Vehicle control method and device, vehicle and storage medium

Abstract

The application discloses a vehicle control method and device, a vehicle and a storage medium, and belongs to the field of automobile control. The method comprises the following steps: acquiring an environment video around a first vehicle and radar sensing information of the first vehicle, wherein the environment video and the radar sensing information are used for representing the surrounding environment of the first vehicle; determining whether the first vehicle has driving danger based on at least one of the environment video and the radar sensing information; and controlling at least one of the speed and the steering of the first vehicle in the case that the first vehicle has driving danger. Through the perception of the surrounding environment of the first vehicle, it can be accurately determined whether the first vehicle has dangerous driving. In the case that it is determined that the first vehicle has driving danger, at least one of the speed and the steering of the first vehicle is accurately controlled according to different dangerous situations, so that the first vehicle is kept away from danger, thereby effectively reducing the accident rate.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automobile control, and in particular to a vehicle control method and device, a vehicle, and a storage medium. BACKGROUND

[0002] With the increase in the number of vehicles and the gradual expansion of urban transportation networks, drivers often encounter complex traffic situations during driving, which leads to frequent traffic accidents and thus poses a great threat to the personal and property safety of drivers. In addition, with the continuous development of intelligent vehicles, users' requirements for driving safety are also increasing, and vehicles also need to break through their own limitations as a means of transportation in order to meet the increasing functional needs of drivers. Therefore, how to control vehicles to meet the needs of users as much as possible has become a problem to be solved at present. SUMMARY

[0003] The embodiments of the present application provide a vehicle control method and device, a vehicle, and a storage medium, which can solve the problem that related technologies cannot accurately control vehicles in real time according to the environment of the vehicles and help vehicles to avoid danger. The technical solution is as follows:

[0004] In one aspect, a vehicle control method is provided, applied to a first vehicle, and the method comprises:

[0005] Obtaining an environment video around the first vehicle and radar perception information of the first vehicle, the environment video and the radar perception information being used to represent the surrounding environment of the first vehicle;

[0006] Determining whether the first vehicle has a driving risk based on at least one of the environment video and the radar perception information;

[0007] Controlling at least one of the speed and the steering of the first vehicle in the case that the first vehicle has a driving risk.

[0008] Optionally, the determining whether the first vehicle has a driving risk based on at least one of the environment video and the radar perception information comprises:

[0009] Determining a target object based on the environment video, the target object being a potential risk object around the first vehicle;

[0010] Obtaining the relative position and the relative speed of the target object and the first vehicle from the radar perception information;

[0011] Determining the relative collision time of the target object and the first vehicle based on the relative position and the relative speed of the target object and the first vehicle;

[0012] determine that the first vehicle has a driving danger if the relative collision time is lower than a collision time threshold.

[0013] Optionally, the determining the target object based on the environment video comprises:

[0014] Optionally, the determining the target object based on the environment video comprises:

[0015] Optionally, the determining the target object based on the environment video comprises:

[0016] Optionally, the determining the target object based on the environment video comprises:

[0017] Optionally, the determining the target object based on the environment video comprises:

[0018] Optionally, the determining the target object based on the environment video comprises:

[0019] Optionally, the determining the target object based on the environment video comprises:

[0020] Optionally, the determining the target object based on the environment video comprises:

[0021] Optionally, the determining the target object based on the environment video comprises:

[0022] Optionally, the method further comprises:

[0023] Optionally, the method further comprises:

[0024] Optionally, the method further comprises:

[0025] Optionally, the determining whether the first vehicle has a driving danger based on at least one of the environment video and the radar sensing information comprises:

[0026] Analyzing the environmental video to determine a position of a first central axis and a position of a second central axis, where the first central axis is the central axis of the first vehicle and the second central axis is the central axis of a lane in which the first vehicle is located;

[0027] determining an angle between the first central axis and the second central axis based on a position of the first central axis and a position of the second central axis;

[0028] When the angle between the first central axis and the second central axis exceeds an angle threshold, it is determined that there is a driving risk for the first vehicle.

[0029] In another aspect, a vehicle control device is provided, the device comprising:

[0030] an acquisition module, configured to acquire an environment video surrounding the first vehicle and radar perception information of the first vehicle, wherein the environment video and the radar perception information are used to represent the environment surrounding the first vehicle;

[0031] a determination module, configured to determine whether the first vehicle is in a driving danger based on at least one of the environmental video and the radar perception information;

[0032] The control module is configured to control at least one of a speed and a steering direction of the first vehicle when the first vehicle is in danger of driving.

[0033] Optionally, the determining module includes:

[0034] a first determining unit, configured to determine a target object based on the environmental video, wherein the target object refers to a potential risk object around the first vehicle;

[0035] an acquiring unit, configured to acquire the relative position and relative speed of the target object and the first vehicle from the radar sensing information;

[0036] a second determining unit, configured to determine a relative collision time between the target object and the first vehicle based on a relative position and a relative speed between the target object and the first vehicle;

[0037] The third determining unit is configured to determine that the first vehicle is in a driving danger when the relative collision time is lower than a collision time threshold.

[0038] Optionally, the first determining unit is specifically configured to:

[0039] Identify the environmental video to determine the motion trajectory of the moving object in the environmental video;

[0040] If it is determined that the moving object has a behavior of crossing a road based on the motion trajectory, the moving object is determined as the target object.

[0041] Optionally, the first determining unit is specifically configured to:

[0042] identify the environment video to determine a driving trajectory of a second vehicle driving on a neighboring lane of the first vehicle;

[0043] If it is determined that a driving direction of the second vehicle deviates and is towards the lane where the first vehicle is located based on the driving trajectory, the second vehicle is determined as the target object.

[0044] Optionally, the first determining unit is specifically configured to:

[0045] identify the environment video to determine whether a target lane where the first vehicle drives after a lane changing operation has a vehicle driving thereon, the target lane being a lane where the first vehicle drives after the lane changing operation;

[0046] If the target lane has a vehicle driving thereon, a third vehicle is determined as the target object, the third vehicle being a vehicle driving on the target lane.

