Methods, devices, equipment, and storage media for constructing emergency risk fields for vehicle hazard avoidance

Abstract

The application discloses an emergency risk field construction method, device and equipment for vehicle safety, and a storage medium, wherein the method comprises the following steps: detecting surrounding obstacle information of a vehicle; constructing an obstacle risk field, a target risk field and a road boundary risk field of an emergency risk field according to an actual vehicle speed and the surrounding obstacle information of the vehicle; respectively calculating field forces of the vehicle subjected to the obstacle risk field, the target risk field and the road boundary risk field of the emergency risk field, obtaining a total field force of the vehicle, and generating a safe emergency stop path of the vehicle based on the total field force. Thus, the problems that related technologies cannot accurately quantify the driving risk under an emergency condition and cannot efficiently realize vehicle safety under the emergency condition are solved.

Description

Technical Field

[0001] This application relates to the field of intelligent connected vehicle decision-making technology, and in particular to a method, apparatus, device and storage medium for constructing an emergency risk field for vehicle risk avoidance. Background Technology

[0002] In recent years, autonomous driving and artificial intelligence have gradually gained national and societal attention. The intelligent connected vehicle sector, combining these two technologies, has formed a comprehensive system under national strategic and policy support, demonstrating promising development prospects. However, accidents caused by drivers losing control of their vehicles are frequent and alarming. The primary cause is sudden illness of the driver. Surveys show that drivers' high-intensity work and irregular schedules make them a high-risk group for sudden illnesses, leading to frequent traffic accidents involving loss of vehicle control. To achieve safe and efficient emergency stopping, vehicles need to avoid risk factors in the road environment, i.e., quantitatively assess potential road risks. Correct and efficient risk assessment methods can prevent secondary injuries in emergency scenarios; therefore, the emergency system for out-of-control vehicles should be based on risk assessment.

[0003] Currently, related technologies mainly rely on historical data to quantify risks or conduct safety assessments based on spatial and temporal safe distances. In addition, some related technologies can utilize driving risk field theory, which is applicable to complex driving scenarios and is a theory capable of accurately predicting the dynamic trends of driving risks.

[0004] However, the relevant technologies cannot accurately quantify driving risks in emergency situations, making it difficult to achieve efficient vehicle avoidance in emergency situations, which urgently needs to be addressed. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, and storage medium for constructing an emergency risk field for vehicle hazard avoidance, in order to solve the problems of related technologies being unable to accurately quantify driving risks in emergency situations and making it difficult to achieve efficient vehicle hazard avoidance in emergency situations.

[0006] The first aspect of this application provides a method for constructing an emergency risk field for vehicle hazard avoidance, comprising the following steps: detecting information about obstacles around the vehicle; constructing an obstacle risk field, a target risk field, and a road boundary risk field of the emergency risk field based on the actual speed of the vehicle and the information about obstacles around the vehicle; calculating the field forces exerted on the vehicle by the obstacle risk field, the target risk field, and the road boundary risk field of the emergency risk field, respectively, to obtain the total field force of the vehicle, and generating a safe emergency stop path for the vehicle based on the total field force.

[0007] Optionally, in one embodiment of this application, the surrounding obstacle information includes at least one of the actual position, actual heading angle, and actual speed of other vehicles.

[0008] Optionally, in one embodiment of this application, the step of constructing the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field based on the actual vehicle speed and the surrounding obstacle information includes: constructing the obstacle risk field based on a preset driving risk field theory and combined with the Doppler effect, wherein the expression of the obstacle risk field is:

[0009]

[0010] k y0 =1,

[0011] k xp =k x0 k yp =k y0 ,

[0012] Among them, E vij E represents the risk field strength generated by obstacle j at vehicle i. j0 E represents the kinetic energy of obstacle j. jp Let k be the relative kinetic energy of vehicle i relative to obstacle j; xp k yp r represents the risk gradient parameter in a relative reference frame, used to describe the non-uniformity of the risk posed to the vehicle by moving obstacles in different directions from a relative perspective; ij x ij y ij Let rj be the distance, horizontal distance, and vertical distance between obstacle j and vehicle i, respectively; r0 is a parameter to be determined; k x0 k y0 v represents the risk gradient parameter, describing the non-uniformity of the risk posed to the vehicle by moving obstacles in different directions; max is the maximum speed allowed for the car; sgn and sgn0 are symbolic functions.

[0013] Optionally, in one embodiment of this application, the step of constructing the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field based on the actual vehicle speed and the surrounding obstacle information further includes: in a positive power form, by comparing the smoothness of the planned path and the time to reach the target point to satisfy time-varying characteristics, to consider the Doppler effect of the moving target point, and combining the Doppler effect of the target point to construct the target risk field, wherein the expression of the target risk field is:

[0014]

[0015] k y0 =1,

[0016] kxp =k x0 k yp =k y0 ,

[0017]

[0018] Among them, E tar The target risk is strong in every field; E j0 E jp Let k be the absolute kinetic energy of vehicle i and the relative kinetic energy of vehicle i relative to target point j, respectively; xp k x0 k yp k y0 are the risk gradient parameters under absolute and relative viewpoints, respectively, representing the non-uniformity of the attraction tendency of target point j to the vehicle in different directions; r ij x ij y ij These represent the distance, horizontal distance, and vertical distance between vehicle i and target point j, respectively; v i v j The velocities of vehicle i and target point j are respectively; t i t represents the system startup time. j This is the maximum safe docking time for the system.

[0019] Optionally, in one embodiment of this application, the construction of the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field based on the actual vehicle speed and the surrounding obstacle information further includes: describing the road boundary risk field using a generalized molecular potential energy model based on the similarity between the road boundary risk field distribution and the molecular potential energy curve, wherein the expression of the road boundary risk field is:

[0020]

[0021]

[0022]

[0023] Where U is the potential energy of the risk field at the road boundary of the vehicle; A, B, m, and n are undetermined parameters, which are related to the road's own properties; r and r0 are the vertical distances between the center of the vehicle and the emergency lane and the road boundary, respectively.

[0024] A second aspect of this application provides an emergency risk field construction device for vehicle hazard avoidance, comprising: a detection module for detecting information about obstacles around the vehicle; a construction module for constructing an obstacle risk field, a target risk field, and a road boundary risk field of the emergency risk field based on the actual speed of the vehicle and the information about the surrounding obstacles; and a generation module for calculating the field forces exerted on the vehicle by the obstacle risk field, the target risk field, and the road boundary risk field of the emergency risk field, respectively, to obtain the total field force of the vehicle, and generating a safe emergency stop path for the vehicle based on the total field force.

[0025] Optionally, in one embodiment of this application, the surrounding obstacle information includes at least one of the actual position, actual heading angle, and actual speed of other vehicles.

