Method, system, computer device and storage medium for avoiding emergencies

Abstract

The present application relates to a method, system, computer device and storage medium for avoiding emergencies. The method comprises: collecting emergency information on the road, determining at least one evasive action of the target vehicle based on the emergency information, and obtaining a first probability of each evasive action, wherein the first probability is the probability of the target vehicle colliding with other vehicles when performing the evasive action; determining a safe action based on the evasive action corresponding to the first probability being lower than a preset probability threshold, and obtaining a first safe driving strategy including the safe action; controlling the target vehicle to drive according to the first safe driving strategy to avoid emergencies on the road. By adopting this method, when an emergency occurs on the road, the target vehicle can avoid the emergency by executing the first safe driving strategy obtained in the aforementioned steps, reduce the possibility of collision with other vehicles, and improve the safety of the autonomous driving car during driving.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, system, computer device, and storage medium for avoiding emergencies. Background Art

[0002] In recent years, with the rapid development of science and technology, especially artificial intelligence, research on autonomous vehicle technology has become a hot topic across various industries. Autonomous vehicles are intelligent vehicles that use cameras, radar, lidar, ultrasonic sensors, and the Global Positioning System (GPS) to perceive the road environment and a designated destination, automatically planning a route and controlling the vehicle to reach the predetermined destination. While driving, autonomous vehicles may encounter unexpected situations, such as a vehicle in another lane changing lanes or the vehicle ahead suddenly braking. These situations can create the potential for a collision between the autonomous vehicle and the other vehicle, posing a safety hazard to both. Summary of the Invention

[0003] Based on this, a method, system, computer device and storage medium for avoiding emergencies are provided to reduce the possibility of collision when an autonomous vehicle encounters an emergency during driving.

[0004] In one aspect, a method for avoiding an emergency is provided, the method comprising:

[0005] Collecting emergency information on the road, determining at least one evasive action for the target vehicle based on the emergency information, and obtaining a first probability for each evasive action, wherein the first probability is a probability of the target vehicle colliding with another vehicle when executing the evasive action;

[0006] Determining a safe action according to an avoidance action corresponding to the first probability being lower than a preset probability threshold, and obtaining a first safe driving strategy including the safe action;

[0007] The target vehicle is controlled to drive according to the first safe driving strategy to avoid unexpected situations on the road.

[0008] In one embodiment, the step of obtaining a first safe driving strategy including the safe action comprises:

[0009] Obtaining a corresponding first action adjustment value according to each of the safety actions and the current driving action of the target vehicle;

[0010] Determine whether each of the first action adjustment values ​​is within a preset first action adjustment interval, and if the first action adjustment value is within the first action adjustment interval, obtain a first safe driving strategy including the safe action corresponding to the first action adjustment value.

[0011] In one embodiment, the step of obtaining the first probability corresponding to each of the avoidance actions includes:

[0012] Obtaining a second safe driving strategy corresponding to the other vehicle based on each of the avoidance actions, wherein when the other vehicle executes the second safe driving strategy, the other vehicle maintains a safe distance from the target vehicle;

[0013] Obtaining the dangerous driving strategies corresponding to the other vehicles according to each of the second safe driving strategies;

[0014] Obtain historical location information and historical driving status information of the other vehicle, obtain a second probability based on the historical location information and the historical driving status information, and obtain the first probability including the second probability, wherein the second probability is the probability that the other vehicle adopts the dangerous driving strategy.

[0015] In one embodiment, the step of obtaining the first probability corresponding to each of the avoidance actions further includes:

[0016] When the number of the other vehicles is two or more, obtaining a second probability corresponding to each of the other vehicles;

[0017] A third probability is obtained based on each of the second probabilities, and a first probability including the third probability is obtained, wherein the third probability is the probability that the target vehicle collides with one of the other vehicles. The mathematical expression for obtaining the third probability is:

[0018]

[0019] Wherein, P is the third probability, P(i) is each of the second probabilities, and n=1, ..., i.

[0020] In one embodiment, the step of obtaining the second safe driving strategy corresponding to the other vehicles based on the avoidance actions of the target vehicles includes:

[0021] Collecting the position information corresponding to the target vehicle according to each of the avoidance actions and the preset time intervals;

[0022] Obtaining a corresponding adjustment strategy based on each of the position information, wherein when the other vehicles execute the adjustment strategy and the target vehicle executes the evasive action, the other vehicles maintain a safe distance from the target vehicle;

[0023] The intersection of the adjustment strategies at each moment is taken to obtain the second safe driving strategy corresponding to the other vehicle.

[0024] In one embodiment, the step of controlling the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road includes:

[0025] Obtaining a second action adjustment value corresponding to the first safe driving strategy based on each safety action included in the first safe driving strategy and the current driving action of the target vehicle;

[0026] adjusting the value according to the second action, determining whether the first safe driving strategy is urgent;

[0027] When it is determined that the first safe driving strategy is in an emergency, the target vehicle is controlled to drive according to the first safe driving strategy to avoid the emergency situation on the road.

[0028] In one embodiment, the step of adjusting the value according to the second action to determine whether the first safe driving strategy is urgent includes:

[0029] determining whether the second action adjustment value is within a preset second action adjustment range;

[0030] If so, determining that the first safe driving strategy is urgent;

[0031] If not, it is determined that the first safe driving strategy is not urgent, and the process returns to the step of collecting emergency information on the road.

