A road risk map generation method and system based on safety potential field

Abstract

The present invention discloses a method for generating a road risk map based on a safety potential field, and the specific steps are as follows: by collecting data information of various external traffic entities, using the safety potential field theory to analyze the road line type and lane division data, road boundary data, and vehicle data, a corresponding potential field model is constructed, a road risk map is generated, and it is provided to the driver in real time; the road risk map generation system of the present invention includes a data acquisition module, a potential field model construction module, a field strength calculation module, a road cutting module, a map generation module, and an early warning information module; each module executes its storage execution instruction respectively and works in coordination to realize the road risk map generation method. The present invention can display the level of safety risks within the time and space range of the road, and can grasp the distribution of road risks from a macro level. At the same time, because the "aggregate field strength" contains the field strength information of the environmental information field, it can provide lane-level risk early warning prompts for vehicles.

Description

Technical Field

[0001] The present invention relates to a method and system for generating a road risk map, and in particular to a method and system for generating a road risk map based on a safety potential field. Background Art

[0002] With the development of social economy, the number of cars has increased significantly, and traffic accidents have become more frequent. As the main cause of traffic accidents, the driver's understanding of road risk information during vehicle driving has a great impact on the safety of vehicle driving. However, for the generation and provision of road risk information, existing technologies mostly focus on providing road risks that only consider the influence of a single factor, or road risks generated in static scenes, or road risks generated for a certain type of scene, which makes the generated road risks inaccurate, and most of them cannot provide road risk information to drivers in real time.

[0003] Therefore, when generating road risks, it is necessary to comprehensively consider various factors in the external environment, such as surrounding vehicle information, forward accident information, traffic signal cycle information, etc., and then generate corresponding road risks, and provide road risk information to the driver in real time, so that the driver can have a more comprehensive understanding of the road risk situation, further ensure driving safety, and reduce the traffic accident rate. Summary of the invention

[0004] Purpose of the invention: The purpose of the present invention is to provide a method and system for generating a road risk map based on a safety potential field, which can generate risk situations in real time and provide them to drivers and can be applied to the entire road network.

[0005] Technical solution: The road risk map generation method of the present invention comprises the following steps:

[0006] S1, obtain the self-attribute information and motion state information of different traffic entities in the road environment;

[0007] S2, design different safety potential field models and weight parameters according to the properties and motion states of different traffic entities;

[0008] S3, according to different safety potential field models, calculate the local potential field strength of various types of traffic entities at the current moment, and perform a superposition process of the potential field strength according to their respective weight parameters;

[0009] S4, using space grid units of uniform size to cut the road space plane, and mapping the safety potential field after superposition processing with the discretized road space grid, and calculating the field intensity aggregation value inside the entire space unit according to the field intensity value of the grid unit boundary;

[0010] S5, according to the value of "aggregate field strength" in each discrete grid, a road risk map is obtained by performing spatiotemporal correlation, and the risk map is sent to the driver.

[0011] Furthermore, in step S1, the specific steps of obtaining the self-attribute information and motion state information of different traffic entities in the road environment include:

[0012] S101, using a visual perception device to identify the attributes of different traffic entities on the road, where the traffic entity attributes include: road sign and marking attributes, signal light parameter information, vehicle type information, and obstacle size information;

[0013] S102, using radar equipment and sensor equipment to obtain movement information of different traffic entities, the movement information of the traffic entity including: position information, speed information, acceleration information and steering angle information.

[0014] Furthermore, in step S2, the specific steps of designing different safety potential field models and weight parameters according to the properties and motion states of different traffic entities include:

[0015] S201, according to the basic composition of road traffic, the safety potential field is divided into a road line field, a road boundary field and a vehicle potential field, and the corresponding safety potential field model category is determined according to the own attributes and motion state of each traffic subject;

[0016] S202, based on the safety potential field theory, construct a road line field model:

[0017]

[0018] Among them, E L is the potential field strength of the road line field; s is the identification number of different types of roads, s = 1, 2, ..., n; j is the identification number of different road line fields, j = 1, 2, ..., n; A s Different potential field strength coefficients generated for different road marking types; is the distance vector of vehicle A pointing to the road line; σ is the speed at which the potential field strength value increases or decreases;