[0047] Optionally, the apparatus further includes:

[0048] an alarm module configured to trigger an alarm information, the alarm information being used to prompt that the first vehicle has a collision risk;

[0049] a triggering module configured to trigger the control module to control at least one of a speed and a steering of the first vehicle if it is detected that a steering wheel angle of the first vehicle exceeds an angle threshold and a yaw angle of the first vehicle exceeds a yaw angle threshold after the alarm information is triggered.

[0050] Optionally, the determining module includes:

[0051] a fourth determining unit configured to analyze the environment video to determine a position of a first center axis and a position of a second center axis, the first center axis being a center axis of the first vehicle, and the second center axis being a center axis of a lane where the first vehicle is located;

[0052] a fifth determining unit configured to determine an included angle between the first center axis and the second center axis based on the position of the first center axis and the position of the second center axis;

[0053] a sixth determining unit configured to determine that the first vehicle has a driving risk if the included angle between the first center axis and the second center axis exceeds an included angle threshold.

[0054] On the other hand, a vehicle is provided, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of the vehicle control method described above.

[0055] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.

[0056] On the other hand, a computer program product comprising instructions is provided. When the instructions are executed on a computer, the computer is caused to perform the steps of the vehicle control method described above.

[0057] The technical solutions provided in the embodiments of the present application can at least bring the following beneficial effects:

[0058] Because the first vehicle faces different dangerous situations in different scenarios during driving, the system can accurately determine whether the first vehicle is driving in a dangerous manner by sensing the first vehicle's surroundings. If it is determined that the first vehicle is driving in a dangerous manner, at least one of the first vehicle's speed and steering is precisely controlled according to the different dangerous situations, thereby moving the first vehicle away from the danger and effectively reducing the accident rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0060] Figure 1 is a flow chart of a vehicle control method provided by an embodiment of the present application;

[0061] Figure 2 is a schematic diagram of a collision time calculation method provided in an embodiment of the present application;

[0062] Figure 3 is a schematic diagram of another collision time calculation method provided in an embodiment of the present application;

[0063] Figure 4 is a schematic diagram of a vehicle control method provided in an embodiment of the present application;

[0064] Figure 5 This is a schematic structural diagram of a vehicle control device provided in an embodiment of the present application;

[0065] Figure 6 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0067] Before explaining in detail the vehicle control method provided in the embodiment of the present application, the application scenarios involved in the embodiment of the present application are first introduced.

[0068] During driving, complex traffic situations such as ghost heads and running red lights emerge in an endless stream, and drivers may also engage in dangerous driving due to wrong judgments, distractions and other reasons. Therefore, this places extremely high demands and challenges on the driver's driving skills, concentration and reaction ability. With the development of intelligent assisted driving technology, people have more expectations for the safety performance of vehicles. Using a variety of sensors, cameras and other equipment to monitor the driving environment in real time can not only monitor the situation within the driver's line of sight, but also monitor blind spots and other situations that the driver has not noticed, and accurately control dangerous situations. The vehicle control method provided in the embodiment of the present application can help the driver collect as much information as possible and accurately control the direction of the vehicle, helping them to drive safely and avoid risks to the greatest extent, and effectively reduce the accident rate.

[0069] Next, the vehicle control method provided in the embodiment of the present application is explained in detail.

[0070] Figure 1 This is a flow chart of a vehicle control method provided in an embodiment of the present application, which is applied to a first vehicle. Figure 1 As shown, the method includes the following steps.

[0071] Step 101: Obtain an environmental video of a first vehicle's surroundings and radar perception information of the first vehicle, where the environmental video and the radar perception information are used to characterize the surroundings of the first vehicle.

[0072] The first vehicle is equipped with a camera and a radar. The camera can collect information about the surrounding environment of the first vehicle and obtain an environmental video about the first vehicle. The radar can sense the environment around the first vehicle and obtain radar sensing information of the first vehicle.

[0073] The radar perception information of the first vehicle may include the relative position and relative speed between the first vehicle and surrounding objects. Of course, it may also include other information, which is not limited in this embodiment of the present application.

[0074] Among them, the relative position between the first vehicle and the surrounding objects includes the relative distance and the relative angle. Taking the target object as an example, the relative distance between the first vehicle and the target object refers to the straight-line distance between the first vehicle and the target object, the relative speed between the first vehicle and the target object refers to the speed difference between the first vehicle and the target object in the same direction, and the relative angle between the first vehicle and the target object refers to the angle value of the target object's position relative to the first vehicle.

[0075] Typically, the camera is used to capture the field of view in the direction of travel of the first vehicle. For example, when the first vehicle is traveling forward, the camera is used to capture the field of view in front of the first vehicle. Of course, in some cases, the camera can also capture the field of view in the opposite direction of travel of the first vehicle. For example, when the first vehicle is traveling forward, the camera is used to capture the field of view behind the first vehicle. The camera can be a monocular camera, a binocular camera, an infrared night vision camera, etc. In some cases, a monocular camera is also called a monocular vision sensor, a binocular camera is also called a binocular vision sensor, and an infrared night vision camera is also called an infrared night vision sensor. The radar can be a microwave radar, an ultrasonic radar, a millimeter-wave radar, a lidar, etc.

[0076] Step 102: Determine whether the first vehicle is in danger of driving based on at least one of the environmental video and the radar perception information.

[0077] There are multiple ways to determine whether the first vehicle is in a driving hazard based on at least one of the environmental video and the radar perception information, two of which are introduced below.

[0078] In the first implementation, a target object is identified based on the surrounding video. The target object refers to a potential risk object around the first vehicle. The relative position and relative velocity of the target object and the first vehicle are obtained from radar perception information. Based on the relative position and relative velocity of the target object and the first vehicle, a relative collision time between the target object and the first vehicle is determined. If the relative collision time is lower than a collision time threshold, the first vehicle is determined to be in a driving hazard.

[0079] Specifically, the system determines whether a target object exists around the first vehicle based on the surrounding video. If a target object exists around the first vehicle, the radar sensing information is used to determine the relative position and velocity of the target object relative to the first vehicle. Then, based on the relative position and velocity of the target object and the first vehicle, the relative collision time between the target object and the first vehicle is determined. If this relative collision time is lower than a collision time threshold, it indicates a collision risk between the first vehicle and the target object, and the first vehicle can be determined to be in a driving danger.