[0032] In another aspect, a system for avoiding emergencies is provided, the system comprising:

[0033] a preprocessing module configured to collect emergency information on the road, determine at least one evasive action for the target vehicle based on the emergency information, and obtain a first probability corresponding to each evasive action, wherein the first probability is a probability of the target vehicle colliding with another vehicle when executing the evasive action;

[0034] a driving strategy generation module, the driving strategy generation module being configured to determine a safe action based on an avoidance action corresponding to the first probability being lower than a preset probability threshold, and to obtain a first safe driving strategy including the safe action;

[0035] A control module is used to control the target vehicle to drive according to the first safe driving strategy to avoid emergencies on the road.

[0036] In another aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0037] Collecting emergency information on the road, determining at least one evasive action for the target vehicle based on the emergency information, and obtaining a first probability for each evasive action, wherein the first probability is a probability of the target vehicle colliding with another vehicle when executing the evasive action;

[0038] Determining a safe action according to an avoidance action corresponding to the first probability being lower than a preset probability threshold, and obtaining a first safe driving strategy including the safe action;

[0039] The target vehicle is controlled to drive according to the first safe driving strategy to avoid unexpected situations on the road.

[0040] In another aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0041] Collecting emergency information on the road, determining at least one evasive action for the target vehicle based on the emergency information, and obtaining a first probability for each evasive action, wherein the first probability is a probability of the target vehicle colliding with another vehicle when executing the evasive action;

[0042] Determining a safe action according to an avoidance action corresponding to the first probability being lower than a preset probability threshold, and obtaining a first safe driving strategy including the safe action;

[0043] The target vehicle is controlled to drive according to the first safe driving strategy to avoid unexpected situations on the road.

[0044] The above-mentioned method, system, computer device and storage medium for avoiding emergencies collect emergency information on the road, determine at least one evasive action of the target vehicle based on the emergency information, and obtain a first probability of each evasive action, wherein the first probability is the probability of the target vehicle colliding with the other vehicles; compare each first probability with a preset probability threshold, determine a safe action based on the evasive action corresponding to the first probability being lower than the probability threshold, and obtain a first safe driving strategy including the safe action; control the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road; determine a safe action by obtaining the probability of the target vehicle colliding with the other vehicles when performing the evasive action, and obtain a first safe driving strategy based on the safer safe action. When an emergency occurs on the road, the target vehicle can avoid the emergency by executing the first safe driving strategy obtained in the above steps, reduce the possibility of collision with the other vehicles, and improve the safety of the autonomous driving car during driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of a method for avoiding emergencies in one embodiment is shown;

[0046] Figure 2 1 is a flow chart of a step of obtaining a first safe driving strategy in one embodiment;

[0047] Figure 3 FIG1 is a flow chart of a step of obtaining a first probability in one embodiment;

[0048] Figure 4 is a schematic diagram of a flow chart for obtaining a first probability in another embodiment;

[0049] Figure 5 1 is a flow chart of a step of obtaining a second safe driving strategy in one embodiment;

[0050] Figure 6 Schematic diagram of a flow chart for executing a first safe driving strategy step in one embodiment;

[0051] Figure 7 1 is a flow chart of determining whether to execute the first safe driving strategy step in one embodiment;

[0052] Figure 8 A structural block diagram of a system for avoiding emergencies in one embodiment;

[0053] Figure 9 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0055] It should be noted that the diagrams provided in the present embodiment are only schematic illustrations of the basic concept of the present invention. Therefore, the diagrams only show components related to the present invention rather than being drawn according to the number, shape, and size of components during actual implementation. During actual implementation, the type, quantity, and ratio of each component can be changed at will, and the component layout type may also be more complex. At the same time, the terms such as "upper", "lower", "left", "right", "front", "back", "middle", and "one" cited in this specification are only for the convenience of description and are not intended to limit the scope of the present invention. Changes or adjustments in their relative relationships should also be considered as the scope of the present invention without substantial changes in the technical content. In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance.

[0056] When driving on the road, self-driving cars may encounter unexpected situations, such as other vehicles suddenly changing lanes into the lane where the self-driving car is located, or the vehicle in front suddenly brakes. At this time, there is a possibility of a collision between the self-driving car and the other vehicle, which poses a safety hazard to the self-driving car during driving and affects the safety of the self-driving car.

[0057] To this end, the present application proposes a method, system, computer device and storage medium for avoiding emergencies, wherein the method determines at least one evasive action that the target vehicle can perform based on the collected emergency information; and determines a safe action with a lower collision probability by obtaining a first probability of each evasive action, that is, the probability of the target vehicle colliding with the other vehicle when performing the evasive action; and obtains a first safe driving strategy including the safe action, and controls the target vehicle to drive according to the first safe driving strategy, so that the target vehicle avoids emergencies as much as possible, thereby reducing the possibility of the target vehicle colliding with the other vehicles, eliminating the safety hazards of the target vehicle and other vehicles to a certain extent, and improving the safety of the autonomous driving vehicle during driving.

[0058] In one embodiment, Figure 1 As shown, a method for avoiding an emergency is provided, comprising the following steps:

[0059] S1: Collect emergency information on the road, determine at least one evasive action of the target vehicle based on the emergency information, and obtain a first probability of each evasive action, wherein the first probability is the probability of the target vehicle colliding with other vehicles when performing the evasive action.