[0019] S203, according to the vehicle operation characteristics, the potential field strength of the road boundary field approaches infinity as the vehicle gradually approaches, and a road boundary field model is constructed:

[0020]

[0021] Among them, E s is the potential field strength of the road boundary field; e is the identification number of the road boundary lines on the left and right sides, e=1, 2, where e=1 represents the left road boundary line, and e=2 represents the right road boundary line; η is the road boundary field coefficient; Represents the distance vector from vehicle A to the road boundary line;

[0022] S204, calculate the equivalent mass M of the target vehicle i according to the composition characteristics of the vehicle's own attributes i :

[0023] M i =m i ·(1.566×10 -14 ·v 6.687 +0.3345)

[0024] Among them, m i is the actual mass of target vehicle i; v is the driving speed of target vehicle i;

[0025] S205, according to the characteristics of the vehicle's motion state, calculate the distance |l′| from the point (x, y) in space to the center of mass of the vehicle:

[0026]

[0027] Among them, (x0, y0) is the spatial coordinate of the center of mass of the target vehicle; τ is the critical threshold of the safety distance; v is the current speed of the vehicle; α is a parameter to be determined related to the speed; e is the base of the natural logarithm function;

[0028] S206: construct a vehicle potential field model based on the vehicle's own attributes and motion characteristics:

[0029]

[0030] Among them, E v is the potential field strength of the vehicle potential field; λ, β1 and ζ are unknown coefficients; θ is the angle between a point around the target vehicle and the spatial coordinates (x0, y0) of the center of mass of the vehicle; a is the acceleration of the target vehicle in its current motion state; l′ is a vector, expressed as is a unit vector, indicating the direction from the point (x, y) in space to the center of mass of the target vehicle;

[0031] S207, designing various potential field strength weights according to different potential field types corresponding to different traffic entities and their impact on vehicle safety.

[0032] Furthermore, in step S3, the local potential field strength of each type of traffic subject at the current moment is calculated according to different safety potential field models, and the potential field strength is superimposed according to the respective weight parameters to calculate the potential field strength model E of the safety total potential field. total :

[0033]

[0034] Among them, ωL ,ω S ,ω V They are the potential field strength weights of the road line field, the potential field strength weights of the road boundary field, and the potential field strength weights of the vehicle potential field.

[0035] Further, in step S4, the road space plane is cut using space grid units of uniform size, and the safety potential field after superposition processing is mapped with the discretized road space grid, and the field intensity aggregation value inside the entire space unit is calculated according to the field intensity value of the grid unit boundary. The specific steps include:

[0036] S401, the road space is cut into space grid units of uniform size, and the length of each grid unit is l g , width is l d ;

[0037] S402, projecting the safety potential field after the superposition processing onto the gridded road to obtain a safety potential field mapped to the road space grid;

[0038] S403, calculating the field intensity concentration value E inside the entire space unit according to the field intensity value of the grid unit boundary i :

[0039]

[0040] Among them, E A 、E B 、E C 、E D They represent the potential field strength values ​​at the midpoints of the four sides of space unit i respectively.

[0041] A road risk map generation system based on a safety potential field includes a data acquisition module, a potential field model construction module, a field strength calculation module, a road cutting module, a map generation module, and an early warning information module; each module executes its stored execution instructions respectively and works together to implement any road risk map generation method; the execution instructions of each module are as follows:

[0042] Data acquisition module: obtains the self-attribute information and motion status information of different traffic entities in the road environment;

[0043] Potential field model construction module: design different safety potential field models and weight parameters according to the properties and motion states of different traffic entities;

[0044] Field strength calculation module: According to different safety potential field models, calculate the local potential field strength of various traffic entities at the current moment, and perform potential field strength superposition processing according to their respective weight parameters;

[0045] Road cutting module: Use space grid units of uniform size to cut the road space plane, map the superimposed safety potential field with the discretized road space grid, and calculate the field strength aggregation value inside the entire space unit according to the field strength value at the grid unit boundary;

[0046] Map generation module: The road risk map is obtained by performing spatiotemporal correlation based on the values ​​of “aggregated field strength” in each discrete grid;

[0047] Warning information module: sends road risk map to the driver.