[0026] Optionally, in one embodiment of this application, the construction module includes: an obstacle risk field construction unit, used to construct the obstacle risk field based on a preset driving risk field theory and combined with the Doppler effect, wherein the expression of the obstacle risk field is:

[0027]

[0028] k y0 =1,

[0029] k xp =k x0 k yp =k y0 ,

[0030] Among them, E vij E represents the risk field strength generated by obstacle j at vehicle i. j0 E represents the kinetic energy of obstacle j. jp Let k be the relative kinetic energy of vehicle i relative to obstacle j; xp k yp r represents the risk gradient parameter in a relative reference frame, used to describe the non-uniformity of the risk posed to the vehicle by moving obstacles in different directions from a relative perspective; ij x ij y ij Let rj be the distance, horizontal distance, and vertical distance between obstacle j and vehicle i, respectively; r0 is a parameter to be determined; k x0 k y0 v represents the risk gradient parameter, describing the non-uniformity of the risk posed to the vehicle by moving obstacles in different directions; max is the maximum speed allowed for the car; sgn and sgn0 are symbolic functions.

[0031] Optionally, in one embodiment of this application, the construction of the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field based on the actual vehicle speed and the surrounding obstacle information further includes: a target risk field construction unit, used to construct the target risk field in a positive power form by comparing the smoothness of the planned path and the time to reach the target point to satisfy time-varying characteristics, taking into account the Doppler effect of the moving target point, and combining the Doppler effect of the target point, wherein the expression of the target risk field is:

[0032]

[0033] k y0 =1,

[0034] k xp =k x0 k yp =k y0 ,

[0035]

[0036] Among them, E tar The target risk is strong in every field; E j0 E jp Let k be the absolute kinetic energy of vehicle i and the relative kinetic energy of vehicle i relative to target point j, respectively; xp k x0 k yp k y0 are the risk gradient parameters under absolute and relative viewpoints, respectively, representing the non-uniformity of the attraction tendency of target point j to the vehicle in different directions; r ij x ij y ij These represent the distance, horizontal distance, and vertical distance between vehicle i and target point j, respectively; v i v j The velocities of vehicle i and target point j are respectively; t i t represents the system startup time. j This is the maximum safe docking time for the system.

[0037] Optionally, in one embodiment of this application, the construction of the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field based on the actual vehicle speed and the surrounding obstacle information further includes: a road boundary risk field construction unit, used to describe the road boundary risk field using a generalized molecular potential energy model based on the similarity between the road boundary risk field distribution and the molecular potential energy curve, wherein the expression of the road boundary risk field is:

[0038]

[0039]

[0040]

[0041] Where U is the potential energy of the risk field at the road boundary of the vehicle; A, B, m, and n are undetermined parameters, which are related to the road's own properties; r and r0 are the vertical distances between the center of the vehicle and the emergency lane and the road boundary, respectively.

[0042] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the emergency risk field construction method for vehicle avoidance as described in the above embodiments.

[0043] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for constructing an emergency risk field for vehicle avoidance.

[0044] Therefore, the embodiments of this application have the following beneficial effects:

[0045] The system detects information about obstacles surrounding the vehicle; based on the vehicle's actual speed and the surrounding obstacle information, it constructs an obstacle risk field, a target risk field, and a road boundary risk field within the emergency risk field; it calculates the field forces exerted on the vehicle by the obstacle risk field, target risk field, and road boundary risk field within the emergency risk field, respectively, to obtain the total field force on the vehicle, and generates a safe emergency stopping path for the vehicle based on the total field force. This solves the problems of related technologies being unable to accurately quantify driving risks in emergency situations and achieving efficient vehicle avoidance in emergency situations.

[0046] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0047] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0048] Figure 1 This is a flowchart of an emergency risk field construction method for vehicle hazard avoidance according to an embodiment of this application;

[0049] Figure 2 This is a schematic diagram illustrating the basic components and corresponding relationships of a driving risk field according to an embodiment of this application;

[0050] Figure 3 This is a schematic diagram of the potential energy field of a driving risk field according to an embodiment of this application;

[0051] Figure 4 This is a schematic diagram of the kinetic energy field of a driving risk field according to an embodiment of this application;

[0052] Figure 5 This is a schematic diagram of the Doppler effect according to an embodiment of this application;

[0053] Figure 6 This is a schematic diagram of the obstacle field distribution of an obstacle vehicle in an emergency scenario according to an embodiment of this application;

[0054] Figure 7 This is a composite diagram of an obstacle risk field and a target risk field in an emergency scenario, according to an embodiment of this application.

[0055] Figure 8 This is a schematic diagram illustrating the parking of a vehicle under the influence of only obstacle risk fields and target risk fields, according to an embodiment of this application;

[0056] Figure 9 This is a schematic diagram of a molecular potential energy curve provided according to an embodiment of this application;

[0057] Figure 10 This is a schematic diagram of a road boundary risk field based on a molecular potential energy model, according to an embodiment of this application.

[0058] Figure 11 A composite diagram of three risk fields in an emergency scenario provided according to an embodiment of this application;

[0059] Figure 12 This is a schematic diagram illustrating the relationship between the combined field strength and the three individual field strengths according to an embodiment of this application;

[0060] Figure 13 This is a schematic diagram illustrating a basic concept of path planning according to an embodiment of this application;

[0061] Figure 14 This is an example diagram of an emergency risk field construction device for vehicle avoidance according to an embodiment of this application;

[0062] Figure 15 A schematic diagram of the structure of the electronic device provided in the application embodiment.

[0063] Explanation of reference numerals in the attached diagram: Emergency risk field construction device for vehicle avoidance - 10; Detection module - 100, Construction module - 200, Generation module - 300; Memory - 1501, Processor - 1502, Communication interface - 1503. Detailed Implementation

[0064] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0065] The following describes a method, apparatus, device, and storage medium for constructing an emergency risk field for vehicle avoidance, based on embodiments of the present application, with reference to the accompanying drawings. Addressing the problems mentioned in the background art, this application provides a method for constructing an emergency risk field for vehicle avoidance. In this method, information about obstacles surrounding the vehicle is detected; based on the vehicle's actual speed and the surrounding obstacle information, an obstacle risk field, a target risk field, and a road boundary risk field of the emergency risk field are constructed; the field forces exerted on the vehicle by the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field are calculated respectively to obtain the total field force on the vehicle; and a safe emergency stopping path for the vehicle is generated based on the total field force. Embodiments of this application not only enable faster emergency stopping, allowing the vehicle to stop quickly in an out-of-control state and minimizing the impact on the traffic system, but also allow the vehicle to stop in a safer posture, minimizing safety hazards after stopping. Therefore, this solves the problems of related technologies being unable to accurately quantify driving risks in emergency situations and struggling to achieve efficient vehicle avoidance in emergency situations.

[0066] Specifically, Figure 1 This is a flowchart illustrating a method for constructing an emergency risk field for vehicle hazard avoidance, as provided in an embodiment of this application.

[0067] like Figure 1 As shown, the method for constructing an emergency risk field for vehicle hazard avoidance includes the following steps:

[0068] In step S101, information about obstacles around the vehicle is detected.

[0069] It should be noted that, in one embodiment of this application, obstacle information around the vehicle can be detected by sensor devices such as ultrasonic or radar, or by using target recognition or semantic mapping technologies such as vehicle cameras, thereby obtaining relevant obstacle data in real time and efficiently, and providing reliable data support for subsequent vehicle avoidance.