[0060] It should be noted that the target vehicle may encounter emergencies during driving, such as sudden lane changes or sudden braking. Therefore, during the driving process of the target vehicle, the environmental information around the target vehicle can be perceived and collected through cameras, radars and infrared sensors, wherein the environmental information includes but is not limited to: road condition information, traffic rules information, other vehicles or pedestrian information; and through deep learning, such as the error back propagation algorithm, the road condition information, traffic rules information, other vehicles or pedestrian information, etc. are identified and processed to obtain the emergency situation information. In an emergency situation, the target vehicle and the other vehicles may collide, posing a safety hazard to the driving of the target vehicle.

[0061] In order to avoid the collision between the target vehicle and the other vehicles to a certain extent, based on the emergency information, a path to avoid the emergency can be searched through the Dijkstra algorithm or the A-star algorithm; then, based on the environmental information, at least one avoidance action suitable for dealing with the current emergency can be obtained through a behavioral decision model, such as a finite state machine model or a decision tree model, such as turning, reducing speed, etc.

[0062] According to each of the avoidance actions, an avoidance motion trajectory can be obtained through a motion planning algorithm, such as a hybrid A-star algorithm, a rapid-exploration random tree (RRT) algorithm, or an artificial potential field method; by combining the avoidance motion trajectory and the collected trajectories of other vehicles corresponding to the emergency situation, a Bayesian network model can be constructed to obtain a first probability of each of the avoidance actions, wherein the first probability is the probability of the target vehicle colliding with the other vehicle when performing the avoidance action.

[0063] S2: determining a safe action according to the avoidance action corresponding to the first probability being lower than a preset probability threshold, and obtaining a first safe driving strategy including the safe action;

[0064] S3: Control the target vehicle to drive according to the first safe driving strategy to avoid unexpected situations on the road.

[0065] The first probability of each of the avoidance actions is compared with a preset probability threshold. When the first probability is less than the probability threshold, the corresponding avoidance action is determined as a safe action, and a first safe driving strategy including the safe action is obtained. The target vehicle is controlled to execute the first safe driving strategy to avoid the sudden situation on the road. By obtaining the first probability, the avoidance actions are screened to determine the safe action, so that the reliability of the first safe driving strategy including the safe action is higher. When the target vehicle executes the first safe driving strategy, the probability of collision with the other vehicles is lower, thereby improving the safety of the target vehicle during driving.

[0066] In the above-mentioned method for avoiding emergencies, at least one evasive action of the target vehicle is determined based on the collected emergency information, and a first probability of each evasive action is obtained, that is, the probability of the target vehicle colliding with other vehicles when performing the evasive action; each first probability is compared with a preset probability threshold, and if the first probability is lower than the probability threshold, the corresponding evasive action is determined as a safe action, and by screening each evasive action, an evasive action with higher safety, that is, the safe action, is obtained; by obtaining a first safe driving strategy including the safe action, and controlling the target vehicle to drive according to the first safe driving strategy, the target vehicle can effectively avoid emergencies on the road, reduce the possibility of the target vehicle colliding with the other vehicles, eliminate the safety hazards of the target vehicle and other vehicles to a certain extent, and improve the safety of the autonomous driving car during driving.

[0067] As a specific implementation of the above embodiment, Figure 2 As shown, in one embodiment, the step of obtaining the first safe driving strategy including the safe action includes:

[0068] S21: Obtaining a corresponding first action adjustment value according to each of the safety actions and the current driving action of the target vehicle.

[0069] Through each of the safety actions and the driving action of the target vehicle at the current moment, the first action adjustment value corresponding to the target vehicle is obtained. For example, the safety action includes a vehicle steering angle of -3 degrees and an acceleration of -5m / s 2 , based on the target vehicle's current driving action, the first action adjustment values ​​corresponding to this safety action include: the first steering angle adjustment value is -3 degrees, the first acceleration adjustment value is -5m / s 2 For example, the safety action includes a vehicle steering angle of -4 degrees and an acceleration of -4m / s2 , based on the target vehicle's current driving action, the first action adjustment values ​​corresponding to this safety action include: the first steering angle adjustment value is -4 degrees, the first acceleration adjustment value is -4m / s 2 ; In addition, “-” indicates that the corresponding safety action is opposite to the current driving action of the target vehicle, for example, the steering is opposite and the speed is reduced; correspondingly, if the first action adjustment value is a positive number, it means that the corresponding safety action is the same as the current driving action of the target vehicle, for example, the steering is the same and the speed is increased.

[0070] S22: Determine whether each of the first action adjustment values ​​is within a preset first action adjustment interval, and if the first action adjustment value is within the first action adjustment interval, obtain a first safe driving strategy including the safe action corresponding to the first action adjustment value.

[0071] Compare each of the first action adjustment values ​​with the preset first action adjustment interval to determine whether the first action adjustment interval includes the first action adjustment value. When the first action adjustment interval includes the first action adjustment value, obtain a first safe driving strategy including the corresponding safety action, wherein the first action adjustment interval can be set according to different scenario requirements to adapt to application scenarios for avoiding various emergencies. Specifically, taking the above two groups of safety actions as an example, assuming that the first action adjustment interval includes: the first steering angle adjustment interval is (-6, 6) degrees, the first acceleration adjustment interval is (-5, 5) m / s 2 , then the first action adjustment values ​​of the above two groups of safety actions include: the first steering angle adjustment value includes (-4, -3) degrees, the first acceleration adjustment value includes (-5, -4) m / s 2 By comparison, the first action adjustment values ​​of the above two groups of safety actions are within the first action adjustment range. Therefore, the above two groups of safety actions are merged into the first safe driving strategy. After merging, the first safe driving strategy is: turn in the opposite direction of the turning action included in the driving action by (3, 4) degrees, and reduce the speed included in the driving action by (4, 5) m / s. 2 .