[0048] Furthermore, the data acquisition module specifically includes an attribute information acquisition module and a motion state information acquisition module:

[0049] Attribute information acquisition module: Use visual perception equipment to identify the attributes of different traffic entities on the road. The attributes of traffic entities include: road sign and marking attributes, signal light parameter information, vehicle type information, and obstacle size information;

[0050] Motion status information acquisition module: uses radar equipment and sensor equipment to acquire the motion information of different traffic entities. The motion information of traffic entities includes: position information, speed information, acceleration information and steering angle information.

[0051] Furthermore, the potential field model building module includes a local potential field model building module and a weighting module:

[0052] Local potential field model construction module: According to the basic composition of road traffic, the safety potential field is divided into road line field, road boundary field and vehicle potential field, and the road line field model is constructed according to the safety potential field theory; the road boundary field model is constructed according to the vehicle operation characteristics; the vehicle potential field model is constructed according to the vehicle's own attributes and movement characteristics;

[0053] Weight assignment module: assign weights to various potential field strengths based on the different potential field types corresponding to different traffic entities and the strength relationship of their impact on vehicle safety.

[0054] Furthermore, the road cutting module specifically includes a road grid division module, a safety potential field mapping module and a gathering field strength calculation module:

[0055] Divide the road grid module: divide the road space into spatial grid units of uniform size, and the length of each grid unit is l g , width is l d ;

[0056] Safety potential field mapping module: maps the safety potential field after superposition processing with the discretized road space grid;

[0057] Aggregate field strength calculation module: Calculates the field strength aggregation value inside the entire space unit based on the field strength value at the grid unit boundary.

[0058] Compared with the prior art, the present invention has the following significant effects:

[0059] 1. In the present invention, since the "aggregated field strength" includes the field strength information of the environmental information field, external environmental factors such as road line type and lane division are fully considered in the road risk map, which can provide lane-level risk warning prompts for vehicles and display the level of safety risks within the time and space range of the road through the road risk map; the distribution of road risks can be grasped from a macro level, which can further improve the safety of the road;

[0060] 2. The present invention collects data information of various external traffic entities, uses the safety potential field theory to analyze the road line type and lane division data, road boundary data, and vehicle data, constructs a corresponding potential field model, generates a road risk map, and provides it to the driver in real time, thereby solving the problems of inaccurate road risk information and unrealistic information provision, and providing technical support for the formulation of reasonable and efficient traffic management control plans;

[0061] 3. The present invention proposes a method for generating a map that can comprehensively reflect road risk information based on a safety potential field using the acquired road environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a schematic diagram of the process of the present invention;

[0063] Figure 2 It is a schematic diagram of the superposition of the road line field model and the road boundary field model in an embodiment of the present invention;

[0064] Figure 3 A schematic diagram of a vehicle potential field model in an embodiment of the present invention;

[0065] Figure 4 It is a schematic diagram of the results of superimposing various types of safety potential fields in an embodiment of the present invention;

[0066] Figure 5 Schematic diagram of road space plane cutting in an embodiment of the present invention;

[0067] Figure 6 Schematic diagram of mapping the road space plane and the superimposed safety potential field in an embodiment of the present invention;

[0068] Figure 7 A schematic diagram of key points when calculating the field intensity concentration value inside a space unit in an embodiment of the present invention;

[0069] Figure 8 A schematic diagram of generating a road risk map in an embodiment of the present invention;

[0070] Fig. 9 It is a schematic diagram of the structure of the system of the present invention. DETAILED DESCRIPTION

[0071] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. The embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, any other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0072] like Figure 1 As shown, the road risk map generation method of the present invention specifically includes the following steps:

[0073] S1, obtain the self-attribute information and motion status information of different traffic entities in the road environment, specifically:

[0074] S101, using visual perception equipment to identify the attributes of different traffic entities on the road, where the attributes of the traffic entity include: road sign and marking attributes, signal light parameter information, vehicle type information, obstacle size information, etc.;

[0075] S102, using radar equipment and sensor equipment to obtain movement information of different traffic entities, the movement information of the traffic entity includes: position information, speed information, acceleration information, steering angle information, etc.