[0070] Optionally, in one embodiment of this application, the surrounding obstacle information includes at least one of the actual position, actual heading angle, and actual speed of other vehicles.

[0071] It should be noted that the obstacle information mentioned above mainly includes the actual position, actual heading angle, and actual speed of other vehicles. After acquiring the obstacle information, the on-board sensor equipment inputs this information into the emergency system, thereby providing data support for vehicle safety and improving vehicle reliability and safety performance.

[0072] In step S102, the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field are constructed based on the vehicle's actual speed and surrounding obstacle information.

[0073] After obtaining information about obstacles around the vehicle, embodiments of this application can construct an emergency risk field based on the vehicle's actual speed and the information about obstacles around the vehicle.

[0074] Those skilled in the art will understand that the concept of constructing an emergency risk field is similar to the theory of driving risk field. The following will first introduce in detail the formation concept and basic model of the driving risk field.

[0075] Specifically, since people, vehicles, and roads are the three essential elements of a transportation system, driving risk can be used to characterize the degree of influence among them in order to accurately describe their interrelationships and mechanisms of action. First, the factors influencing driving risk mainly fall into three categories: the driver (person), road users (vehicles), and the road environment (road). Driver factors include the driver's skill level and personality traits; road user factors include the characteristics and movement states of motor vehicles and non-motor vehicles; and road environment factors include road-related factors and weather conditions.

[0076] Based on the aforementioned risk influencing factors, driving risks have four characteristics: objectivity, driving risks are objectively existing and do not change with human will; universality, driving risks are universally present, and accidents can occur anytime and anywhere; variability, driving risks are not static, but change with the changes in influencing factors; and measurability, driving risks have specific patterns and can be measured through prior judgment.

[0077] Similar to driving risk fields, physical fields also possess the above characteristics: objectivity, physical fields exist objectively; universality, physical fields are ubiquitous in life; variability, physical fields are functions of spatial coordinates and time, and therefore change with location and time; and measurability, physical fields can be described by values ​​such as field strength and potential energy, and therefore can be measured.

[0078] Therefore, based on the similarity between driving risk and physical fields, driving risk can be quantified using field theory.

[0079] In the theory of driving risk field, it is divided into three parts according to the type of influencing factors: potential energy field (describing the road), kinetic energy field (describing the vehicle), and behavioral field (describing the person), such as... Figure 2As shown. According to the characteristics of physical fields, the field strength of the driving risk field follows the parallelogram law, that is:

[0080] E s =E R +E v +E D (1)

[0081] Among them, E s For the overall strength of driving risk field, E R For potential energy fields to be strong, E v For kinetic field strength, E D For behavior field strength.

[0082] The potential energy field is a "physical field" that characterizes the impact of stationary objects on driving risks. It has the following characteristics: the greater the mass of the object, the greater the driving risk; the smaller the distance between the vehicle and the object, the greater the driving risk, and the faster the risk increases; the driving risk is the same regardless of which direction the vehicle approaches the object. Figure 3 As shown. Based on the above characteristics, the driving risk field is as follows:

[0083]

[0084] Among them, E Rij M is the potential energy field strength produced by object i at position j. i Let r be the equivalent mass of object i. ij Let G and R be the distance between objects i and j. i Both k1 and k2 are undetermined parameters.

[0085] The kinetic energy field is a "physical field" that characterizes the impact of moving objects on driving risks on a road. It has the following characteristics: the greater the mass of the object, the greater the driving risk; the closer the vehicle is to the object, the greater the driving risk, and the faster the risk increases; the risk is greater when the vehicle is in front of the object along its direction of motion, and less when it is behind the object along its direction of motion. Figure 4 As shown. Based on the above characteristics, the driving risk field is as shown in equation (3):

[0086]

[0087] Among them, E vij M is the kinetic energy field strength produced by the moving object i at position j. i Let r be the equivalent mass of the moving object i. ij v is the distance between moving objects i and j. i Let θ be the velocity of the moving object. i The direction of the velocity of the moving object is relative to r. ij The included angle, G, R i k1 and k2 are all parameters to be determined.

[0088] The behavioral field is a "physical field" that characterizes the magnitude of the impact of driver characteristics on driving risk. Driver characteristics can be characterized by driver risk factors (related to the driver's physiological and psychological factors). Therefore, the driving risk field is shown in equation (4):

[0089] E Dij =E vij D ri (4)

[0090] Among them, E Dij Let E be the field strength of the behavioral field generated by vehicle i at position j. vij Let D be the field strength of the kinetic energy field generated by vehicle i at position j. ri Risk factors for drivers.

[0091] The above is the basic model of the driving risk field theory, which is constructed based on two ideas: classification and analogical reasoning. Classification involves constructing different risk fields based on different objects. Analogical reasoning, on the other hand, constructs the risk field based on the similarity between driving risks and physical fields. The construction of the emergency risk field described below is also based on these two ideas within the framework of the driving risk field theory.

[0092] In emergency situations, the degree of danger posed to a vehicle can also be described as risk. The factors influencing this degree of danger primarily fall into three categories: other vehicles (obstacles), the target point, and road boundaries. Based on these three different risk sources, the emergency risk field can also be divided into three parts: the obstacle risk field, the target risk field, and the road boundary risk field. This provides theoretical support for constructing the risk field in emergency situations, further ensuring the safety and reliability of vehicles in such circumstances.

[0093] Optionally, in one embodiment of this application, constructing an obstacle risk field, a target risk field, and a road boundary risk field for an emergency risk field based on the vehicle's actual speed and surrounding obstacle information includes: constructing an obstacle risk field based on a preset driving risk field theory and incorporating the Doppler effect, wherein the expression for the obstacle risk field is:

[0094]

[0095] k y0 =1,

[0096] k xp =k x0 k yp =k y0 ,

[0097] Among them, E vij E represents the risk field strength generated by obstacle j at vehicle i. j0E represents the kinetic energy of obstacle j. jp Let k be the relative kinetic energy of vehicle i relative to obstacle j; xp k yp r represents the risk gradient parameter in a relative reference frame, used to describe the non-uniformity of the risk posed to the vehicle by moving obstacles in different directions from a relative perspective; ij x ij y ij Let rj be the distance, horizontal distance, and vertical distance between obstacle j and vehicle i, respectively; r0 is a parameter to be determined; k x0 k y0 v represents the risk gradient parameter, describing the non-uniformity of the risk posed to the vehicle by moving obstacles in different directions; max is the maximum speed at which a car is allowed to travel, equivalent to the wave speed in the Doppler effect; sgn and sgn0 are sign functions.