[0072] As a specific implementation of the above embodiment, Figure 3 As shown, in one embodiment, the step of obtaining the first probability corresponding to each of the avoidance actions includes:

[0073] S101: Obtaining a second safe driving strategy corresponding to the other vehicle based on each of the avoidance actions, wherein when the other vehicle executes the second safe driving strategy, the other vehicle maintains a safe distance from the target vehicle.

[0074] According to each of the avoidance actions, the second safe driving strategy corresponding to the other vehicles can be predicted, wherein, when the other vehicles execute the second safe driving strategy and the target vehicle executes the avoidance action, the target vehicle and the other vehicles can maintain a safe distance; specifically, the step of predicting the second safe driving strategy corresponding to the other vehicles can include: collecting the position information of the target vehicle through the Global Positioning System (GPS), the Global Navigation Satellite System (GNSS), the Real Time Kinematic (RTK) and the inertial navigation, etc.; and obtaining the avoidance motion trajectory of the target vehicle when performing the avoidance action according to the position information and the avoidance action, and based on the avoidance motion trajectory, the adjustment motion trajectory of the other vehicle can be predicted by the Dijkstra algorithm or the A star algorithm, wherein the avoidance motion trajectory and the adjustment motion trajectory maintain a safe distance; according to the adjustment motion trajectory and the environmental information, the adjustment action of the other vehicle can be obtained by a finite state machine model, a decision tree model, etc., thereby obtaining the second safe driving strategy including the adjustment action.

[0075] S102: Obtaining dangerous driving strategies corresponding to the other vehicles according to each of the second safe driving strategies.

[0076] It should be noted that actions other than those included in each of the second safe driving strategies are merged into the dangerous driving strategy, wherein when the other vehicles execute the dangerous driving strategy and the target vehicle executes the avoidance action, the target vehicle is likely to collide with the other vehicles.

[0077] S103: Obtain historical location information and historical driving status information of the other vehicle, obtain a second probability based on the historical location information and the historical driving status information, and obtain the first probability including the second probability, wherein the second probability is the probability that the other vehicle adopts the dangerous driving strategy.

[0078] It should be noted that the historical position information and historical driving status information of the other vehicles can be obtained through the coordinated action of cameras, radars and navigation systems (such as inertial navigation, etc.); based on the historical position information and the historical driving status information, the second probability, that is, the probability that the other vehicles adopt dangerous driving strategies, can be obtained by constructing a Bayesian network model.

[0079] As a preferred implementation of the above embodiment, Figure 4 As shown, in one embodiment, the step of obtaining the first probability corresponding to each of the avoidance actions further includes:

[0080] S111: When the number of the other vehicles is two or more, obtaining a second probability corresponding to each of the other vehicles;

[0081] S112: Obtain a third probability based on each of the second probabilities, and obtain a first probability including the third probability, wherein the third probability is a probability of the target vehicle colliding with one of the other vehicles. The mathematical expression for obtaining the third probability is:

[0082]

[0083] Wherein, P is the third probability, P(i) is each of the second probabilities, and n=1, ..., i.

[0084] It should be noted that, taking into account the situation where there is more than one other vehicle causing an emergency on the road at the same time, in this embodiment, the second probability of each of the other vehicles is obtained through the aforementioned steps S101-S103, and the third probability, that is, the probability of the target vehicle colliding with one of the other vehicles, is obtained through the aforementioned mathematical expression, thereby being more adaptable to application scenarios where emergencies occur on the road and the target vehicle needs to take evasive action, thereby improving adaptability.

[0085] As a specific implementation of the above embodiment, Figure 5 As shown, in one embodiment, the step of obtaining the second safe driving strategy corresponding to the other vehicles according to the avoidance action of each target vehicle includes:

[0086] S1021: Collecting the position information corresponding to the target vehicle according to each of the avoidance actions and a preset time interval;

[0087] S1022: Obtaining corresponding adjustment strategies based on the respective position information, wherein when the other vehicles execute the adjustment strategies and the target vehicle executes the evasive action, the other vehicles maintain a safe distance from the target vehicle;

[0088] S1023: Taking the intersection of the adjustment strategies at each moment to obtain the second safe driving strategy corresponding to the other vehicle.

[0089] According to each of the avoidance actions and preset time intervals, for example, every 0.1 seconds, and for example, every 0.5 seconds, the position information corresponding to the target vehicle can be collected through GPS, GNSS, inertial navigation, etc., wherein the time interval can be set according to different application scenarios to adapt to more scenario requirements; according to the position information and the avoidance action, the avoidance motion trajectory of the target vehicle when performing the avoidance action is obtained; based on the avoidance motion trajectory, the adjustment motion trajectory of the other vehicles can be predicted by Dijkstra algorithm or A star algorithm; according to the adjustment motion trajectory and the environmental information, the adjustment action of the other vehicles can be obtained through a finite state machine model, a decision tree model, etc., thereby obtaining an adjustment strategy including the adjustment action, wherein a safe distance is maintained when the target vehicle performs the avoidance action and when the other vehicles perform the adjustment strategy; the intersection of the adjustment strategies obtained at each moment is taken to obtain the second safe driving strategy. By taking the intersection of each of the adjustment strategies, the second safe driving strategy obtained is safer, the subsequent dangerous driving strategy obtained based on the second safe driving strategy has a higher risk factor, and the first probability obtained based on the dangerous driving strategy is more accurate, further improving the safety of the autonomous driving car during driving.