[0080] In the case that there is no target object around the first vehicle, or in the case that there is a target object around the first vehicle but the relative collision time of the target object and the first vehicle exceeds the collision time threshold, it indicates that there is no collision risk between the first vehicle and the target object, and at this time, it can be determined that the first vehicle is not in driving danger.

[0081] In some embodiments, the relative collision time of the target object and the first vehicle being below the collision time threshold can be understood as that the relative collision time of the target object and the first vehicle is less than or equal to the collision time threshold, and the relative collision time of the target object and the first vehicle exceeding the collision time threshold can be understood as that the relative collision time of the target object and the first vehicle is greater than the collision time threshold.

[0082] In other embodiments, the relative collision time of the target object and the first vehicle being below the collision time threshold can be understood as that the relative collision time of the target object and the first vehicle is less than the collision time threshold, and the relative collision time of the target object and the first vehicle exceeding the collision time threshold can be understood as that the relative collision time of the target object and the first vehicle is greater than or equal to the collision time threshold.

[0083] That is, in the embodiments of the present application, “exceeding” can be understood as greater than, and can also be understood as greater than or equal to. In the case that “exceeding” is understood as greater than, “below” can be understood as less than or equal to. In the case that “exceeding” is understood as greater than or equal to, “below” can be understood as less than. The “exceeding” and “below” involved later can be referred to the above explanation.

[0084] Based on the above description, the relative position includes the relative distance and the relative angle, and at this time, based on the relative position and the relative speed of the target object and the first vehicle, the implementation process of determining the relative collision time of the target object and the first vehicle includes: based on the relative distance and the relative angle of the target object and the first vehicle, determining the relative distance of the target object and the first vehicle in the driving direction of the first vehicle according to a relevant algorithm. Based on the relative speed of the target object and the first vehicle, determining the relative speed of the target object and the first vehicle in the driving direction of the first vehicle according to a relevant algorithm. Dividing the relative distance of the target object and the first vehicle in the driving direction of the first vehicle by the relative speed of the target object and the first vehicle in the driving direction of the first vehicle to obtain the relative collision time of the target object and the first vehicle.

[0085] For example, please refer to Figure 2, the target object is a pedestrian, the first vehicle is located at point A, the target object is located at point C, the driving direction of the first vehicle is from point A to point B, and the motion trajectory of the target object is from point C to point B. Among them, the relative distance AC between the target object and the first vehicle is 3m (meters), and the relative angle between the target object and the first vehicle is 60°. Based on the relative distance and relative angle between the target object and the first vehicle, the relative distance AB between the target object and the first vehicle in the driving direction of the first vehicle is determined to be 3×sin60°=1.5×√3. Assuming that the relative speed of the target object and the first vehicle in the driving direction of the first vehicle is 2m / s (meters per second), the relative distance between the target object and the first vehicle in the driving direction of the first vehicle is divided by the relative speed between the target object and the first vehicle in the driving direction of the first vehicle to obtain a relative collision time between the target object and the first vehicle of approximately 1.299s.

[0086] For example, please refer to Figure 3 The target object is another vehicle. The first vehicle is located at point A, and the target object is located at point C. The first vehicle is traveling from point A to point B, and the target object's trajectory is from point C to point B. The relative distance AC between the target object and the first vehicle is 3×√2m, and the relative angle between the target object and the first vehicle is 45°. Assuming that the angle between the target object's trajectory and the first vehicle's direction of travel is 45° according to the relevant algorithm, AD and BD can be calculated to be 3m and 3m, respectively. Furthermore, the relative distance AB between the target object and the first vehicle in the direction of travel can be calculated to be 6m. Assuming that the relative speed between the target object and the first vehicle in the direction of travel is 4m / s, the relative distance between the target object and the first vehicle in the direction of travel is divided by the relative speed between the target object and the first vehicle in the direction of travel to obtain a relative collision time of approximately 1.5s between the target object and the first vehicle.

[0087] There are various ways to determine the target object based on the surrounding video, such as using the YOLO (You Only Look Once) algorithm to detect the target object. The target object can be a pedestrian, an animal, a vehicle, etc. The collision time threshold is pre-set and determined based on the driver's reaction time, driving habits, etc., and can be adjusted in different situations.

[0088] The target objects vary in different scenarios. The following sections introduce several different scenarios.

[0089] Scenario 1: Identify the environment video to determine the motion trajectory of the moving object in the environment video. If the moving object is determined to be crossing the road based on the motion trajectory, the moving object is determined to be the target object.

[0090] In other words, scenario 1 identifies moving objects that cross the road as target objects. To do this, the first vehicle needs to identify moving objects in the surrounding video and determine the motion trajectory of each moving object. Based on the motion trajectory of each moving object, it determines whether any of these moving objects are crossing the road, and then identifies these moving objects that are crossing the road as target objects. In other words, these moving objects that are crossing the road are identified as potential risk objects around the first vehicle.

[0091] In some embodiments, the first vehicle identifies moving objects in each frame of the environment video to determine the position of each moving object in each frame. The position of each moving object in multiple frames is then spliced ​​together to determine the motion trajectory of each moving object. For example, the position of a moving object in 30 frames of video preceding the current moment is spliced ​​together to obtain the motion trajectory of the moving object.

[0092] After determining the motion trajectory of the mobile object, it can be determined whether the angle between the motion trajectory of the mobile object and the driving direction of the first vehicle is within a first reference angle range. If the angle between the motion trajectory of the mobile object and the driving direction of the first vehicle is within the first reference angle range, it is determined that the mobile object has crossed the road. If the angle between the motion trajectory of the mobile object and the driving direction of the first vehicle is not within the first reference angle range, it is determined that the mobile object has not crossed the road.

[0093] It should be noted that the first reference angle range is pre-set and can be adjusted according to different needs. For example, the first reference angle range is [80°, 100°]. In this case, if the angle between the motion trajectory of a certain mobile object and the travel direction of the first vehicle is determined to be within the range of [80°, 100°], the mobile object is determined to have crossed the road.

