g., lateral deviation without turn signal), it indicates that there is a danger ahead in this lane, but the specific lateral position of the obstacle in the lane is not yet clear. At this time, the lateral range of the potential risk area is set to cover the full width of this lane, and continues to expand to both sides of the lane by a preset lateral expansion amount; when an emergency lane change behavior of the preceding vehicle is detected, it indicates that the obstacle is located in the original lane and the lateral position is relatively certain. At this time, the lateral range of the potential risk area is concentrated towards the center of the original lane, that is, the lateral range is appropriately reduced.

[0062] Step S1024: The area formed by the lower boundary of the longitudinal range, the upper boundary of the longitudinal range, the lower boundary of the transverse range, and the upper boundary of the transverse range is determined as the potential risk area.

[0063] See again Figure 1 In step S103, at least one abnormal event received from an external device is selected according to a preset selection rule, and the selected abnormal event is determined as the target abnormal event.

[0064] Here, the default selection rule is to select the anomaly whose location is closest to the potential risk area from all anomaly events as the target anomaly event. External devices refer to information source devices other than the vehicle itself, including roadside units, V2X communication devices of other vehicles, and cloud platform servers, used to send anomaly event information to the vehicle. The anomaly event information is a data packet sent by the external device regarding abnormal road conditions, and includes at least the event location, event type (e.g., stationary vehicle, slow traffic, construction, etc.), event timestamp (time of event occurrence or reporting), and the credibility of the information source. The credibility of the roadside unit is higher than that of the V2X communication devices of other vehicles, and the credibility of the V2X communication devices of other vehicles is higher than that of the cloud platform server. In this application, the vehicle receives anomaly event information through its own V2X communication device.

[0065] Step S104: Perform spatiotemporal correlation matching between the target abnormal event and the potential risk area to obtain the spatiotemporal matching degree.

[0066] Here, the location information of the target abnormal event is spatiotemporally correlated and matched with the potential risk area. If the match is successful, the confidence that there are obstacles in the potential risk area is significantly improved.

[0067] The following is combined Figure 4 This illustrates how to perform spatiotemporal correlation matching between target abnormal events and the potential risk areas to obtain the spatiotemporal matching degree.

[0068] Please see Figure 4 , Figure 4 This is the fourth flowchart of a vehicle control method provided in the embodiments of this application.

[0069] like Figure 4 As shown, regarding step S104, in a specific implementation, as an example, the following steps may be included: Step S1041: Based on the location of the target abnormal event and the longitudinal coordinates of the center point, determine the longitudinal position matching degree and the lateral position matching degree corresponding to the target abnormal event, respectively.

[0070] As an example, the longitudinal position matching degree can be calculated using formula (5).

[0071] (5), in, For vertical position matching degree, The x-coordinate represents the location where the target abnormal event occurred. The vertical coordinate of the center point The width is half the longitudinal extent of the potential risk area.

[0072] As an example, the lateral position matching degree can be calculated using formula (6).

[0073] (6), in, For lateral position matching degree, The vertical coordinate represents the location where the target abnormal event occurred. The horizontal coordinates of the center point of the potential risk area (usually the center of this lane). The width is half the horizontal extent of the potential risk area.

[0074] Step S1042: The longitudinal position matching degree and the lateral position matching degree are weighted and summed to obtain the comprehensive spatial matching degree.

[0075] Here, as an example, the overall spatial matching degree can be calculated using formula (7).

[0076] (7), in, To achieve a comprehensive spatial matching degree, , These represent the weights of the horizontal and vertical coordinates of the center point, respectively. When calculating the overall spatial matching degree, considering that the vertical position has a more critical impact on collision risk, a larger weight coefficient can be assigned to the vertical matching degree. For example, =0.6, =0.4.

[0077] Step S1043: Based on the occurrence time of the target abnormal event and the occurrence time of the abnormal behavior of the preceding vehicle, determine the time matching degree corresponding to the target abnormal event.