[0090] As a specific implementation of the above embodiment, Figure 6 As shown, in one embodiment, the step of controlling the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road includes:

[0091] S31: Obtaining a second action adjustment value corresponding to the first safe driving strategy based on each safety action included in the first safe driving strategy and the current driving action of the target vehicle;

[0092] S32: adjusting the value according to the second action, and determining whether the first safe driving strategy is urgent;

[0093] S33: When it is determined that the first safe driving strategy is in an emergency, control the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road.

[0094] As a specific implementation of the above embodiment, Figure 7 As shown, in one embodiment, the step of adjusting the value according to the second action to determine whether the first safe driving strategy is urgent includes:

[0095] S321: Determine whether the second action adjustment value is within a preset second action adjustment range;

[0096] S322: If yes, determining that the first safe driving strategy is urgent;

[0097] S323: If not, it is determined that the first safe driving strategy is not urgent, and the process returns to the step of collecting emergency information on the road.

[0098] For example, assume that one of the first safe driving strategies includes: a steering angle of -3 degrees, an acceleration of -5 m / s 2 ; and the steering angle is 0 degrees and the acceleration is +5m / s 2 , the second safety action adjustment values ​​include: the second steering angle adjustment values ​​are -3 and 0 degrees, the second acceleration adjustment values ​​are -5 and +5m / s 2 Assume that one of the first safe driving strategies includes: steering angle of -3 degrees, acceleration of -4m / s 2 ; and a steering angle of -3.5 degrees and an acceleration of -5m / s 2 , the second safety action adjustment values ​​include: the second steering angle adjustment value is -3 and -3.5 degrees, the second acceleration adjustment value is -4 and -5m / s 2 , where “-” and “+” represent the direction of the steering angle and the increase or decrease of speed.

[0099] According to the second action adjustment value, determine whether the second action adjustment value is within the preset second action adjustment interval, and determine whether the first safe driving strategy is urgent; if so, the first safe driving strategy includes a smaller degree of freedom of the safety action, which may result in missed opportunities if not executed in time. Therefore, at this time, control the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road; if not, the first safe driving strategy includes a larger degree of freedom of the safety action, and continue to look for a first safe driving strategy that is more suitable for avoiding the emergency. Therefore, at this time, return to step S1, continue to collect the emergency information and environmental information, and subsequently obtain the avoidance action, obtain the first probability of the avoidance action, determine the safety action, and obtain the first safe driving strategy, etc., until a more urgent first safe driving strategy is obtained, thereby executing the first safe driving strategy to avoid the emergency.

[0100] For example, assume that the second action adjustment range includes: the second steering angle adjustment range is (-4, -2) degrees, the second acceleration adjustment range is (-5, 0) m / s 2, the above-mentioned second action adjustment values ​​are taken as an example for explanation; the first group of second action adjustment values ​​do not all fall within the second action adjustment interval, that is, the corresponding first safe driving strategy includes safety actions that do not all meet the emergency conditions, so the strategy does not need to be executed at this time; the second group of second action adjustment values ​​all fall within the second action adjustment interval, that is, the corresponding first safe driving strategy includes safety actions that all meet the emergency conditions, so the strategy needs to be executed at this time.

[0101] It should be understood that although Figure 1-7 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1-7 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0102] In one embodiment, Figure 8 As shown, a system for avoiding emergencies is provided, comprising: a pre-processing module, a driving strategy generation module and a control module, wherein:

[0103] A preprocessing module is used to collect emergency situation information on the road, determine at least one evasive action of the target vehicle based on the emergency situation information, and obtain a first probability corresponding to each evasive action, wherein the first probability is the probability of the target vehicle colliding with other vehicles when performing the evasive action.

[0104] It should be noted that the preprocessing module may include cameras, radars and infrared sensors, which perceive and collect environmental information around the target vehicle through cameras, radars and infrared sensors, wherein the environmental information includes but is not limited to: road condition information, traffic rules information, other vehicles or pedestrian information; and through deep learning, such as the error back propagation algorithm, the road condition information, traffic rules information, other vehicles or pedestrian information, etc. are identified and processed to obtain the emergency situation information.

[0105] Then, a path to avoid the emergency can be searched through the Dijkstra algorithm or the A-star algorithm; then, based on the environmental information, at least one avoidance action suitable for dealing with the current emergency can be obtained through a behavioral decision model, such as a finite state machine model or a decision tree model, such as turning, reducing speed, etc.

[0106] According to each of the avoidance actions, the avoidance motion trajectory can be obtained by a motion planning algorithm, such as a hybrid A-star algorithm, an RRT algorithm, or an artificial potential field method; combining the avoidance motion trajectory and the collected trajectories of other vehicles corresponding to the emergency situation, a Bayesian network model can be constructed to obtain the first probability of each of the avoidance actions.

[0107] a driving strategy generation module, the driving strategy generation module being configured to determine a safe action based on an avoidance action corresponding to the first probability being lower than a preset probability threshold, and to obtain a first safe driving strategy including the safe action;

[0108] A control module is used to control the target vehicle to drive according to the first safe driving strategy to avoid emergencies on the road.