[0094] For the above scenario 1, the first vehicle identifies the environmental video to determine the motion trajectory of the mobile object in the environmental video. If it is determined based on the motion trajectory that the mobile object has the behavior of crossing the road, the relative position and relative speed of the mobile object and the first vehicle are obtained from the radar perception information. Based on the relative position and relative speed of the mobile object and the first vehicle, the relative collision time between the mobile object and the first vehicle is determined. When the relative collision time is lower than the collision time threshold, it is determined that the first vehicle is in danger of driving. That is to say, when a certain mobile object has a tendency to cross the road, the relative collision time between the mobile object and the first vehicle can be determined. When the relative collision time is lower than the collision time threshold, it is determined that the mobile object will affect the driving safety of the first vehicle. At this time, it can be determined that the first vehicle is in danger of driving.

[0095] The above-mentioned moving objects can be pedestrians, animals, non-motorized vehicles, etc. in the direction of travel of the first vehicle. For example, when the first vehicle is traveling forward, the moving objects in front of the first vehicle can be detected. Moreover, the above-mentioned scenario 1 can be applicable to the situation of starting at a traffic light at an intersection, and can also be applicable to the situation of encountering ghost heads or pedestrians or bicycles running red lights while the vehicle is driving or crossing the road. In these situations, the driver's field of vision may be obstructed due to the obstruction of surrounding vehicles, and the driver cannot clearly observe the vehicles or pedestrians on the horizontal road, and the risk of accidents increases sharply. Therefore, according to the method provided in the embodiment of the present application, the surrounding environment can be monitored, so as to identify ghost heads, running red lights, etc. in the shortest time.

[0096] Scenario 2: The environment video is recognized to determine the driving trajectory of a second vehicle traveling in an adjacent lane to the first vehicle. If the driving trajectory determines that the second vehicle's direction of travel is offset and heading toward the lane where the first vehicle is located, the second vehicle is identified as a target object.

[0097] That is, scenario 2 identifies vehicles in lanes adjacent to the first vehicle that are traveling in a direction that is offset and oriented toward the first vehicle's lane as target objects. The first vehicle identifies vehicles traveling in adjacent lanes in the surrounding video and determines the trajectory of each vehicle in the adjacent lanes. Based on the trajectory of each vehicle, it determines whether any of these vehicles have a direction that is offset and whether these vehicles are traveling toward the first vehicle's lane. As a result, vehicles with a direction that is offset and oriented toward the first vehicle's lane are identified as target objects. In other words, vehicles in these adjacent lanes that have a direction that is offset and oriented toward the first vehicle's lane are identified as potential risk objects around the first vehicle.

[0098] In some embodiments, the first vehicle identifies lane markings in the environment video and uses the identified lane markings to determine the lane in which the first vehicle is located, as well as the position of the adjacent lane to the lane in which the first vehicle is located. After determining the position of the adjacent lane to the lane in which the first vehicle is located, the first vehicle identifies vehicles in the adjacent lane to determine the position of each vehicle in the adjacent lane in each video frame. By splicing the positions of each vehicle in the adjacent lane across multiple video frames, the driving trajectory of each vehicle in the adjacent lane can be determined. For example, the position of a vehicle in an adjacent lane in the 30 frames of video preceding the current moment can be spliced ​​together to obtain the driving trajectory of the vehicle.

[0099] After determining the driving trajectory of a vehicle in an adjacent lane, it is possible to determine whether the angle between the vehicle's driving trajectory and the lane marking is within a second reference angle range. If the angle between the vehicle's driving trajectory and the lane marking is within the second reference angle range, and the vehicle is traveling toward the lane where the first vehicle is located, it is determined that the vehicle's driving direction has deviated, thereby posing a risk of collision with the first vehicle. If the angle between the vehicle's driving trajectory and the lane marking is not within the second reference angle range, or if the vehicle is traveling away from the lane where the first vehicle is located, it is determined that the vehicle does not pose a risk of collision with the first vehicle.

[0100] It should be noted that the second reference angle range is pre-set and can be adjusted according to different needs. For example, the second reference angle range is [30°, 150°]. In this case, if it is determined that the angle between the driving trajectory of a certain vehicle and the lane line is within the range [30°, 150°] and the driving direction of the vehicle is toward the lane where the first vehicle is located, then the vehicle is determined to have a risk of collision with the first vehicle.

[0101] The adjacent lane mentioned above can be the adjacent lane to the left of the first vehicle's lane, or the adjacent lane to the right of the first vehicle's lane. The second vehicle mentioned above can be a vehicle traveling in the same direction as the first vehicle. For example, if the first vehicle is traveling forward, the vehicle in the adjacent lane ahead of the first vehicle can be detected. Furthermore, the above scenario 2 is applicable to normal vehicle driving on the road, especially when driving at high speeds.

[0102] Scenario 3: In response to a lane change by a first vehicle, the system identifies the surrounding video to determine whether a vehicle is traveling in the target lane. The target lane is the lane the first vehicle is traveling in after the lane change. If a vehicle is traveling in the target lane, a third vehicle is identified as the target object. The third vehicle is the vehicle traveling in the target lane.

[0103] That is, scenario 3 is to determine a third vehicle running on a target lane of the first vehicle as a target object. When the first vehicle has a lane changing operation, the environment video around the first vehicle captured by the camera is recognized to determine whether there is a vehicle running on the driving path of the target lane where the first vehicle is driving. If there is a vehicle running on the driving path, the third vehicle is determined as the target object, and the third vehicle refers to the vehicle running on the target lane.

[0104] In some embodiments, the first vehicle determines the lane where the first vehicle is located by recognizing the lane line in the environment video, and determines the position of the adjacent lane of the lane where the first vehicle is located. Since the adjacent lane of the lane where the first vehicle is located can be one lane on the left side or the right side, or two lanes on the left side and the right side, in the case where the adjacent lane of the lane where the first vehicle is located is one lane, the adjacent lane is directly determined as the target lane, and then it is determined whether there is a vehicle running on the target lane. In the case where the adjacent lane of the lane where the first vehicle is located is two lanes, the driving direction of the first vehicle is determined by recognizing the environment video, and the lane in the driving direction of the first vehicle among the two adjacent lanes is determined as the target lane, and then it is determined whether there is a vehicle running on the target lane. If there is a vehicle running on the target lane, the vehicle running on the target lane is determined as the target object.