[0098] Specifically, in emergency situations, the obstacle risk field is a "physical field" characterizing the impact of obstacles on driving risks. It is a repulsive force field, manifested as the obstacle repelling the vehicle to prevent a collision. Since both the vehicle and the obstacle are in motion in most cases, the risk posed by the obstacle to the vehicle varies in different directions. For example, the risk posed by the obstacle along the direction of motion is significantly greater than the risk perpendicular to the direction of motion. Therefore, obstacles in emergency situations have the following characteristics: the greater the kinetic energy of the obstacle, the greater the risk to the vehicle; the greater the relative speed between the vehicle and the obstacle, the greater the risk posed by the obstacle, and the faster this increase; the risk posed by the obstacle to the vehicle is not uniform in different directions, with the greatest risk along the direction of the obstacle's movement.

[0099] Similarly, the Doppler effect exhibits similar characteristics. In physics, the Doppler effect refers to the phenomenon that the frequency of radiation emitted by an object changes with the relative motion between the object and the observer. When the observer is in front of the moving wave source, the emitted wave is compressed, and the observer's received frequency becomes higher; when the observer is behind the moving wave source, the emitted wave is stretched, and the observer's received frequency becomes lower.

[0100] Assume the wave source and the observer move along the same straight line, and the velocity of the wave source is v. S The frequency emitted by the wave source itself is ν S The observer's velocity is v R (taking the positive direction of motion toward the wave source), the frequency received by the observer is ν. R The speed of wave propagation in the medium is u, such as Figure 5 As shown, the Doppler formula is as follows:

[0101]

[0102] Therefore, equation (5) shows that the Doppler effect has similar characteristics: the higher the frequency emitted by the wave source, the higher the frequency received by the observer; the higher the relative speed between the wave source and the observer, the higher the frequency received by the observer; the influence of the wave source on the frequency received by the observer varies in different directions, with the greatest effect occurring in the opposite direction along the velocity of the wave source. Therefore, the obstacle risk field is constructed by combining the Doppler effect with the theory of driving risk field.

[0103] Referring to the form of the potential energy field of the driving risk field, and based on the similarity between the risk distribution characteristics and the Doppler effect, its risk distribution should be composed of many elliptical equipotential surfaces, resulting in the formulas shown in equations (6)-(7):

[0104]

[0105] k y0 =1 (7)

[0106] Among them, E vij E represents the risk field strength generated by obstacle j at vehicle i. j0 Let r be the kinetic energy of obstacle j. ij x ij y ij Let r0 be the distance, horizontal distance, and vertical distance between obstacle j and vehicle i, respectively; r0 is a parameter to be determined; and k is the distance between obstacle j and vehicle i. x0 k y0 v represents the risk gradient parameter, describing the non-uniformity of the risk posed to the vehicle by moving obstacles in different directions; max is the maximum speed allowed for the car, equivalent to the wave speed in the Doppler effect; sgn and sgn0 are sign functions, and their operation rules are shown in the following formula, used to determine whether the car is approaching or moving away from the obstacle.

[0107]

[0108] However, the risk distribution of moving obstacles described by equations (6)-(7) uses the ground as a reference frame, and this method still has certain shortcomings, such as when the obstacle is stationary, i.e., E j0 Substitute 0 into equation (6)-(7) to calculate E. vij =0, meaning that stationary obstacles pose no risk to the vehicle. This conclusion is obviously not realistic, so the model still needs to be revised.

[0109] Further investigation revealed that the reason for the aforementioned illogical result was because when E j0 =0, meaning the vehicle's kinetic energy is not zero, and the risk of collision between the vehicle and the stationary obstacle still exists. More precisely, the risk arises because "the relative speed between the vehicle and the obstacle is not zero." Therefore, the risk distribution for moving obstacles should include the relative motion term.

[0110] Therefore, by integrating the perspectives of absolute motion and relative motion, the expression for the obstacle risk field can be obtained by analogy, as shown in equations (9)-(11):

[0111]

[0112] k y0 =1(10)

[0113] k xp =k x0 k yp =k y0 (11)

[0114] Among them, E jp Let k be the relative kinetic energy of vehicle i relative to obstacle j. xp k yp The risk gradient parameter is defined in a relative reference frame and is used to describe the non-uniformity of the risk posed by moving obstacles to the vehicle in different directions from a relative perspective.

[0115] However, the obstacle risk field expressions in equations (9)-(11) contain two step function terms, sgn(x) and sgn0(x), which makes the obstacle risk field discontinuous at local points. This discontinuity may cause the vehicle to experience a large force rate at a certain instant, thus affecting passenger comfort and safety. Therefore, to ensure the continuity of the obstacle risk field, tanh(x) is used instead of the step function, resulting in the final expression of the obstacle risk field, as shown in equations (12)-(14):

[0116]

[0117] k y0 =1 (13)

[0118] k xp =k x0 k yp =k y0 (14)

[0119] For example, such as Figure 6 As shown, assuming only the influence of obstacle vehicle B is considered, car A and obstacle vehicle B are traveling in the same lane, and the speeds of car A and car B are in the same direction and related by v. A >v BAfter constructing the obstacle field according to equations (12)-(14), the risk field characteristics of obstacle vehicle B can be obtained: the density of equipotential surfaces in front of vehicle B is greater than that on the sides, and greater on the sides than behind. When vehicle A approaches vehicle B, vehicle A is subjected to a risk field strength opposite to its direction of motion, that is, it is subjected to a risk field force opposite to its direction of motion. At this time, the path planning algorithm will perform deceleration planning based on this, so that the vehicle avoids colliding with the obstacle, further improving the vehicle's safety performance.

[0120] Optionally, in one embodiment of this application, constructing the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field based on the vehicle's actual speed and surrounding obstacle information further includes: in a positive power form, comparing the smoothness of the planned path and the time to reach the target point to ensure time-varying characteristics, to consider the Doppler effect of the moving target point, and combining the Doppler effect of the target point to construct the target risk field, wherein the expression for the target risk field is:

[0121]

[0122] k y0 =1,

[0123] k xp =k x0 k yp =k y0 ,

[0124]

[0125] Among them, E tar The target risk is strong in every field; E j0 E jp Let k be the absolute kinetic energy of vehicle i and the relative kinetic energy of vehicle i relative to target point j, respectively; xp k x0 k yp k y0 are the risk gradient parameters under absolute and relative viewpoints, respectively, representing the non-uniformity of the attraction tendency of target point j to the vehicle in different directions; r ij x ij y ij These represent the distance, horizontal distance, and vertical distance between vehicle i and target point j, respectively; v i v j The velocities of vehicle i and target point j are respectively; t i t represents the system startup time. j This is the maximum safe docking time for the system.

[0126] Specifically, in emergency situations, the target risk field is a "physical field" characterizing the magnitude of the vehicle's tendency to move towards the planned target point. It is a gravitational field, manifested as the target point attracting the vehicle towards it. From the above theory, it can be seen that the driving risk field theoretical model and the obstacle risk field expression share a common point: the magnitude of the risk is only a function of spatial position, that is:

[0127] E=f(x) (15)

[0128] Where E represents the magnitude of the driving risk field, and x represents the position vector.