[0078] Here, as an example, the time matching degree can be calculated using formula (8).

[0079] (8), in, For time matching degree, This is the difference between the current time and the time when the abnormal behavior occurred. This is the difference between the time of occurrence of the target abnormal event and the time of occurrence of the abnormal behavior. This is the time tolerance threshold, which can be set to 2~5 seconds.

[0080] Step S1044: The time-space matching degree is obtained by weighted summation of the time matching degree and the comprehensive spatial matching degree.

[0081] Here, as an example, the spatiotemporal matching degree can be calculated using formula (9).

[0082] (9), in, For spatiotemporal matching degree, , These represent the weights for spatial and temporal matching, respectively. When calculating spatiotemporal matching, spatial matching is considered more important; therefore, a larger weight coefficient can be assigned to spatial matching. For example, =0.7, =0.3.

[0083] Step S105: Adjust the behavioral confidence level based on the spatiotemporal matching degree and preset adjustment factors, and determine the adjusted behavioral confidence level as a comprehensive confidence level used to characterize the degree of certainty that there are obstacles in the potential risk area.

[0084] Here, the preset adjustment factors include at least one of the following: a preset range within which the spatiotemporal matching degree lies, the event type of the target anomalous event, and at least one information source for the target anomalous event. Preferably, a first confidence adjustment value is determined based on the preset range within which the spatiotemporal matching degree lies; a second confidence adjustment value is determined based on the event type of the target anomalous event; the information source with the highest credibility is selected from at least one information source for the target anomalous event, and a third confidence adjustment value is determined based on the selected information source; the result of adding the first confidence adjustment value, the second confidence adjustment value, the third confidence adjustment value, and the behavioral confidence value is determined as the comprehensive confidence level used to characterize the degree of certainty that an obstacle exists in the potential risk area. As an example, the adjustment values ​​corresponding to the preset adjustment factors are shown in Table 5.

[0085] Table 5. Adjustment values ​​corresponding to preset adjustment factors

[0086] As an example, suppose an abnormal deceleration behavior of the vehicle ahead is detected, and the calculated behavior confidence is 0.7. Simultaneously, the V2X communication module receives an abnormal event message from a roadside unit, indicating the presence of a stationary accident vehicle ahead. Spatiotemporal matching calculations show that the location of this abnormal event is entirely within the potential risk area, with a time deviation of 0.9 seconds, resulting in a spatiotemporal matching degree M=0.85, which is considered a high match. According to the confidence adjustment rules, a high match corresponds to an adjustment value of +0.25, a stationary accident vehicle event type corresponds to an adjustment value of +0.05, and a roadside unit information source corresponds to an adjustment value of +0.05, for a total confidence adjustment value of 0.35. Adding the adjustment value to the behavior confidence and taking the minimum value function min() to limit the upper limit, we obtain the overall confidence value = min(1, 0.7 + 0.35) = 1.0. This result indicates that an obstacle exists within the potential risk area with 100% confidence.

[0087] It should be noted that if the spatiotemporal matching degree is 0, it means that the location of the abnormal event is not in the potential risk area, and the process returns to step S101 to re-detect whether the preceding vehicle has abnormal behavior.

[0088] In this embodiment, the following special cases need to be considered in actual application and handled according to corresponding rules: V2X information and abnormal behavior do not exist simultaneously: If the V2X communication module reports an accident or other abnormal event ahead, but the vehicle does not detect any abnormal behavior from the preceding vehicle, no confidence enhancement operation is performed, and monitoring of the preceding vehicle continues. The spatiotemporal matching process is initiated only when abnormal behavior is subsequently detected in the preceding vehicle. V2X information expires: A timestamp is recorded for each abnormal event. If the time difference between the current moment and the moment the abnormal event occurred exceeds a preset time threshold (e.g., 30 seconds), the information is considered expired and ignored, not participating in the behavior confidence adjustment calculation. The preceding vehicle's behavior and V2X information point to different locations: If the risk area location pointed to by the abnormal behavior of the preceding vehicle is inconsistent with the event location reported by the V2X information (e.g., the preceding vehicle decelerates abnormally, but the V2X-reported event is located in an adjacent lane), no behavior confidence adjustment operation is performed, and the movement status of the preceding vehicle continues to be monitored, awaiting subsequent information for further judgment.