[0105] Among them, scenario 3 is generally applicable to the case where the driver performs a lane changing operation, including the case of overtaking and the case of normal driving lane changing. In this case, it is generally considered that the driver will perform a lane changing operation when the driver turns on the turn signal or the steering wheel angle exceeds the steering angle threshold. Of course, scenario 3 described above can also be applicable to other situations, such as turning or U-turn.

[0106] In the case where scenario 3 is applicable to overtaking the front vehicle of the adjacent lane, the adjacent lane is the target lane, and the third vehicle described above can be the vehicle in the driving direction of the first vehicle, for example, in the case where the first vehicle drives forward, the vehicle in front of the first vehicle and located on the target lane can be detected.

[0107] In the case where scenario 3 is applicable to normal driving lane changing, the third vehicle described above can be the vehicle on the target lane and in the driving direction of the first vehicle, or the vehicle on the target lane and in the opposite direction of the driving direction of the first vehicle. For example, in the case where the first vehicle drives forward, the front vehicle on the target vehicle can be detected, and the rear vehicle on the target vehicle can also be detected.

[0108] Among them, the steering angle threshold is set in advance, and in different cases, it can also be adjusted according to different needs.

[0109] In the second implementation, the environment video is analyzed to determine the position of the first center axis and the position of the second center axis, the first center axis being the center axis of the first vehicle, and the second center axis being the center axis of the lane in which the first vehicle is located; based on the position of the first center axis and the position of the second center axis, the included angle between the first center axis and the second center axis is determined; and in a case where the included angle between the first center axis and the second center axis is greater than an included angle threshold, it is determined that the first vehicle is in a driving danger.

[0110] That is, the environment video is identified to determine the position of the first center axis and the position of the second center axis. The first center axis is the center axis of the first vehicle, and the second center axis is the center axis of the lane in which the first vehicle is located. The included angle between the first center axis and the second center axis can be determined through the position of the first center axis and the position of the second center axis. Then the included angle between the first center axis and the second center axis is compared with the included angle threshold. In a case where the included angle between the first center axis and the second center axis exceeds the included angle threshold, it indicates that the first vehicle has a tendency to deviate from the lane, and at this time it can be determined that the first vehicle is in a driving danger. In a case where the included angle between the first center axis and the second center axis is lower than the included angle threshold, it indicates that the first vehicle does not have a tendency to deviate from the lane, and at this time it can be determined that the first vehicle is not in a driving danger.

[0111] The first center axis is the center axis of the first vehicle after the position of the camera is calibrated. The second center axis is a center axis fitted according to the lane line width of the lane in which the first vehicle is located, which is determined through the environment video captured by the camera. The included angle threshold is set in advance, and in different cases, the included angle threshold can also be adjusted according to different needs.

[0112] The second implementation is generally applicable to the case where the vehicle is normally driving, and is used to monitor in real time whether the driving track of the first vehicle is likely to deviate from the lane in which the first vehicle is located.

[0113] Step 103: In a case where the first vehicle is in a driving danger, at least one of the speed and the steering of the first vehicle is controlled.

[0114] In a case where it is determined through the above steps that the first vehicle is in a driving danger, the first vehicle is controlled to help the vehicle to get away from the dangerous situation. The control of the speed of the first vehicle includes but is not limited to the control through an ESP (Electronic Stability Program) system. The steering of the first vehicle includes but is not limited to the output of corresponding torque through an EPS (Electric Power Steering) system.

[0115] The above step 102 includes two implementation methods, and the first implementation method illustrates three scenarios. In different situations, the methods of controlling at least one of the speed and the steering of the first vehicle are different, which will be introduced below respectively.

[0116] Corresponding to Scenario 1 above, if Scenario 1 determines that the first vehicle is in danger of driving, a determination can be made as to whether the first vehicle can brake within the relative collision time based on the relative collision time between the target object and the first vehicle and the first vehicle's current speed. If the first vehicle can brake within the relative collision time, deceleration control is implemented on the first vehicle. If the first vehicle cannot brake within the relative collision time, deceleration control of the first vehicle cannot avoid the danger. In this case, steering control of the first vehicle can be implemented to avoid the danger.

[0117] In some embodiments, the time required for the first vehicle's speed to drop to zero can be determined based on the first vehicle's current speed according to a relevant algorithm. If this time is less than the relative collision time between the target object and the first vehicle, it is determined that the first vehicle can brake within the relative collision time. If this time exceeds the relative collision time between the target object and the first vehicle, it is determined that the first vehicle cannot brake within the relative collision time. If the first vehicle cannot brake within the relative collision time, the first vehicle can determine the first vehicle's torque according to a relevant algorithm based on the relative position of the target object and the first vehicle and the first vehicle's current speed, and then output this torque to control the first vehicle's steering.

[0118] Corresponding to Scenario 2 above, if Scenario 2 determines that the first vehicle is in danger, a determination can be made as to whether deceleration control is required for the first vehicle based on the first vehicle's current speed. If deceleration control is required, steering control is performed simultaneously with deceleration control. If deceleration control is not required, steering control is performed directly to move the first vehicle away from the target object, thereby avoiding the danger.

[0119] If the first vehicle is traveling at a high speed, directly controlling the steering of the first vehicle without performing deceleration control on the first vehicle can easily cause the vehicle to overturn. Therefore, it is possible to determine whether the current speed of the first vehicle exceeds a speed threshold. If the current speed of the first vehicle exceeds the speed threshold, it is determined that the first vehicle is currently traveling at a high speed and deceleration control is required for the first vehicle. If the current speed of the first vehicle does not exceed the speed threshold, it is determined that the first vehicle is currently not traveling at a high speed and deceleration control is not required for the first vehicle.

[0120] The speed threshold is set in advance, and can be adjusted according to different requirements in different situations.