[0109] The driving generation module compares each of the first probabilities with the probability threshold. When the first probability is less than the probability threshold, the corresponding evasive action is determined to be a safe action, and a first safe driving strategy including the safe action is obtained. The control module controls the target vehicle to execute the first safe driving strategy to avoid the sudden situation on the road. The control module may include an electronic control unit (ECU), which can control the steering, speed, gear position, etc. of the target vehicle. The preprocessing module obtains the first probability, thereby screening the evasive actions to determine the safe action, making the first safe driving strategy including the safe action more reliable. When the target vehicle executes the first safe driving strategy, the probability of collision with the other vehicle is also lower, thereby improving the safety of the target vehicle during driving.

[0110] In one embodiment, the step of the safe driving strategy generation module obtaining the first safe driving strategy including the safe action includes:

[0111] Obtaining a corresponding first action adjustment value according to each of the safety actions and the current driving action of the target vehicle;

[0112] Determine whether each of the first action adjustment values ​​is within a preset first action adjustment interval, and if the first action adjustment value is within the first action adjustment interval, obtain a first safe driving strategy including the safe action corresponding to the first action adjustment value.

[0113] In one embodiment, the step of obtaining, by the pre-processing module, the first probability corresponding to each of the avoidance actions includes:

[0114] Obtaining a second safe driving strategy corresponding to the other vehicle based on each of the avoidance actions, wherein when the other vehicle executes the second safe driving strategy, the other vehicle maintains a safe distance from the target vehicle;

[0115] Obtaining the dangerous driving strategies corresponding to the other vehicles according to each of the second safe driving strategies;

[0116] Obtain historical location information and historical driving status information of the other vehicle, obtain a second probability based on the historical location information and the historical driving status information, and obtain the first probability including the second probability, wherein the second probability is the probability that the other vehicle adopts the dangerous driving strategy.

[0117] In one embodiment, the step of obtaining the first probability corresponding to each of the avoidance actions by the pre-processing module further includes:

[0118] When the number of the other vehicles is two or more, obtaining a second probability corresponding to each of the other vehicles;

[0119] A third probability is obtained based on each of the second probabilities, and a first probability including the third probability is obtained, wherein the third probability is the probability that the target vehicle collides with one of the other vehicles. The mathematical expression for obtaining the third probability is:

[0120]

[0121] Wherein, P is the third probability, P(i) is each of the second probabilities, and n=1, ..., i.

[0122] In one embodiment, the step of the pre-processing module obtaining the second safe driving strategy corresponding to the other vehicles according to the avoidance action of each target vehicle includes:

[0123] Collecting the position information corresponding to the target vehicle according to each of the avoidance actions and the preset time intervals;

[0124] Obtaining a corresponding adjustment strategy based on each of the position information, wherein when the other vehicles execute the adjustment strategy and the target vehicle executes the evasive action, the other vehicles maintain a safe distance from the target vehicle;

[0125] The intersection of the adjustment strategies at each moment is taken to obtain the second safe driving strategy corresponding to the other vehicle.

[0126] In one embodiment, the step of the control module controlling the target vehicle to drive according to the first safe driving strategy to avoid an emergency on the road includes:

[0127] Obtaining a second action adjustment value corresponding to the first safe driving strategy based on each safety action included in the first safe driving strategy and the current driving action of the target vehicle;

[0128] adjusting the value according to the second action, determining whether the first safe driving strategy is urgent;

[0129] When it is determined that the first safe driving strategy is in an emergency, the target vehicle is controlled to drive according to the first safe driving strategy to avoid the emergency situation on the road.

[0130] In one embodiment, the control module adjusts the value according to the second action to determine whether the first safe driving strategy is urgent, including:

[0131] determining whether the second action adjustment value is within a preset second action adjustment range;

[0132] If so, determining that the first safe driving strategy is urgent;

[0133] If not, it is determined that the first safe driving strategy is not urgent, and the process returns to the step of collecting emergency information on the road.

[0134] The specific definition of the system for avoiding emergencies can be found in the definition of the method for avoiding emergencies above, and will not be repeated here. Each module in the above-mentioned system for avoiding emergencies can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0135] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for avoiding emergencies is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0136] Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0137] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed:

[0138] S1: Collecting emergency information on the road, determining at least one evasive action of the target vehicle based on the emergency information, and obtaining a first probability of each evasive action, wherein the first probability is a probability of the target vehicle colliding with another vehicle when executing the evasive action;

[0139] S2: determining a safe action according to the avoidance action corresponding to the first probability being lower than a preset probability threshold, and obtaining a first safe driving strategy including the safe action;

[0140] S3: Control the target vehicle to drive according to the first safe driving strategy to avoid unexpected situations on the road.

[0141] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0142] The step of obtaining a first safe driving strategy including the safe action comprises:

[0143] S21: Obtaining a corresponding first action adjustment value according to each of the safety actions and the current driving action of the target vehicle;

[0144] S22: Determine whether each of the first action adjustment values ​​is within a preset first action adjustment interval, and if the first action adjustment value is within the first action adjustment interval, obtain a first safe driving strategy including the safe action corresponding to the first action adjustment value.