[0129] This is because under normal driving conditions, the risk level of a vehicle under the same circumstances (same obstacle distribution, same vehicle position and speed information) is independent of time; in emergency situations, the magnitude of the obstacle risk field experienced by the vehicle under the same circumstances is also almost independent of time. However, the target risk field is different. In the goal of achieving safe and efficient emergency stopping in an out-of-control vehicle emergency system, the existence of the target risk field is to ensure the efficiency of stopping, that is, for the vehicle to reach the vicinity of the target point as quickly as possible. This requires that the magnitude of the target risk field is related not only to spatial location but also to time, i.e.:

[0130] E = f(x, t) (16)

[0131] In summary, the target risk field has the following characteristics: the strength of the target risk field is a function of spatial location and time; the longer the system operates, the greater the attraction of the target point to the vehicle; the stronger the system operates, the greater the attraction rate of the target point to the vehicle should be. This is because the attraction of the target point to the vehicle increases with time, and the vehicle may have to take risks, such as passing through a place closer to the obstacle to reach the target point. Although this involves risky behavior, it will greatly shorten the time to reach the target point if successful, which is worth trying.

[0132] To satisfy the time-varying characteristics of the target risk field, the following methods can all be used, but the results of some experiments are not optimistic. The following table lists several methods that satisfy the time-varying characteristics and their experimental characteristics.

[0133] Table 1

[0134] proportional relationship Experimental characteristics Exponential form <![CDATA[E tar ∝e t ]]> The attraction trend increases too rapidly, increasing the risk of collision with obstacles. Logarithmic form <![CDATA[E tar ∝lnt]]> Attraction trends are increasing too slowly to adopt a risk-taking approach. Positive power form <![CDATA[E tar ∝t m (m>0)]]> The attraction trend increases moderately, allowing for a risk-taking approach when appropriate. Negative power form <![CDATA[E tar ∝t -m (m>0)]]> The attraction trend is decreasing, and the planned path is not smooth.

[0135] Based on the experimental results above, the positive power form best satisfies the time-varying characteristics. Furthermore, by comparing the smoothness of the planned path and the time to reach the target point under the positive power form, m=2 achieves better results; therefore, we adopt Ei. tar ∝t 2 .

[0136] Furthermore, unlike normal driving scenarios where the target point is relatively far from the initial position and its location is generally fixed, the target point in an emergency situation is not strictly required. It only needs to be selected from the nearest point in the center of the emergency lane. Therefore, in the path planning algorithm, the target point is movable. Similar to moving obstacles, the Doppler effect of the moving target point can be considered. Using analogical reasoning, it can be found that in t... 2 By adding a risk gradient parameter before the term and referring to equations (12)-(14) and combining them with the Doppler effect of the target point, the calculation formula for the target risk field is obtained, as shown in equations (17)-(21):

[0137]

[0138] k y0 =1 (18)

[0139] k xp =k x0 k yp =k y0 (19)

[0140]

[0141] k tp =k t0 (twenty one)

[0142] Among them, E tar The target risk is strong in every field; E j0 E jp Let k be the absolute kinetic energy of vehicle i and the relative kinetic energy of vehicle i relative to target point j, respectively; xp k x0 k yp k y0 are the risk gradient parameters under absolute and relative viewpoints, respectively, representing the non-uniformity of the attraction tendency of target point j to the vehicle in different directions; r ij x ij y ij These represent the distance, horizontal distance, and vertical distance between vehicle i and target point j, respectively; v i v j The velocities of vehicle i and target point j are respectively; t i t represents the system startup time. j This is the maximum safe docking time for the system, which is usually set manually (e.g., 10 seconds).

[0143] It should be noted that the risk function was constructed with explicit time in mind, which optimized the efficiency of emergency stops in emergency situations and provided a good foundation for the path planning algorithm.

[0144] For example, as Figure 7 shown, the host vehicle A and the obstacle vehicle B are in different lanes and the speed relationship v A > v B . At this time, the emergency system for out-of-control vehicles starts to work. In practical experience, it is a better method for vehicle A to cross vehicle B at risk and reach the emergency lane. However, in addition to the gravitational force of the target point, vehicle A is also subject to the repulsive force of the obstacle vehicle B. If the time-varying characteristics are not considered in the target risk field, when vehicle A attempts to cross in front of vehicle B, it will be subject to a repulsive force much greater than the gravitational force of the target point due to the too-close distance. At this time, vehicle A will be repelled and the risk-taking will fail. If the time-varying property is considered, initially vehicle A may fail in the risk-taking. However, as time increases, the gravitational force on vehicle A by the target point will increase exponentially. Eventually, after a period of time, it will be sufficient to resist the repulsive force of vehicle B and complete the risk-taking, and finally achieve docking, so that the host vehicle can reach the target point as soon as possible and complete emergency avoidance.

[0145] However, experiments have found that this docking method is not safe. Vehicle A does not complete parallel docking along the lane line direction at the center of the emergency lane, but completes inclined docking near the center line of the emergency lane. As Figure 8 shown, this unsafe docking method will pose a safety hazard. Therefore, this problem still needs to be solved by constructing a road boundary risk field.

[0146] Optionally, in an embodiment of the present application, according to the actual vehicle speed and surrounding obstacle information of the vehicle, an obstacle risk field, a target risk field and a road boundary risk field of the emergency risk field are constructed, and further include: according to the similarity between the distribution of the road boundary risk field and the molecular potential energy curve, a generalized molecular potential energy model is used to describe the road boundary risk field, where the expression of the road boundary risk field is:

[0147]

[0148]

[0149]

[0150] where U is the potential energy of the road boundary risk field at the host vehicle; A, B, m, n are undetermined parameters related to the road's own attributes; 2 < m < n, 2 < m is to ensure that the magnitude of the force on the host vehicle by the road boundary risk field is less than the force of the obstacle risk field, and m < n is to ensure that the road boundary risk field provides gravitational force when the distance is too far and repulsive force when the distance is too close; r and r0 are the perpendicular distances from the host vehicle and the center of the emergency lane to the road boundary, respectively.

[0151] Specifically, in an emergency, the road boundary risk field is a "physical field" that characterizes the risk magnitude generated by the road boundary on the host vehicle. It is a field that provides gravitational force at a long distance and repulsive force at a short distance, and its manifestation is to constrain the host vehicle to drive on the road without going out of the boundary. From Figure 8 It can be found that the target risk field only ensures the efficiency of the host vehicle's parking, and the safety of parking (whether the parking posture is safe) has not been guaranteed. Therefore, it is also hoped that the host vehicle can achieve parking safety under the action of the road boundary risk field.

[0152] Under the assumption of a sufficiently long straight road with a consistent road surface, the risk magnitude generated by the road boundary on the host vehicle only depends on the direction perpendicular to the road boundary and is independent of the direction parallel to the road boundary. Therefore, the road boundary risk field has the following properties: the force of the road boundary risk field on the host vehicle at the center of the emergency lane is zero; when the host vehicle is too close to the road boundary, the road boundary provides a repulsive force to the host vehicle to reach the center of the emergency lane; when the host vehicle is too far from the road boundary, the road boundary provides a gravitational force to the host vehicle to reach the center of the emergency lane; the host vehicle cannot cross the road boundary, so the potential energy value at the road boundary should be infinite; the force magnitude of the road boundary field on the host vehicle should be less than the obstacle field force of the moving obstacle on the host vehicle, otherwise when the host vehicle is too close to the obstacle, the repulsive force of the host vehicle by the obstacle will be too weak due to the road boundary field force being greater than the obstacle field force, and finally the host vehicle will collide with the obstacle.