[0121] Corresponding to Scenario 3 above, if the first vehicle is determined to be in a driving hazard according to Scenario 3, if the target object is a preceding vehicle in an adjacent lane to the first vehicle's lane, the first vehicle's torque is determined based on the relative position of the target object and the first vehicle, as well as the first vehicle's current speed, according to a relevant algorithm. This torque is then output to control the first vehicle's steering. If the target object is a following vehicle in an adjacent lane to the first vehicle's lane, an alarm is triggered, indicating that the first vehicle is at risk of collision. If, after the alarm is triggered, the steering wheel angle of the first vehicle is detected to exceed a steering angle threshold and the yaw angle of the first vehicle exceeds a yaw angle threshold, at least one of the speed and steering of the first vehicle is controlled.

[0122] If there is a vehicle behind the first vehicle in an adjacent lane, an alarm will be issued to the user. However, if the steering wheel angle of the first vehicle exceeds the steering angle threshold and the yaw angle of the first vehicle exceeds the yaw angle threshold, indicating that the driver has forced a lane change, the steering of the first vehicle can be directly controlled to further alert the driver and avoid danger.

[0123] The warning information includes, but is not limited to, displaying a corresponding icon on the instrument panel, emitting an alarm sound, and generating vibration on the steering wheel. The turning angle threshold and yaw angle threshold are pre-set and can be adjusted according to different needs in different situations. Moreover, in the embodiment of the present application, the driver is considered to have forced a lane change only when the steering wheel angle of the first vehicle exceeds the turning angle threshold and the yaw angle of the first vehicle exceeds the yaw angle threshold. If the steering wheel angle of the first vehicle is below the turning angle threshold or the yaw angle of the first vehicle is below the yaw angle threshold, it may be due to driver error. In this case, the driver is considered not to have forced a lane change.

[0124] When the driver changes lanes forcibly, the first vehicle may output a fixed torque for steering control. The fixed torque is pre-set and may be different in different situations.

[0125] It should be noted that the above alarm information is triggered when the target object in scenario 3 is the rear vehicle in the adjacent lane of the lane where the first vehicle is located. In actual applications, the alarm information can also be triggered in other situations to remind the user that there is a current collision risk.

[0126] The current speed and other information of the first vehicle can be obtained through a TCU (Transmission Control Unit), an EMS (Engine Management System), etc., and this embodiment of the present application does not limit this.

[0127] Next, we will combine Figure 4 The implementation process of the embodiment of the present application is introduced.

[0128] During driving, the first vehicle's camera captures real-time video of the environment around it, and its radar senses the environment around it, obtaining radar-sensed information about the first vehicle. The first vehicle sends the captured data to a domain controller, which processes the data using appropriate algorithms and mechanisms. The domain controller then transmits the processed information to the central gateway via the CAN (Controller Area Network) bus. The central gateway then performs protocol conversion on the relevant information and transmits the processed commands to the various execution systems via the CAN bus. For example, during driving, both the camera-captured video and the radar-sensed information can be sent to the domain controller. After calculation, the domain controller determines that the first vehicle is in a driving danger and that the target vehicle is a vehicle following behind in an adjacent lane. The domain controller generates an alarm and sends it via the CAN bus to the central gateway. The central gateway processes the alarm and then sends it via the CAN bus to the first vehicle's instrument cluster, which displays the alarm.

[0129] In the embodiment of the present application, based on different environmental information around the first vehicle, a target object that may pose a threat to the safe driving of the first vehicle is determined, and it is further determined whether the first vehicle is in a driving danger, so that different operations are adopted for different dangerous situations for precise control to ensure driving safety. Moreover, the vehicle-mounted devices such as cameras and radars can obtain as much and accurate information as possible, even information that cannot be perceived by the driver, and through these information, it can be accurately determined whether the first vehicle is in danger, even the possible danger can be predicted, and then the dangerous situation is timely warned and the vehicle is timely taken further precise control. That is, in the case of ghost head or a pedestrian or a bicycle running a red light, according to the method provided in the embodiment of the present application, the surrounding environment can be monitored to identify the ghost head, red light running and the like in the shortest time and implement corresponding control. When the vehicle is normally driving on the road, dangerous driving of the vehicle around the first vehicle may cause the first vehicle to be in a dangerous situation, and according to the method provided in the embodiment of the present application, the deviation of the surrounding vehicle can be detected in the first time, and corresponding control is timely performed. When changing lanes, there may be a driving danger between the vehicle in the adjacent lane of the first vehicle and the first vehicle, and according to the method provided in the embodiment of the present application, the driving danger of the first vehicle can be detected in time, and corresponding control and warning are timely performed, so as to improve the safety performance of the vehicle and further reduce the accident rate.

[0130] Figure 5 is a structural schematic diagram of a vehicle control device provided in the embodiment of the present application, which can be realized by software, hardware or a combination of both as part or all of the vehicle. Please refer to Figure 5 , which comprises an acquisition module 501, a determination module 502 and a control module 503.

[0131] The acquisition module 501 is configured to acquire the environmental video around the first vehicle and the radar sensing information of the first vehicle, and the environmental video and the radar sensing information are used to represent the surrounding environment of the first vehicle.

[0132] The determination module 502 is configured to determine whether the first vehicle is in a driving danger based on at least one of the acquired environmental video and radar sensing information.

[0133] The control module 503 is configured to control at least one of the speed and the steering of the first vehicle in the case that the first vehicle is in a driving danger.

[0134] Optionally, the determination module 502 comprises:

[0135] The first determination unit is configured to determine a target object based on the environmental video, the target object being a potential risk object around the first vehicle.

[0136] an acquiring unit, configured to acquire the relative position and relative speed of the target object and the first vehicle from the radar sensing information;

[0137] a second determining unit, configured to determine a relative collision time between the target object and the first vehicle based on the acquired relative position and relative speed between the target object and the first vehicle;

[0138] The third determining unit is configured to determine that the first vehicle is in a driving danger when the relative collision time is lower than a collision time threshold.

[0139] Optionally, the first determining unit is specifically configured to:

[0140] Identify the environment video to determine the motion trajectory of the moving object in the environment video;

[0141] If it is determined based on the motion trajectory that the moving object has a behavior of crossing the road, the moving object is determined as a target object.