[0089] Step S106: Based on the comprehensive confidence level, perform corresponding control on the vehicle.

[0090] Here, as Figure 5 As shown, when the overall confidence level is greater than the overall confidence level threshold, the vehicle is controlled to issue a warning (Level 1 warning), and the vehicle's onboard sensors are acquired to determine the perception confidence level of obstacles within the potential risk area. The warning operation includes issuing an audible and visual alarm to the driver and pre-filling the brake lines to reduce brake idle time. Perception confidence level is the degree of certainty by the onboard sensors that the detected target is a real obstacle. When the overall confidence level is less than or equal to the overall confidence level threshold, the process returns to step S101.

[0091] After acquiring the perception confidence level, if the perception confidence level is within a preset perception confidence level range, the vehicle is controlled to perform pre-braking (secondary pre-braking), and the perception confidence level of the vehicle's onboard sensors for obstacles in the potential risk area is acquired again. If the perception confidence level is not within the preset perception confidence level range, the comprehensive confidence level is recalculated, and it is determined whether the recalculated comprehensive confidence level is less than the comprehensive confidence level threshold. If the recalculated comprehensive confidence level is less than the comprehensive confidence level threshold, the vehicle is restored to its original state, which means the alarm is deactivated. If the recalculated comprehensive confidence level is greater than or equal to the comprehensive confidence level threshold, the vehicle is restored to its original state.

[0092] After re-acquiring the perception confidence level, if the re-acquired perception confidence level is greater than the upper limit of the preset perception confidence level range and the collision time between the vehicle and the preceding vehicle is less than a preset time threshold, the vehicle is controlled to brake (level three full braking). If the re-acquired perception confidence level is less than or equal to the upper limit of the preset perception confidence level range, the comprehensive confidence level is recalculated to determine if it is less than the comprehensive confidence level threshold. If the re-calculated comprehensive confidence level is greater than or equal to the comprehensive confidence level threshold, the process returns to the level two pre-braking step. If the re-calculated comprehensive confidence level is less than or equal to the comprehensive confidence level threshold, the vehicle is restored to its original state. If the re-acquired perception confidence level is less than or equal to the upper limit of the preset perception confidence level range and the collision time between the vehicle and the preceding vehicle is greater than or equal to the preset time threshold, the process returns to the level one warning step.

[0093] In this application, the potential risk area predicted based on the behavior of the preceding vehicle is fused with real-time obstacle information directly perceived by onboard sensors. During actions such as lane changes or lateral deviating by the preceding vehicle, if the onboard sensors can directly perceive some obstacle information, even if the confidence level of the sensor's perception of the obstacle is low due to obstruction by the preceding vehicle body, the system can still utilize this portion of perceived information to enhance the confidence level of the potential risk area. In other words, while low-confidence sensor detection results are insufficient to trigger braking alone, they can serve as an aid to further improve the certainty of the presence of obstacles within the potential risk area.