[0145] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0146] The step of obtaining the first probability corresponding to each of the avoidance actions includes:

[0147] S101: Obtaining a second safe driving strategy corresponding to the other vehicle based on each of the avoidance actions, wherein when the other vehicle executes the second safe driving strategy, the other vehicle maintains a safe distance from the target vehicle;

[0148] S102: Obtaining dangerous driving strategies corresponding to the other vehicles according to each of the second safe driving strategies;

[0149] S103: Obtain historical location information and historical driving status information of the other vehicle, obtain a second probability based on the historical location information and the historical driving status information, and obtain the first probability including the second probability, wherein the second probability is the probability that the other vehicle adopts the dangerous driving strategy.

[0150] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0151] The step of obtaining the first probability corresponding to each of the avoidance actions further includes:

[0152] S111: When the number of the other vehicles is two or more, obtaining a second probability corresponding to each of the other vehicles;

[0153] S112: Obtain a third probability based on each of the second probabilities, and obtain a first probability including the third probability, wherein the third probability is a probability of the target vehicle colliding with one of the other vehicles. The mathematical expression for obtaining the third probability is:

[0154]

[0155] Wherein, P is the third probability, P(i) is each of the second probabilities, and n=1, ..., i.

[0156] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0157] The step of obtaining the second safe driving strategy corresponding to the other vehicles according to the avoidance action of each target vehicle includes:

[0158] S1021: Collecting the position information corresponding to the target vehicle according to each of the avoidance actions and a preset time interval;

[0159] S1022: Obtaining corresponding adjustment strategies based on the respective position information, wherein when the other vehicles execute the adjustment strategies and the target vehicle executes the evasive action, the other vehicles maintain a safe distance from the target vehicle;

[0160] S1023: Taking the intersection of the adjustment strategies at each moment to obtain the second safe driving strategy corresponding to the other vehicle.

[0161] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0162] The step of controlling the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road includes:

[0163] S31: Obtaining a second action adjustment value corresponding to the first safe driving strategy based on each safety action included in the first safe driving strategy and the current driving action of the target vehicle;

[0164] S32: adjusting the value according to the second action, and determining whether the first safe driving strategy is urgent;

[0165] S33: When it is determined that the first safe driving strategy is in an emergency, control the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road.

[0166] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0167] The step of adjusting the value according to the second action to determine whether the first safe driving strategy is urgent includes:

[0168] S321: Determine whether the second action adjustment value is within a preset second action adjustment range;

[0169] S322: If yes, determining that the first safe driving strategy is urgent;

[0170] S323: If not, it is determined that the first safe driving strategy is not urgent, and the process returns to the step of collecting emergency information on the road.

[0171] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0172] S1: Collecting emergency information on the road, determining at least one evasive action of the target vehicle based on the emergency information, and obtaining a first probability of each evasive action, wherein the first probability is a probability of the target vehicle colliding with another vehicle when executing the evasive action;

[0173] S2: determining a safe action according to the avoidance action corresponding to the first probability being lower than a preset probability threshold, and obtaining a first safe driving strategy including the safe action;

[0174] S3: Control the target vehicle to drive according to the first safe driving strategy to avoid unexpected situations on the road.

[0175] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0176] The step of obtaining a first safe driving strategy including the safe action comprises:

[0177] S21: Obtaining a corresponding first action adjustment value according to each of the safety actions and the current driving action of the target vehicle;

[0178] S22: Determine whether each of the first action adjustment values ​​is within a preset first action adjustment interval, and if the first action adjustment value is within the first action adjustment interval, obtain a first safe driving strategy including the safe action corresponding to the first action adjustment value.

[0179] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0180] The step of obtaining the first probability corresponding to each of the avoidance actions includes:

[0181] S101: Obtaining a second safe driving strategy corresponding to the other vehicle based on each of the avoidance actions, wherein when the other vehicle executes the second safe driving strategy, the other vehicle maintains a safe distance from the target vehicle;

[0182] S102: Obtaining dangerous driving strategies corresponding to the other vehicles according to each of the second safe driving strategies;

[0183] S103: Obtain historical location information and historical driving status information of the other vehicle, obtain a second probability based on the historical location information and the historical driving status information, and obtain the first probability including the second probability, wherein the second probability is the probability that the other vehicle adopts the dangerous driving strategy.

[0184] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0185] The step of obtaining the first probability corresponding to each of the avoidance actions further includes:

[0186] S111: When the number of the other vehicles is two or more, obtaining a second probability corresponding to each of the other vehicles;

[0187] S112: Obtain a third probability based on each of the second probabilities, and obtain a first probability including the third probability, wherein the third probability is a probability of the target vehicle colliding with one of the other vehicles. The mathematical expression for obtaining the third probability is:

[0188]

[0189] Wherein, P is the third probability, P(i) is each of the second probabilities, and n=1, ..., i.

[0190] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0191] The step of obtaining the second safe driving strategy corresponding to the other vehicles according to the avoidance action of each target vehicle includes:

[0192] S1021: Collecting the position information corresponding to the target vehicle according to each of the avoidance actions and a preset time interval;

[0193] S1022: Obtaining corresponding adjustment strategies based on the respective position information, wherein when the other vehicles execute the adjustment strategies and the target vehicle executes the evasive action, the other vehicles maintain a safe distance from the target vehicle;

[0194] S1023: Taking the intersection of the adjustment strategies at each moment to obtain the second safe driving strategy corresponding to the other vehicle.