[0153] Furthermore, it can be found that the distribution of the road boundary risk field is very similar to the molecular potential energy model. In physics, due to the existence of mutual forces between molecules, there is energy related to their relative positions, which is called molecular potential energy. When two molecules start to approach each other from infinity, the force between the molecules will gradually change from gravitational force to repulsive force, and there is a distance r0 where the force is zero, which is called the equilibrium distance. Therefore, when r = r0, the molecular potential energy takes the minimum value; when r < r0, the force between the molecules shows repulsive force; when r > r0, the force between the molecules shows gravitational force, as Figure 9 shown.

[0154] In addition, the molecular potential energy function curve of Lennard-Jones is shown as follows:

[0155]

[0156] where r is the distance between two molecules, and A and B are undetermined parameters.

[0157] The similarity of the molecular potential energy model can be obtained from Equation (22), that is, the force on the molecule at the equilibrium distance is zero; when a molecule is too close to another molecule, the other molecule provides a repulsive force to make the molecule reach the equilibrium distance; when a molecule is too far away from another molecule, the other molecule provides an attractive force to make the molecule reach the equilibrium distance; the distance between molecules cannot be zero, so the potential energy at zero distance is infinite; the magnitudes of the two terms in the expression of the molecular potential energy curve are r -6 and r -12 , which are much smaller than the magnitude of the Coulomb repulsive force r -2 .

[0158] Therefore, according to the similarity between the distribution of the road boundary risk field and the molecular potential energy curve, a generalized molecular potential energy model can be used to describe the road boundary risk field, as Figure 10 shown.

[0159]

[0160]

[0161] where U is the potential energy of the road boundary risk field at the ego-vehicle; A, B, m, and n are undetermined parameters related to the properties of the road itself; 2 < m < n, 2 < m is to ensure that the magnitude of the force on the ego-vehicle by the road boundary risk field is less than that of the obstacle risk field, and m < n is to ensure that the road boundary risk field provides an attractive force when the distance is too far and a repulsive force when the distance is too close; r and r0 are the perpendicular distances from the ego-vehicle and the center of the emergency lane to the road boundary, respectively.

[0162] From the relationship between force and potential energy:

[0163]

[0164] Equations (23)-(25) are the expressions of the road boundary risk field.

[0165] For example, as Figure 11 shown, the ego-vehicle A and the obstacle vehicle B are in different lanes respectively and the speed relationship v A > v BAt this point, the emergency system for out-of-control vehicles begins to function. First, the system constructs an obstacle risk field, a target risk field, and a road boundary risk field. Then, it calculates the field strength of the three risk fields affecting the vehicle's position. Since vehicle A is relatively close to obstacle vehicle B, the repulsive force dominates between the attractive force of the road boundary risk field and the repulsive force of the obstacle risk field. Therefore, the path planning algorithm will first actively avoid the obstacle and overtake. After passing obstacle vehicle B, the obstacle field force gradually decreases. At this point, the road boundary field force and the target field force become dominant. The target field force ensures efficient stopping, allowing the vehicle to quickly reach the emergency lane area; the road boundary field force ensures safe stopping, allowing the vehicle to accurately stop in the center of the emergency lane, ultimately achieving a safe and efficient emergency stop. This effectively prevents the vehicle from touching the road boundary, further improving the vehicle's reliability and safety performance.

[0166] Understandably, by establishing a road boundary risk field model based on the molecular potential energy model, the emergency system for out-of-control vehicles can better adapt to emergency scenarios, thus optimizing the problems of inaccurate parking positions and unsafe parking postures.

[0167] In step S103, the field forces of the vehicle under the emergency risk field, the obstacle risk field, the target risk field, and the road boundary risk field are calculated respectively to obtain the total field force of the vehicle, and a safe emergency stop path for the vehicle is generated based on the total field force.

[0168] After constructing three risk fields and calculating the three forces acting on the vehicle, the vehicle will calculate the total field strength. Since the field strength of each risk field is a vector, it follows the parallelogram law; therefore, the total field strength is the vector sum of the three individual field strengths, as follows: Figure 12 As shown, the greater the overall risk field strength, the more dangerous the vehicle's situation, and the more necessary it is for the vehicle to leave that position and reach a low-risk, safe location.

[0169] The magnitude of the field force on the vehicle's position due to the total risk field is calculated based on the total field strength calculated above, where it is assumed that the value of the field force is equal to the magnitude of the field strength.

[0170] Path planning is performed based on the magnitude of the field force acting on the vehicle. A path includes three pieces of information: position, velocity, and heading angle. After synthesizing the total field strength, the system will use the basic method of artificial potential field path planning to plan an effective path, where the magnitude and direction of the resultant force are the displacement changes between the current moment and the next moment, such as... Figure 13As shown. After path planning is completed, the system will add speed planning to the path, referring to some existing speed planning algorithms. The system will then make a judgment: if the distance between the next path point and the target point is less than a given value, the system will consider the vehicle to have achieved a safe emergency stop and will stop path planning; otherwise, the system will consider the vehicle to still be in a dangerous state and will re-collect the speed, position, and heading angle information of the vehicle and surrounding obstacles after the vehicle reaches the next path point, and conduct a new round of emergency risk field construction and path planning. This process continues, allowing the vehicle to plan an effective safe emergency stop path under the guidance of the emergency risk field. Under this planning, the vehicle can achieve a safe and efficient emergency stop. Therefore, the construction of the emergency risk field is the core factor determining the effectiveness of path planning.

[0171] Therefore, the embodiments of this application, by utilizing the theory of driving risk field and innovating the basic model of driving risk field to be applicable to emergency situations, solve the problem that driving risk field is difficult to accurately describe the magnitude of driving risk in emergency situations. This plays a key role in improving the efficiency and safety of route planning, and can minimize property damage and personal injury when the vehicle is out of control due to the driver's loss of driving ability, while ensuring the operational efficiency of the transportation system.

[0172] It should be noted that the above only provides one method for constructing an emergency risk field for vehicle risk avoidance, and does not negate the rationality of driving risk fields in normal driving scenarios. Researchers studying normal driving scenarios can still continue to use driving risk field theory.

[0173] The emergency risk field construction method for vehicle avoidance proposed in this application involves inputting the speed, position, and heading angle information of the vehicle and other vehicles; constructing an emergency risk field, including: constructing an obstacle risk field, a target risk field, and a road boundary risk field; then synthesizing the total emergency risk field according to the parallelogram law; calculating the magnitude of the field force on the vehicle's position from the total risk field; performing path planning based on the magnitude of the field force on the vehicle; and determining whether the vehicle has reached the target point. If it has, the system terminates; otherwise, it modifies and iterates the information of the vehicle and other vehicles, starting a new cycle. Therefore, the embodiments of this application enable vehicles to plan a safer and more efficient path when facing emergencies, thereby ensuring the safety of passengers, drivers, and the transportation system, and featuring high efficiency, high safety, and strong adaptability.