[0094] As can be seen from the above, this application implements the following three-level graded response strategy based on the comprehensive confidence level and the perceived confidence level: (1) Level 1 Warning (Risk Prediction Phase): When a potential risk area is predicted and V2X information provides partial evidence (i.e., the spatiotemporal matching degree is greater than 0), a Level 1 warning is triggered. This warning includes: issuing an audio-visual prompt to the driver (e.g., a voice announcement saying "Beware of the vehicle in front that may need to avoid an obstacle"), and pre-filling the brake lines to reduce the brake idle travel time and prepare for possible subsequent emergency braking. (2) Level 2 Preparatory Braking (Abnormal Behavior Confirmation Phase): When the vehicle in front begins to perform an emergency lane change and the obstruction is about to disappear, the system applies a preset gentle preparatory braking force (e.g., 0.2g to 0.3g) before the sensors fully identify the obstacle, so that the vehicle begins to decelerate smoothly. This phase aims to reduce the vehicle speed in advance to buy valuable time for possible full braking later, while avoiding the discomfort caused by premature and sudden braking or the risk of rear-end collisions. (3) Level 3 full braking (direct perception and confirmation stage): When the on-board sensor directly confirms that there is a stationary or slow-moving obstacle in the potential risk area and the collision time is less than the preset time threshold, the maximum braking force is immediately triggered based on the fused high confidence risk field to execute automatic emergency braking (AEB) until the vehicle stops completely or the risk is eliminated.

[0095] In this application, the graded response strategy includes a Level 1 warning, which serves as a risk alert and preparation phase to alert the driver and shorten the braking system's response time. Level 2 pre-braking intervenes when the collision risk is already high but the onboard sensors have not yet fully confirmed the obstacle, applying gentle braking force to achieve smooth deceleration and thus gain valuable reaction and deceleration time for potential subsequent emergency braking. Level 3 full braking serves as the final safety guarantee, triggering maximum braking force when the sensors directly confirm the obstacle and the collision time is below a threshold. The entire graded response process can adjust the response level or disengage braking in real time based on dynamic changes in the overall confidence level, balancing driving safety and passenger comfort.

[0096] As an example, on a highway, this vehicle is following the vehicle in front (target vehicle A) at a speed of 100 km / h. Upon receiving a vehicle malfunction warning from a roadside unit 800 meters ahead, before the malfunctioning vehicle enters the effective detection range of this vehicle's onboard sensors, when it detects that target vehicle A, without any apparent cause (such as no other visible vehicles ahead), undergoes abnormal deceleration (approximately -0.4g) accompanied by a slight, unsignaled, rightward lateral movement, suspected to be an evasive maneuver, a potential risk zone is delineated ahead of its direction of movement. This potential risk zone highly overlaps with the location of the malfunctioning vehicle in the abnormal event information, significantly increasing the overall confidence level. A tiered response is then initiated: firstly, a Level 1 warning is issued, accompanied by a voice prompt stating "There may be an obstacle ahead, please be careful," while the brake lines are pre-filled. Approximately one second later, target vehicle A suddenly activates its left turn signal and rapidly accelerates to change lanes. At the instant its body begins to move away and the obstacle behind is not fully exposed, based on the risk zone assessment, a Level 2 pre-braking of 0.25g is decisively applied, causing the vehicle's speed to decrease smoothly. Subsequently, target vehicle A completed its lane change, and a stationary, disabled vehicle partially appeared in the sensor's field of view. Although the initial visual confidence level was only 60%, due to the previously established high-risk area assessment, the system immediately triggered maximum braking force (-1.0g) to implement level three full braking, bringing the vehicle to a complete stop approximately 30 meters from the disabled vehicle. In contrast, traditional systems require waiting for the sensor's confidence level for the stationary target to reach over 95% (approximately 0.3–0.5 seconds) before initiating braking, greatly increasing the probability of a collision.