[0076] S2, according to the properties and motion states of different traffic entities, design different safety potential field models and weight parameters, specifically:

[0077] S201, according to the basic composition of road traffic, the safety potential field is divided into three categories: road line field, road boundary field and vehicle potential field, and the corresponding safety potential field model category is determined according to the own attributes and motion state of each traffic subject;

[0078] S202, based on the safety potential field theory, construct a road line field model, such as Figure 2 As shown,

[0079]

[0080] Among them, E L is the potential field strength of the road line field; s is the identification number of different types of roads, s = 1, 2, ..., n; j is the identification number of different road line fields, j = 1, 2, ..., n; A s Different potential field strength coefficients generated for different road marking types; is the distance vector of vehicle A pointing to the road line; σ is the speed at which the potential field strength value increases or decreases;

[0081] S203, such as Figure 2 As shown in the figure, according to the vehicle operation characteristics, the potential field strength of the road boundary field approaches infinity as the vehicle gradually approaches, and the road boundary field model is constructed:

[0082]

[0083] Among them, E s is the potential field strength of the road boundary field; e is the identification number of the road boundary lines on the left and right sides, e = 1, 2 (usually e = 1 represents the left road boundary line, e = 2 represents the right road boundary line); η is the road boundary field coefficient; Represents the distance vector from vehicle A to the road boundary line;

[0084] S204, calculate the equivalent mass M of the target vehicle i according to the composition characteristics of the vehicle's own attributes i :

[0085] M i =m i ·(1.566×10 -14 ·v 6.687 +0.3345) (3)

[0086] Among them, m i is the actual mass of target vehicle i; v is the driving speed of target vehicle i;

[0087] S205, according to the characteristics of the vehicle's motion state, calculate the distance |l′| from the point (x, y) in the space to the center of mass of the vehicle,

[0088]

[0089] Among them, (x0, y0) is the spatial coordinate of the center of mass of the target vehicle; τ is the critical threshold of the safety distance; v is the current speed of the vehicle; α is a parameter to be determined related to the speed; e is the base of the natural logarithm function;

[0090] S206, such as Figure 3 As shown in the figure, the vehicle potential field model is constructed based on the vehicle's own properties and motion characteristics:

[0091]

[0092] Among them, E v is the potential field strength of the vehicle potential field; λ, β1 and ζ are unknown coefficients; θ is the angle between a point around the target vehicle and the spatial coordinates (x0, y0) of the center of mass of the vehicle; a is the acceleration of the target vehicle in its current motion state; l′ is a vector, expressed as is a unit vector, indicating the direction from the point (x, y) in space to the center of mass of the target vehicle;

[0093] S207, designing strength weights of various potential fields according to different potential field types corresponding to different traffic entities and the strength relationship of their impact on vehicle safety.

[0094] S3, such as Figure 4 As shown in Figure 1, according to different safety potential field models, the local potential field strength of various traffic entities at the current moment is calculated, and the potential field strength is superimposed according to their respective weight parameters to calculate the potential field strength model E of the total safety potential field. total :

[0095]

[0096] Among them, ω L ,ω S ,ω V They correspond to the weights of the potential field strength of the road line field, the potential field strength of the road boundary field, and the potential field strength of the vehicle potential field.

[0097] S4, using space grid units of uniform size to cut the road space plane, and mapping the superimposed safety potential field with the discretized road space grid, and calculating the field strength aggregation value inside the entire space unit, i.e., the aggregated field strength, according to the field strength value at the grid unit boundary, specifically:

[0098] S401, such as Figure 5 As shown, the road space is cut into grid units of uniform size, and the length of each grid unit is l g (usually 4-10 meters), width is l d (Usually the lane width is taken);

[0099] S402, such as Figure 6 As shown, by projecting the safety potential field after superposition processing onto the gridded road, the safety potential field mapped to the road space grid is obtained;

[0100] S403, such as Figure 7 As shown in the figure, the field strength concentration value inside the entire space unit is calculated based on the field strength value at the grid unit boundary, that is, the concentrated field strength E i :

[0101]

[0102] Among them, E A 、E B 、E C 、E D They represent the potential field strength values ​​at the midpoints of the four sides of space unit i respectively.

[0103] S5, such as Figure 8As shown, according to the value of "aggregate field strength" in each discrete grid, spatiotemporal correlation is performed, the risk intensity of the road is marked, the road risk map is obtained, and the risk map is sent to the driver.