[0174] Next, referring to the accompanying drawings, an emergency risk field construction device for vehicle avoidance according to an embodiment of this application is described.

[0175] Figure 14 This is a block diagram of an emergency risk field construction device for vehicle avoidance according to an embodiment of this application.

[0176] like Figure 14As shown, the emergency risk field construction device 10 for vehicle avoidance includes: a detection module 100, a construction module 200, and a generation module 300.

[0177] The detection module 100 is used to detect information about obstacles around the vehicle.

[0178] Module 200 is used to construct the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field based on the vehicle's actual speed and surrounding obstacle information.

[0179] The generation module 300 is used to calculate the field forces of the vehicle in the emergency risk field, the obstacle risk field, the target risk field, and the road boundary risk field, respectively, to obtain the total field force of the vehicle, and to generate a safe emergency stop path for the vehicle based on the total field force.

[0180] Optionally, in one embodiment of this application, the surrounding obstacle information includes at least one of the actual position, actual heading angle, and actual speed of other vehicles.

[0181] Optionally, in one embodiment of this application, the construction module includes: an obstacle risk field construction unit, used to construct an obstacle risk field based on a preset driving risk field theory and combined with the Doppler effect, wherein the expression of the obstacle risk field is:

[0182]

[0183] k y0 =1,

[0184] k xp =k x0 k yp =k y0 ,

[0185] Among them, E vij E represents the risk field strength generated by obstacle j at vehicle i. j0 E represents the kinetic energy of obstacle j. jp Let k be the relative kinetic energy of vehicle i relative to obstacle j; xp k yp r represents the risk gradient parameter in a relative reference frame, used to describe the non-uniformity of the risk posed to the vehicle by moving obstacles in different directions from a relative perspective; ij x ij y ij Let rj be the distance, horizontal distance, and vertical distance between obstacle j and vehicle i, respectively; r0 is a parameter to be determined; k x0 k y0 v represents the risk gradient parameter, describing the non-uniformity of the risk posed to the vehicle by moving obstacles in different directions; maxis the maximum speed allowed for the car; sgn and sgn0 are symbolic functions.

[0186] Optionally, in one embodiment of this application, the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field are constructed based on the vehicle's actual speed and surrounding obstacle information. The system further includes a target risk field construction unit, used to construct the target risk field in a positive power form by comparing the smoothness of the planned path and the time to reach the target point to ensure time-varying characteristics, taking into account the Doppler effect of the moving target point, and combining the Doppler effect of the target point. The expression for the target risk field is:

[0187]

[0188] k y0 =1,

[0189] k xp =k x0 k yp =l y0 ,

[0190]

[0191] Among them, E tar The target risk is strong in every field; E j0 E jp Let k be the absolute kinetic energy of vehicle i and the relative kinetic energy of vehicle i relative to target point j, respectively; xp k x0 k yp k y0 are the risk gradient parameters under absolute and relative viewpoints, respectively, representing the non-uniformity of the attraction tendency of target point j to the vehicle in different directions; r ij x ij y ij These represent the distance, horizontal distance, and vertical distance between vehicle i and target point j, respectively; v i v j The velocities of vehicle i and target point j are respectively; t i t represents the system startup time. j This is the maximum safe docking time for the system.

[0192] Optionally, in one embodiment of this application, the obstacle risk field, target risk field, and road boundary risk field of the emergency risk field are constructed based on the vehicle's actual speed and surrounding obstacle information. The system further includes a road boundary risk field construction unit, used to describe the road boundary risk field using a generalized molecular potential energy model based on the similarity between the road boundary risk field distribution and the molecular potential energy curve. The expression for the road boundary risk field is:

[0193]

[0194]

[0195]

[0196] Where U is the potential energy of the risk field at the road boundary of the vehicle; A, B, m, and n are undetermined parameters, which are related to the road's own properties; r and r0 are the vertical distances between the center of the vehicle and the emergency lane and the road boundary, respectively.

[0197] It should be noted that the explanation of the above-mentioned embodiment of the emergency risk field construction method for vehicle avoidance also applies to the emergency risk field construction device for vehicle avoidance in this embodiment, and will not be repeated here.

[0198] The emergency risk field construction device for vehicle avoidance proposed in this application detects information about obstacles around the vehicle; constructs an obstacle risk field, a target risk field, and a road boundary risk field of the emergency risk field based on the vehicle's actual speed and the surrounding obstacle information; calculates the field forces exerted on the vehicle by the obstacle risk field, the target risk field, and the road boundary risk field of the emergency risk field, respectively, to obtain the total field force on the vehicle, and generates a safe emergency stopping path for the vehicle based on the total field force. The embodiments of this application not only enable faster emergency stopping, allowing the vehicle to stop quickly in a state of loss of control and minimizing the impact on the traffic system, but also allow the vehicle to stop in a safer posture, minimizing safety hazards after stopping.

[0199] Figure 15 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0200] The memory 1501, the processor 1502, and the computer program stored on the memory 1501 and executable on the processor 1502.

[0201] When the processor 1502 executes the program, it implements the emergency risk field construction method for vehicle avoidance provided in the above embodiments.

[0202] Furthermore, electronic devices also include:

[0203] Communication interface 1503 is used for communication between memory 1501 and processor 1502.

[0204] The memory 1501 is used to store computer programs that can run on the processor 1502.

[0205] The memory 1501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0206] If the memory 1501, processor 1502, and communication interface 1503 are implemented independently, then the communication interface 1503, memory 1501, and processor 1502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 15 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0207] Optionally, in a specific implementation, if the memory 1501, processor 1502, and communication interface 1503 are integrated on a single chip, then the memory 1501, processor 1502, and communication interface 1503 can communicate with each other through an internal interface.

[0208] The processor 1502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0209] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for constructing an emergency risk field for vehicle avoidance.