[0097] In this application, a system and method are provided for predicting, identifying, and responding robustly to stationary or slow-moving obstacles that are exposed after a vehicle suddenly changes lanes. This application has the following beneficial effects: (1) Shift from passive reaction to early prediction: This application uses the indirect signal of abnormal behavior of the vehicle in front to predict risks in advance before the vehicle's sensors directly perceive the obstacle, thus providing critical reaction time and significantly improving driving safety. (2) Multi-source information collaboration: This application integrates three layers of information: kinematic analysis based on the behavior of the vehicle in front, V2X event notification, and direct sensor perception, which greatly improves the robustness and reliability of the system in complex scenarios and effectively reduces false triggering. (3) Smooth graded response: This application achieves a smooth, timely, and human-expected braking process through a three-level response mechanism of "early warning - pre-braking - full braking", avoiding collisions caused by braking too late, as well as discomfort and the risk of rear-end collisions caused by braking too early or too suddenly. (4) Compatibility and practicality: It can be implemented through software upgrades based on existing sensors and V2X hardware, and is especially suitable for L2+ and L3 advanced driver assistance systems, which can significantly improve their safety limit in high-speed scenarios.

[0098] This application provides a vehicle control method that enables proactive prediction and smooth braking before obstacles are exposed, thereby improving driving safety and comfort in obstructed scenarios.

[0099] Based on the same application concept, this application also provides a vehicle control device corresponding to the vehicle control method provided in the above embodiments. Since the principle of the device in this application to solve the problem is similar to the vehicle control method in the above embodiments of this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0100] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this application.

[0101] like Figure 6 As shown in the illustration, the vehicle control device 610 provided in this application embodiment includes: The detection module 611 is used to determine the behavior confidence level of the abnormal behavior when the vehicle in front is detected to have at least one abnormal behavior while the vehicle is following the vehicle in front. The area determination module 612 is used to determine the potential risk area based on the motion state information of the preceding vehicle at the moment of the abnormal behavior and the lane boundary information; The selection module 613 is used to select at least one abnormal event received from an external device according to a preset selection rule, and to determine the selected abnormal event as the target abnormal event. Matching module 614 is used to perform spatiotemporal correlation matching between the target abnormal event and the potential risk area to obtain the spatiotemporal matching degree; The adjustment module 615 is used to adjust the behavior confidence based on the spatiotemporal matching degree and preset adjustment factors, and to determine the adjusted behavior confidence as a comprehensive confidence level that characterizes the degree of certainty that there are obstacles in the potential risk area. The control module 616 is used to perform corresponding control on the vehicle based on the comprehensive confidence level.

[0102] Furthermore, the confidence level of the behavior is obtained based on at least one of the following: the type of all abnormal behaviors, the type of the preceding vehicle, environmental conditions, and the relative relationship between the current vehicle and the preceding vehicle.

[0103] Furthermore, the region determination module 612 is specifically used for: Based on the motion state information of the preceding vehicle at the moment of the abnormal behavior, determine the longitudinal coordinates of the center point of the potential risk area; The difference between the longitudinal coordinates of the center point and the first preset distance is determined as the lower boundary of the longitudinal range, and the sum of the longitudinal coordinates of the center point and the second preset distance is determined as the upper boundary of the longitudinal range. The difference between the left boundary line of the lane where the vehicle is located and the preset lateral expansion amount is determined as the lower boundary of the lateral range, and the sum of the right boundary line of the lane where the vehicle is located and the preset lateral expansion amount is determined as the upper boundary of the lateral range. The area formed by the lower boundary of the longitudinal range, the upper boundary of the longitudinal range, the lower boundary of the lateral range, and the upper boundary of the lateral range is defined as the potential risk area.

[0104] Furthermore, when the region determination module 612 determines the longitudinal coordinates of the center point of the potential risk region based on the motion state information of the preceding vehicle at the moment of the abnormal behavior, it is also specifically used for: Based on the longitudinal position, longitudinal speed, longitudinal acceleration, and preset simulation time of the preceding vehicle at the moment of the abnormal behavior, determine the first longitudinal calculated coordinates of the center point of the potential risk area. Based on the longitudinal position and braking distance of the preceding vehicle at the moment the abnormal behavior occurred, determine the second longitudinal estimated coordinates of the center point of the potential risk area; The first calculated coordinate and the second calculated coordinate are weighted and summed to obtain the longitudinal coordinates of the center point of the potential risk area.