[0195] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0196] The step of controlling the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road includes:

[0197] S31: Obtaining a second action adjustment value corresponding to the first safe driving strategy based on each safety action included in the first safe driving strategy and the current driving action of the target vehicle;

[0198] S32: adjusting the value according to the second action, and determining whether the first safe driving strategy is urgent;

[0199] S33: When it is determined that the first safe driving strategy is in an emergency, control the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0201] The step of adjusting the value according to the second action to determine whether the first safe driving strategy is urgent includes:

[0202] S321: Determine whether the second action adjustment value is within a preset second action adjustment range;

[0203] S322: If yes, determining that the first safe driving strategy is urgent;

[0204] S323: If not, it is determined that the first safe driving strategy is not urgent, and the process returns to the step of collecting emergency information on the road.

[0205] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0206] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0207] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for avoiding an emergency, characterized in that: include: Collecting emergency information on the road, determining at least one evasive action for a target vehicle based on the emergency information, and obtaining a first probability for each evasive action, wherein the first probability is a probability of the target vehicle colliding with another vehicle when executing the evasive action; Determining a safe action according to an avoidance action corresponding to the first probability being lower than a preset probability threshold, and obtaining a first safe driving strategy including the safe action; Controlling the target vehicle to drive according to the first safe driving strategy to avoid an emergency on the road; The step of obtaining the first probability corresponding to each of the avoidance actions includes: Obtaining a second safe driving strategy corresponding to the other vehicle based on each of the avoidance actions, wherein when the other vehicle executes the second safe driving strategy, the other vehicle maintains a safe distance from the target vehicle; Obtaining the dangerous driving strategies corresponding to the other vehicles according to each of the second safe driving strategies; Obtain historical location information and historical driving status information of the other vehicle, obtain a second probability based on the historical location information and the historical driving status information, and obtain the first probability including the second probability, wherein the second probability is the probability that the other vehicle adopts the dangerous driving strategy.

2. The method for avoiding an emergency according to claim 1, characterized in that: The step of obtaining a first safe driving strategy including the safe action comprises: Obtaining a corresponding first action adjustment value according to each of the safety actions and the current driving action of the target vehicle; Determine whether each of the first action adjustment values ​​is within a preset first action adjustment interval, and if the first action adjustment value is within the first action adjustment interval, obtain a first safe driving strategy including the safe action corresponding to the first action adjustment value.

3. The method for avoiding an emergency according to claim 1, characterized in that: The step of obtaining the first probability corresponding to each of the avoidance actions further includes: When the number of the other vehicles is two or more, obtaining a second probability corresponding to each of the other vehicles; A third probability is obtained based on each of the second probabilities, and a first probability including the third probability is obtained, wherein the third probability is the probability that the target vehicle collides with one of the other vehicles. The mathematical expression for obtaining the third probability is: Wherein, P is the third probability, P(i) is each of the second probabilities, and n=1, ..., i.

4. The method for avoiding an emergency according to claim 1, characterized in that: The step of obtaining the second safe driving strategy corresponding to the other vehicles according to the avoidance action of each target vehicle includes: Collecting the position information corresponding to the target vehicle according to each of the avoidance actions and the preset time intervals; Obtaining a corresponding adjustment strategy based on each of the position information, wherein when the other vehicles execute the adjustment strategy and the target vehicle executes the evasive action, the other vehicles maintain a safe distance from the target vehicle; The intersection of the adjustment strategies at each moment is taken to obtain the second safe driving strategy corresponding to the other vehicle.

5. The method for avoiding an emergency according to claim 1, characterized in that: The step of controlling the target vehicle to drive according to the first safe driving strategy to avoid the emergency on the road includes: Obtaining a second action adjustment value corresponding to the first safe driving strategy based on each safety action included in the first safe driving strategy and the current driving action of the target vehicle; adjusting the value according to the second action, determining whether the first safe driving strategy is urgent; When it is determined that the first safe driving strategy is in an emergency, the target vehicle is controlled to drive according to the first safe driving strategy to avoid the emergency situation on the road.

6. The method for avoiding an emergency according to claim 5, characterized in that: The step of adjusting the value according to the second action to determine whether the first safe driving strategy is urgent includes: determining whether the second action adjustment value is within a preset second action adjustment range; If so, determining that the first safe driving strategy is urgent; If not, it is determined that the first safe driving strategy is not urgent, and the process returns to the step of collecting emergency information on the road.

7. A system for avoiding emergencies, characterized in that: include: a preprocessing module configured to collect emergency information on the road, determine at least one evasive action for a target vehicle based on the emergency information, and obtain a first probability corresponding to each evasive action, wherein the first probability is a probability of the target vehicle colliding with another vehicle when executing the evasive action; a driving strategy generation module, the driving strategy generation module being configured to determine a safe action based on an avoidance action corresponding to the first probability being lower than a preset probability threshold, and to obtain a first safe driving strategy including the safe action; a control module, the control module being configured to control the target vehicle to drive according to the first safe driving strategy to avoid an emergency on the road; The step of obtaining the first probability corresponding to each of the avoidance actions by the pre-processing module includes: Obtaining a second safe driving strategy corresponding to the other vehicle based on each of the avoidance actions, wherein when the other vehicle executes the second safe driving strategy, the other vehicle maintains a safe distance from the target vehicle; Obtaining the dangerous driving strategies corresponding to the other vehicles according to each of the second safe driving strategies; Obtain historical location information and historical driving status information of the other vehicle, obtain a second probability based on the historical location information and the historical driving status information, and obtain the first probability including the second probability, wherein the second probability is the probability that the other vehicle adopts the dangerous driving strategy.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for avoiding an emergency situation according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for avoiding an emergency situation according to any one of claims 1 to 6 are implemented.

Images