[0104] like Fig. 9 As shown, the present invention provides a road risk map generation system based on a safety potential field, and the system specifically includes the following modules:

[0105] Data acquisition module: obtains the self-attribute information and motion status information of different traffic entities in the road environment;

[0106] Potential field model construction module: design different safety potential field models and weight parameters according to the properties and motion states of different traffic entities;

[0107] Field strength calculation module: According to different safety potential field models, calculate the local potential field strength of various traffic entities at the current moment, and perform potential field strength superposition processing according to their respective weight parameters;

[0108] Road cutting module: Use space grid units of uniform size to cut the road space plane, map the superimposed safety potential field with the discretized road space grid, and calculate the field strength aggregation value inside the entire space unit, i.e., the aggregated field strength, according to the field strength value at the grid unit boundary;

[0109] Map generation module: The road risk map is obtained by performing spatiotemporal correlation based on the values ​​of “aggregated field strength” in each discrete grid;

[0110] Warning information module: sends road risk map to the driver.

[0111] The data acquisition module comprises:

[0112] Attribute information acquisition module: Use visual perception equipment to identify the attributes of different traffic entities on the road. The attributes of traffic entities include: road sign and marking attributes, signal light parameter information, vehicle type information, obstacle size information, etc.

[0113] Motion status information acquisition module: Use radar equipment and sensor equipment to acquire the motion information of different traffic entities. The motion information of traffic entities includes: position information, speed information, acceleration information, steering angle information, etc.

[0114] The potential field model construction module includes:

[0115] Local potential field model construction module: According to the basic composition of road traffic, the safety potential field is divided into three categories: road line field, road boundary field and vehicle potential field. According to the safety potential field theory, the road line field model is constructed; according to the vehicle operation characteristics, the road boundary field model is constructed; according to the vehicle's own attributes and movement characteristics, the vehicle potential field model is constructed;

[0116] Weight assignment module: Design various potential field strength weights according to the different potential field types corresponding to different traffic entities and the strength of their impact on vehicle safety.

[0117] The road cutting module comprises:

[0118] Divide the road grid module: divide the road space into spatial grid units of uniform size, and the length of each grid unit is l g , width is l d ;

[0119] Safety potential field mapping module: maps the safety potential field after superposition processing with the discretized road space grid;

[0120] Aggregate field strength calculation module: Calculate the field strength aggregation value inside the entire space unit, namely the aggregate field strength, based on the field strength value of the grid unit boundary.

[0121] Each module executes its stored execution instructions respectively and works in coordination to implement the road risk map generation method of the present invention.

[0122] The specific implementation methods of the present invention are described in detail above in conjunction with the accompanying drawings, but it should be understood that these embodiments are only examples of the principles and applications of the present invention. It should be understood that various changes and modifications can be made to the embodiments and other arrangements can be designed within the knowledge of ordinary technicians in the field.

Claims

1. A method for generating a road risk map based on a safety potential field, characterized in that: The following steps are involved: S1, obtain the self-attribute information and motion state information of different traffic entities in the road environment; S2, design different safety potential field models and weight parameters according to the properties and motion states of different traffic entities; S3, according to different safety potential field models, calculate the local potential field strength of various types of traffic entities at the current moment, and perform a superposition process of the potential field strength according to their respective weight parameters; S4, using space grid units of uniform size to cut the road space plane, and mapping the safety potential field after superposition processing with the discretized road space grid, and calculating the field intensity aggregation value inside the entire space unit according to the field intensity value of the grid unit boundary; the specific steps include: S401, the road space is cut into space grid units of uniform size, and the length of each grid unit is l g , width is l d ; S402, projecting the safety potential field after the superposition processing onto the gridded road to obtain a safety potential field mapped to the road space grid; S403, calculating the field intensity concentration value E inside the entire space unit according to the field intensity value of the grid unit boundary i : Among them, E A 、E B 、E C 、E D Respectively represent the potential field strength values ​​at the midpoints of the four sides of space unit i; S5, performing spatiotemporal correlation according to the values ​​of "aggregated field strength" in each discrete grid, marking the risk intensity of the road, obtaining a road risk map, and sending the risk map to the driver.

2. The method for generating a road risk map based on a safety potential field according to claim 1, characterized in that: In step S1, the specific steps of obtaining the self-attribute information and motion state information of different traffic entities in the road environment include: S101, using a visual perception device to identify the attributes of different traffic entities on the road, where the traffic entity attributes include: road sign and marking attributes, signal light parameter information, vehicle type information, and obstacle size information; S102, using radar equipment and sensor equipment to obtain movement information of different traffic entities, the movement information of the traffic entity including: position information, speed information, acceleration information and steering angle information.