[0105] Furthermore, the matching module 614 is specifically used for: Based on the location of the target abnormal event and the longitudinal coordinates of the center point, the longitudinal position matching degree and the lateral position matching degree corresponding to the target abnormal event are determined respectively. The comprehensive spatial matching degree is obtained by weighted summation of the vertical and horizontal position matching degrees. Based on the occurrence time of the target abnormal event and the occurrence time of the abnormal behavior of the preceding vehicle, determine the time matching degree corresponding to the target abnormal event; The spatiotemporal matching degree is obtained by weighted summation of the temporal matching degree and the comprehensive spatial matching degree.

[0106] Furthermore, the preset adjustment factors include at least one of the following: the preset range of spatiotemporal matching degree, the event type of the target abnormal event, and at least one information source of the target abnormal event.

[0107] Furthermore, the control module 616 is specifically used for: When the overall confidence level is greater than the overall confidence threshold, the vehicle is controlled to issue a warning and the vehicle's onboard sensors are used to obtain the perception confidence level of obstacles in the potential risk area. When the perception confidence level is within the preset perception confidence level range, the vehicle is controlled to perform pre-braking, and the perception confidence level of the vehicle's on-board sensors for obstacles in the potential risk area is acquired again. When the perceived confidence level is obtained again and is greater than the upper limit of the preset perceived confidence level range, and the collision time between the vehicle and the vehicle in front is less than the preset time threshold, the vehicle is controlled to brake.

[0108] This application provides a vehicle control device that enables proactive prediction and smooth braking before obstacles are exposed, thereby improving driving safety and comfort in obstructed scenarios.

[0109] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0110] like Figure 7 As shown, the electronic device 700 includes a processor 710, a memory 720, and a bus 730.

[0111] The memory 720 stores machine-readable instructions executable by the processor 710. When the electronic device 700 is running, the processor 710 communicates with the memory 720 via the bus 730. When the machine-readable instructions are executed by the processor 710, they can perform the operations described above. Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5 The steps of the vehicle control method in the illustrated method embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.

[0112] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figure 1 , Figure 2 , Figure 3 , Figure 4 and Figure 5 The steps of the vehicle control method in the illustrated method embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.

[0113] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0116] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for controlling a vehicle, characterized in that, The control method includes: When the vehicle is following the vehicle in front, if at least one abnormal behavior of the vehicle in front is detected, the behavior confidence level of the abnormal behavior is determined. Based on the motion state information of the preceding vehicle at the moment of the abnormal behavior and lane boundary information, the potential risk area is determined. According to the preset selection rules, at least one abnormal event received from the external device is selected, and the selected abnormal event is determined as the target abnormal event. The spatiotemporal correlation matching between the target abnormal event and the potential risk area is performed to obtain the spatiotemporal matching degree; The behavioral confidence level is adjusted based on the spatiotemporal matching degree and preset adjustment factors, and the adjusted behavioral confidence level is determined as a comprehensive confidence level used to characterize the degree of certainty that there are obstacles in the potential risk area; Based on the comprehensive confidence level, the vehicle is controlled accordingly.

2. The vehicle control method according to claim 1, characterized in that, The confidence level of the behavior is obtained based on at least one of the following: the type of all abnormal behaviors, the type of the preceding vehicle, environmental conditions, and the relative relationship between the current vehicle and the preceding vehicle.

3. The vehicle control method according to claim 1, characterized in that, The determination of potential risk areas based on the motion state information of the preceding vehicle at the moment of the abnormal behavior and lane boundary information includes: Based on the motion state information of the preceding vehicle at the moment of the abnormal behavior, determine the longitudinal coordinates of the center point of the potential risk area; The difference between the longitudinal coordinates of the center point and the first preset distance is determined as the lower boundary of the longitudinal range, and the sum of the longitudinal coordinates of the center point and the second preset distance is determined as the upper boundary of the longitudinal range. The difference between the left boundary line of the lane where the vehicle is located and the preset lateral expansion amount is determined as the lower boundary of the lateral range, and the sum of the right boundary line of the lane where the vehicle is located and the preset lateral expansion amount is determined as the upper boundary of the lateral range. The area formed by the lower boundary of the longitudinal range, the upper boundary of the longitudinal range, the lower boundary of the lateral range, and the upper boundary of the lateral range is defined as the potential risk area.