[0142] Optionally, the first determining unit is specifically configured to:

[0143] Recognize the environment video to determine the driving trajectory of a second vehicle traveling in an adjacent lane of the first vehicle;

[0144] If it is determined based on the driving trajectory that the driving direction of the second vehicle is deviated and is heading towards the lane where the first vehicle is located, the second vehicle is determined as a target object.

[0145] Optionally, the first determining unit is specifically configured to:

[0146] In response to the lane change operation of the first vehicle, identifying the environment video to determine whether there is a vehicle traveling in a target lane, the target lane being the lane in which the first vehicle is traveling after the lane change;

[0147] If there is a vehicle traveling in the target lane, a third vehicle is determined as a target object, where the third vehicle refers to the vehicle traveling in the target lane.

[0148] Optionally, the device further comprises:

[0149] An alarm module is used to trigger an alarm message, where the alarm message is used to indicate that the first vehicle has a collision risk;

[0150] The trigger module is configured to trigger the control module 503 to control at least one of the speed and steering of the first vehicle if it is detected that the steering wheel angle of the first vehicle exceeds the steering angle threshold and the yaw angle of the first vehicle exceeds the yaw angle threshold after the alarm information is triggered.

[0151] Optionally, the determination module 502 includes:

[0152] a fourth determining unit, configured to analyze the environmental video to determine a position of a first central axis and a position of a second central axis, wherein the first central axis is the central axis of the first vehicle and the second central axis is the central axis of a lane where the first vehicle is located;

[0153] a fifth determining unit, configured to determine an angle between the first central axis and the second central axis based on a position of the first central axis and a position of the second central axis;

[0154] The sixth determination unit is configured to determine that the first vehicle is in a driving danger when an angle between the first central axis and the second central axis exceeds an angle threshold.

[0155] In an embodiment of the present application, based on different environmental information around the first vehicle, a target object that may pose a threat to the safe driving of the first vehicle is determined, and it is further determined whether the first vehicle is in danger of driving, so that different operations are used to accurately control different dangerous situations to ensure driving safety. Moreover, vehicle-mounted equipment such as cameras and radars can obtain as much and accurate information as possible, even information that the driver cannot perceive. Through this information, it is possible to accurately determine whether the first vehicle is in danger, and even predict possible dangers, and then timely warn of dangerous situations and take further precise control of the vehicle in a timely manner. That is, when encountering a situation of ghosting or pedestrians or bicycles running red lights, according to the method provided in the embodiment of the present application, the surrounding environment can be monitored, so that ghosting, running red lights, etc. can be identified in the shortest time and corresponding control can be implemented. When the vehicle is driving normally on the road, the dangerous driving of vehicles around the first vehicle may put the first vehicle in a dangerous situation. According to the method provided in the embodiment of the present application, the deviation of the surrounding vehicles can be detected in the first time and corresponding control can be implemented in a timely manner. When changing lanes, there may be a driving hazard between the first vehicle and the vehicle in the adjacent lane of the first vehicle. The method provided in accordance with the embodiment of the present application can detect the possible driving hazard of the first vehicle in a timely manner, and perform corresponding control and reminders in a timely manner, thereby improving the safety performance of the vehicle and further reducing the accident rate.

[0156] It should be noted that the vehicle control device provided in the above embodiment is merely an example of the division of the aforementioned functional modules when performing vehicle control. In actual applications, the aforementioned functions can be distributed among different functional modules as needed, i.e., the internal structure of the device can be divided into different functional modules to perform all or part of the functions described above. Furthermore, the vehicle control device provided in the above embodiment and the vehicle control method embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0157] Figure 66 is a schematic diagram of the structure of a vehicle provided in an embodiment of the present application. Vehicle 600 includes a central processing unit (CPU) 601, a system memory 604 including a random access memory (RAM) 602 and a read-only memory (ROM) 603, and a system bus 605 connecting system memory 604 and central processing unit 601. Vehicle 600 also includes a basic input / output system (I / O system) 606 that facilitates information transmission between various components, and a mass storage device 607 for storing an operating system 613, application programs 614, and other program modules 615.

[0158] The basic input / output system 606 includes a display 608 for displaying information and an input device 609, such as a touch panel, for user input. Both the display 608 and the input device 609 are connected to the central processing unit 601 via an input / output controller 610 connected to the system bus 605. The basic input / output system 606 may also include an input / output controller 610 for receiving and processing input from other devices such as a touch panel. Similarly, the input / output controller 610 also provides output to a display screen, speakers, or other types of output devices.

[0159] The mass storage device 607 is connected to the central processing unit 601 through a mass storage controller (not shown) connected to the system bus 605. The mass storage device 607 and its associated computer-readable media provide non-volatile storage for the vehicle 600. That is, the mass storage device 607 may include computer-readable media (not shown) such as a hard disk or CD-ROM drive.

[0160] Without loss of generality, computer-readable media may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storage technologies, CD-ROM, DVD or other optical storage, magnetic cassettes, magnetic tape, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media is not limited to the aforementioned types. The above-mentioned system memory 604 and mass storage device 607 may be collectively referred to as memory.

[0161] According to various embodiments of the present application, the vehicle 600 can also operate connected to a remote computer on a network, such as the Internet. That is, the vehicle 600 can be connected to a network 612 through a network interface unit 611 connected to the system bus 605, or can be connected to other types of networks or remote computer systems (not shown) using the network interface unit 611.

[0162] The above-mentioned memory also includes one or more programs stored in the memory configured to be executed by the CPU.

[0163] In some embodiments, a computer readable storage medium is also provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the vehicle control method in the above-mentioned embodiments. For example, the computer readable storage medium can be a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0164] It is worth noting that the computer readable storage medium mentioned in the embodiments of the present application can be a non-volatile storage medium, in other words, can be a non-transitory storage medium.

[0165] It should be understood that all or part of the steps of the above-mentioned embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in the form of a computer program product entirely or partially. The computer program product includes one or more computer instructions. The computer instructions can be stored in the above-mentioned computer readable storage medium.

[0166] That is, in some embodiments, a computer program product including instructions, which when executed on a computer, cause the computer to perform the steps of the vehicle control method described above.

[0167] It should be understood that "at least one" mentioned herein refers to one or more, and "multiple" refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B; "and / or" herein is only a description of the association between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, "first", "second", etc. are used to distinguish the same items or similar items with basically the same function and effect in the embodiments of the present application. Those skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. also do not necessarily mean different.