[0210] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0211] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0212] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0213] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0214] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0215] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0216] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0217] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A vehicle risk avoidance method based on an emergency risk field construction, characterized in that, The method comprises the following steps: detecting surrounding obstacle information of a vehicle; constructing an obstacle risk field, a target risk field and a road boundary risk field of an emergency risk field according to an actual vehicle speed of the vehicle and the surrounding obstacle information; calculating field forces of the vehicle subjected to the obstacle risk field, the target risk field and the road boundary risk field of the emergency risk field respectively to obtain a total field force of the vehicle, and generating a safe emergency stop path of the vehicle based on the total field force, and controlling the vehicle to take refuge according to the safe emergency stop path; the constructing an obstacle risk field, a target risk field and a road boundary risk field of an emergency risk field according to an actual vehicle speed of the vehicle and the surrounding obstacle information comprises: constructing the obstacle risk field based on a preset driving risk field theory in combination with a Doppler effect, wherein an expression of the obstacle risk field is: ， ， ， ， wherein, is the obstacle is the ego vehicle is the risk field strength generated at the ego vehicle is the obstacle is the kinetic energy size of the obstacle is the ego vehicle is the relative kinetic energy of the obstacle is the relative kinetic energy of the obstacle is the risk gradient parameter in the relative reference frame, which describes the non-uniformity of the moving obstacle generating risk to the ego vehicle in different directions; , , is the distance, horizontal distance and vertical distance of the obstacle and the ego vehicle , is the undetermined parameter; , is the risk gradient parameter, which describes the non-uniformity of the moving obstacle generating risk to the ego vehicle in different directions; is the maximum speed allowed for the vehicle to travel; is the speed of the ego vehicle ; is the speed of the obstacle ; is the horizontal position of the ego vehicle ; is the horizontal position of the obstacle ; the constructing an obstacle risk field, a target risk field and a road boundary risk field of an emergency risk field according to an actual vehicle speed of the vehicle and the surrounding obstacle information further comprises: in a positive power form, the target risk field is constructed in combination with a Doppler effect of a target point by comparing smoothness of a planned path and time to reach the target point to satisfy time-varying characteristics, wherein an expression of the target risk field is: ， ， ， ， ， ， in, The target risk is high in every situation; Bicycles Absolute kinetic energy, self-propelled vehicle relative target point The relative kinetic energy; These are the risk gradient parameters under absolute and relative perspectives, respectively, representing the target point. The non-uniformity of the attraction tendency of the vehicle in different directions; Bicycles With the target point The distance, horizontal distance, and vertical distance; Bicycles With the target point speed; For system startup time, This is the maximum safe docking time for the system; This represents the time parameter of the risk gradient from an absolute perspective; This represents the time parameter of the risk gradient from a relative perspective; The parameter to be determined; Indicates a bicycle Horizontal position; Indicates obstacles Horizontal position; This refers to the maximum speed at which a car is permitted to travel. the constructing an obstacle risk field, a target risk field and a road boundary risk field of an emergency risk field according to an actual vehicle speed of the vehicle and the surrounding obstacle information further comprises: a generalized molecular potential energy model is adopted to describe the road boundary risk field according to similarity between a road boundary risk field distribution and a molecular potential energy curve, wherein an expression of the road boundary risk field is: ， ， ， wherein, is the potential energy of the road boundary risk field at the ego vehicle; A, B, m, n are undetermined parameters, which are related to the properties of the road, and wherein, so that the magnitude of the force of the road boundary risk field acting on the ego vehicle is less than the force of the obstacle risk field, so that the road boundary risk field provides an attractive force when the distance is greater than a preset distance threshold, and the road boundary risk field provides a repulsive force when the distance is less than the preset distance threshold; respectively represent the vertical distance between the ego vehicle, the center of the emergency lane and the road boundary; represents the field force of the road boundary risk field acting on the ego vehicle.

2. The method of claim 1, wherein, The surrounding obstacle information comprises at least one of actual positions, actual heading angles and actual speeds of other vehicles.

3. A vehicle risk avoidance device based on an emergency risk field construction, characterized by, comprises: a detection module configured to detect surrounding obstacle information of a vehicle; a construction module configured to construct an obstacle risk field, a target risk field and a road boundary risk field of an emergency risk field according to an actual vehicle speed of the vehicle and the surrounding obstacle information; a generation module configured to calculate field forces of the vehicle subjected to the obstacle risk field, the target risk field and the road boundary risk field of the emergency risk field respectively to obtain a total field force of the vehicle, and generate a safe emergency stop path of the vehicle based on the total field force, and control the vehicle to take refuge according to the safe emergency stop path; wherein the construction module comprises: an obstacle risk field construction unit configured to construct the obstacle risk field based on a preset driving risk field theory in combination with a Doppler effect, wherein an expression of the obstacle risk field is: ， ， ， ， in, For obstacles In the car The risk field strength generated at that location; Obstacles The magnitude of kinetic energy; For bicycle relative obstacles The relative kinetic energy; The risk gradient parameter is used to describe the non-uniformity of the risk posed by moving obstacles to the vehicle in different directions from a relative perspective. , , Obstacles With bicycle The distance, horizontal distance, and vertical distance. These are parameters to be determined. , The risk gradient parameter describes the non-uniformity of the risk posed by moving obstacles to the vehicle in different directions; This refers to the maximum speed at which a car is permitted to travel. Indicates a bicycle speed; Indicates obstacles speed; Indicates a bicycle Horizontal position; Indicates obstacles Horizontal position; the constructing an obstacle risk field, a target risk field and a road boundary risk field of an emergency risk field according to an actual vehicle speed of the vehicle and the surrounding obstacle information further comprises: a target risk field construction unit configured to construct the target risk field in combination with a Doppler effect of a target point in a positive power form by comparing smoothness of a planned path and time to reach the target point to satisfy time-varying characteristics, wherein an expression of the target risk field is: ， ， ， ， ， ， in, The target risk is high in every situation; Bicycles Absolute kinetic energy, self-propelled vehicle relative target point The relative kinetic energy; These are the risk gradient parameters under absolute and relative perspectives, respectively, representing the target point. The non-uniformity of the attraction tendency of the vehicle in different directions; Bicycles With the target point The distance, horizontal distance, and vertical distance; Bicycles With the target point speed; For system startup time, This is the maximum safe docking time for the system; This represents the time parameter of the risk gradient from an absolute perspective; This represents the time parameter of the risk gradient from a relative perspective; The parameter to be determined; Indicates a bicycle Horizontal position; Indicates obstacles Horizontal position; This refers to the maximum speed at which a car is permitted to travel. The obstacle risk field, the target risk field and the road boundary risk field are constructed according to the actual vehicle speed of the vehicle and the surrounding obstacle information, and further include: The road boundary risk field construction unit is configured to describe the road boundary risk field by using a generalized molecular potential model according to similarity between a road boundary risk field distribution and a molecular potential curve, and an expression of the road boundary risk field is: ， ， ， wherein, is the potential energy of the road boundary risk field at the ego vehicle; A, B, m, n are undetermined parameters, which are related to the properties of the road, and wherein, so that the magnitude of the force of the road boundary risk field acting on the ego vehicle is less than the force of the obstacle risk field, so that the road boundary risk field provides an attractive force when the distance is greater than a preset distance threshold, and the road boundary risk field provides a repulsive force when the distance is less than the preset distance threshold; respectively, the vertical distance from the ego vehicle, the center of the emergency lane and the road boundary; represents the field force of the road boundary risk field acting on the ego vehicle.

4. The apparatus of claim 3, wherein, The surrounding obstacle information includes at least one of an actual position, an actual heading angle and an actual speed of another vehicle.

5. An electronic device, comprising: The computer program is stored in the memory and executable on the processor, and the processor executes the program to implement the vehicle risk avoidance method based on the emergency risk field construction according to any one of claims 1-2. The program is executed by the processor to implement the vehicle risk avoidance method based on the emergency risk field construction according to any one of claims 1-2.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, ​

Images