4. The vehicle control method according to claim 3, characterized in that, The determination of the longitudinal coordinates of the center point of the potential risk area based on the motion state information of the preceding vehicle at the moment of the abnormal behavior includes: Based on the longitudinal position, longitudinal speed, longitudinal acceleration, and preset simulation time of the preceding vehicle at the moment of the abnormal behavior, determine the first longitudinal calculated coordinates of the center point of the potential risk area. Based on the longitudinal position and braking distance of the preceding vehicle at the moment the abnormal behavior occurred, determine the second longitudinal estimated coordinates of the center point of the potential risk area; The first calculated coordinate and the second calculated coordinate are weighted and summed to obtain the longitudinal coordinates of the center point of the potential risk area.

5. The vehicle control method according to claim 1, characterized in that, The step of performing spatiotemporal correlation matching between the target abnormal event and the potential risk area to obtain the spatiotemporal matching degree includes: Based on the location of the target abnormal event and the longitudinal coordinates of the center point, the longitudinal position matching degree and the lateral position matching degree corresponding to the target abnormal event are determined respectively. The comprehensive spatial matching degree is obtained by weighted summation of the vertical and horizontal position matching degrees. Based on the occurrence time of the target abnormal event and the occurrence time of the abnormal behavior of the preceding vehicle, determine the time matching degree corresponding to the target abnormal event; The spatiotemporal matching degree is obtained by weighted summation of the temporal matching degree and the comprehensive spatial matching degree.

6. The vehicle control method according to claim 1, characterized in that, The preset adjustment factors include at least one of the following: the preset range of spatiotemporal matching degree, the event type of the target abnormal event, and at least one information source of the target abnormal event.

7. The vehicle control method according to claim 1, characterized in that, The control of the vehicle based on the comprehensive confidence level includes: When the overall confidence level is greater than the overall confidence threshold, the vehicle is controlled to issue a warning and the vehicle's onboard sensors are used to obtain the perception confidence level of obstacles in the potential risk area. When the perception confidence level is within the preset perception confidence level range, the vehicle is controlled to perform pre-braking, and the perception confidence level of the vehicle's on-board sensors for obstacles in the potential risk area is acquired again. When the perceived confidence level is obtained again and is greater than the upper limit of the preset perceived confidence level range, and the collision time between the vehicle and the vehicle in front is less than the preset time threshold, the vehicle is controlled to brake.

8. A vehicle control device, characterized in that, The control device includes: The detection module is used to determine the behavioral confidence level of the abnormal behavior when the vehicle in front is detected to have at least one abnormal behavior while the vehicle is following the vehicle in front. The area determination module is used to determine the potential risk area based on the motion state information of the preceding vehicle at the moment of the abnormal behavior and the lane boundary information; The selection module is used to select at least one abnormal event received from an external device according to a preset selection rule, and to determine the selected abnormal event as the target abnormal event. The matching module is used to perform spatiotemporal correlation matching between the target abnormal event and the potential risk area to obtain the spatiotemporal matching degree; The adjustment module is used to adjust the confidence level of the behavior based on the spatiotemporal matching degree and preset adjustment factors, and to determine the adjusted confidence level of the behavior as a comprehensive confidence level that characterizes the degree of certainty that there are obstacles in the potential risk area. The control module is used to perform corresponding control on the vehicle based on the comprehensive confidence level.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. The machine-readable instructions are executed by the processor to perform the steps of the vehicle control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the vehicle control method as described in any one of claims 1 to 7.

Images