[0168] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in the embodiments of this application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the environmental information around the first vehicle and the radar perception information of the first vehicle involved in the embodiments of this application are both obtained with full authorization.

[0169] The above description is an embodiment provided for this application and is not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application should be included in the scope of protection of this application.

Claims

1. A vehicle control method, characterized in that: Applied to a first vehicle, the method includes: Acquire an environment video around the first vehicle and radar perception information of the first vehicle, wherein the environment video and the radar perception information are used to represent the environment around the first vehicle; determining whether the first vehicle is in danger of driving based on at least one of the environmental video and the radar perception information; When the first vehicle is in danger of traveling, controlling at least one of a speed and a steering direction of the first vehicle; The determining, based on at least one of the environmental video and the radar perception information, whether the first vehicle is in danger of traveling includes: determining a target object based on the environmental video, the target object being a potential risk object around the first vehicle; obtaining a relative position and relative speed of the target object and the first vehicle from the radar perception information; determining a relative collision time between the target object and the first vehicle based on the relative position and relative speed of the target object and the first vehicle; and determining that the first vehicle is in danger of traveling if the relative collision time is lower than a collision time threshold; The determining of the target object based on the environmental video includes: identifying the moving objects in each video frame of the environmental video to determine the position of each moving object in each video frame, splicing the position of each moving object in multiple video frames, and determining the motion trajectory of each moving object; determining whether the angle between the motion trajectory of the moving object and the driving direction of the first vehicle is within a first reference angle range, if the angle between the motion trajectory of the moving object and the driving direction of the first vehicle is within the first reference angle range, determining that the moving object has a behavior of crossing the road, the first reference angle range being [80°, 100°]; if it is determined that the moving object has a behavior of crossing the road, determining the moving object as the target object; If the target object is a moving object with the intention of crossing the road, and if there is a driving danger for the first vehicle, at least one of the speed and the steering of the first vehicle is controlled, including: determining whether the first vehicle can brake within the relative collision time based on the relative collision time between the target object and the first vehicle and the current speed of the first vehicle; if the first vehicle can brake within the relative collision time, decelerating the first vehicle; if the first vehicle cannot brake within the relative collision time, controlling the steering of the first vehicle to avoid the danger.

2. The method according to claim 1, wherein The determining the target object based on the environment video includes: Recognizing the environment video to determine a driving trajectory of a second vehicle traveling in a lane adjacent to the first vehicle; If it is determined based on the driving trajectory that the driving direction of the second vehicle is deviated and is heading towards the lane where the first vehicle is located, the second vehicle is determined as the target object.

3. The method according to claim 1, wherein The determining the target object based on the environment video includes: In response to the lane change operation of the first vehicle, identifying the environment video to determine whether there is a vehicle traveling in a target lane, the target lane being the lane in which the first vehicle is traveling after the lane change; If there is a vehicle traveling in the target lane, a third vehicle is determined as the target object, where the third vehicle refers to the vehicle traveling in the target lane.

4. The method according to claim 3, wherein Before controlling at least one of the speed and the steering of the first vehicle, the method further comprises: triggering an alarm message, wherein the alarm message is used to indicate that the first vehicle has a collision risk; If it is detected that the steering wheel angle of the first vehicle exceeds a steering angle threshold and the yaw angle of the first vehicle exceeds a yaw angle threshold after the warning information is triggered, a step of controlling at least one of the speed and steering of the first vehicle is performed.

5. The method according to claim 1, wherein The determining, based on at least one of the environmental video and the radar perception information, whether the first vehicle is in a driving danger includes: Analyzing the environmental video to determine a position of a first central axis and a position of a second central axis, where the first central axis is the central axis of the first vehicle and the second central axis is the central axis of a lane in which the first vehicle is located; determining an angle between the first central axis and the second central axis based on a position of the first central axis and a position of the second central axis; When the angle between the first central axis and the second central axis exceeds an angle threshold, it is determined that there is a driving risk for the first vehicle.

6. A vehicle control device, characterized in that: Applied to a first vehicle, the device comprises: an acquisition module, configured to acquire an environment video surrounding the first vehicle and radar perception information of the first vehicle, wherein the environment video and the radar perception information are used to represent the environment surrounding the first vehicle; a determination module, configured to determine whether the first vehicle is in a driving danger based on at least one of the environmental video and the radar perception information; a control module, configured to control at least one of a speed and a steering direction of the first vehicle when the first vehicle is in a driving danger; The determining module includes: a first determining unit, configured to determine a target object based on the environmental video, wherein the target object refers to a potential risk object around the first vehicle; an acquiring unit, configured to acquire the relative position and relative speed of the target object and the first vehicle from the radar sensing information; a second determining unit, configured to determine a relative collision time between the target object and the first vehicle based on a relative position and a relative speed between the target object and the first vehicle; a third determining unit, configured to determine that the first vehicle is in a driving danger when the relative collision time is lower than a collision time threshold; The first determination unit is configured to identify the moving objects in each video frame of the environmental video to determine the position of each moving object in each video frame, and to splice the positions of each moving object in multiple video frames to determine the motion trajectory of each moving object; determine whether the angle between the motion trajectory of the moving object and the driving direction of the first vehicle is within a first reference angle range, and if the angle between the motion trajectory of the moving object and the driving direction of the first vehicle is within the first reference angle range, determine that the moving object has a behavior of crossing the road, and the first reference angle range is [80°, 100°]; if it is determined that the moving object has a behavior of crossing the road, determine the moving object as the target object; The control module is configured to determine, if the target object is a moving object that is intended to cross a road, whether the first vehicle can brake within the relative collision time between the target object and the first vehicle, and the current speed of the first vehicle; if the first vehicle can brake within the relative collision time, perform deceleration control on the first vehicle; and if the first vehicle cannot brake within the relative collision time, perform steering control on the first vehicle to avoid danger.

7. A vehicle, characterized in that: The vehicle includes a memory and a processor, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of any one of the methods described in claims 1-5.

8. A computer-readable storage medium, characterized in that The storage medium stores a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

Images