3. The method for generating a road risk map based on a safety potential field according to claim 1, characterized in that: In step S2, the specific steps of designing different safety potential field models and weight parameters according to the properties and motion states of different traffic entities include: S201, according to the basic composition of road traffic, the safety potential field is divided into a road line field, a road boundary field and a vehicle potential field, and the corresponding safety potential field model category is determined according to the own attributes and motion state of each traffic subject; S202, based on the safety potential field theory, construct a road line field model: Among them, E L is the potential field strength of the road line field; s is the identification number of different types of roads, s = 1, 2, ..., n; j is the identification number of different road line fields, j = 1, 2, ..., n; A s Different potential field strength coefficients generated for different road marking types; is the distance vector of vehicle A pointing to the road line; σ is the speed at which the potential field strength value increases or decreases; S203, according to the vehicle operation characteristics, the potential field strength of the road boundary field approaches infinity as the vehicle gradually approaches, and a road boundary field model is constructed: Among them, E s is the potential field strength of the road boundary field; e is the identification number of the road boundary lines on the left and right sides, e=1, 2, where e=1 represents the left road boundary line, and e=2 represents the right road boundary line; η is the road boundary field coefficient; Represents the distance vector from vehicle A to the road boundary line; S204, calculate the equivalent mass M of the target vehicle i according to the composition characteristics of the vehicle's own attributes i : M i =m i ·(1.566×10 -14 ·in 6.687 +0.3345) Among them, m i is the actual mass of target vehicle i; v is the driving speed of target vehicle i; S205, based on the characteristics of the vehicle's motion state, calculate the distance from the point (x, y) in the space to the center of mass of the vehicle | l ′ |: Among them, (x0, y0) is the spatial coordinate of the center of mass of the target vehicle; τ is the critical threshold of the safety distance; v is the current speed of the vehicle; α is a parameter to be determined related to the speed; e is the base of the natural logarithm function; S206: construct a vehicle potential field model based on the vehicle's own attributes and motion characteristics: Among them, E v is the potential field strength of the vehicle potential field; λ, β1 and ζ are unknown coefficients; θ is the angle between a point around the target vehicle and the spatial coordinates (x0, y0) of the vehicle's center of mass; a is the acceleration of the target vehicle's current motion state; l ′ is a vector, represented by (y-y0)τ); is a unit vector, indicating the direction from the point (x, y) in space to the center of mass of the target vehicle; S207, designing various potential field strength weights according to different potential field types corresponding to different traffic entities and their impact on vehicle safety.

4. The method for generating a road risk map based on a safety potential field according to claim 3, characterized in that: In step S3, according to different safety potential field models, the local potential field strength of each type of traffic subject at the current moment is calculated, and the potential field strength is superimposed according to the respective weight parameters to calculate the potential field strength model E of the safety total potential field. total : Among them, ω L ,ω S ,ω V They are the potential field strength weights of the road line field, the potential field strength weights of the road boundary field, and the potential field strength weights of the vehicle potential field.

5. A road risk map generation system based on safety potential field, characterized in that: The invention comprises a data acquisition module, a potential field model construction module, a field strength calculation module, a road cutting module, a map generation module, and an early warning information module; each module executes its storage execution instruction respectively and works together to implement the road risk map generation method based on the safety potential field according to any one of claims 1 to 4; the execution instructions of each module are as follows: Data acquisition module: obtains the self-attribute information and motion status information of different traffic entities in the road environment; Potential field model construction module: design different safety potential field models and weight parameters according to the properties and motion states of different traffic entities; Field strength calculation module: According to different safety potential field models, calculate the local potential field strength of various traffic entities at the current moment, and perform potential field strength superposition processing according to their respective weight parameters; Road cutting module: Use space grid units of uniform size to cut the road space plane, map the superimposed safety potential field with the discretized road space grid, and calculate the field strength aggregation value inside the entire space unit according to the field strength value of the grid unit boundary; the road cutting module specifically includes a road grid division module, a safety potential field mapping module and an aggregation field strength calculation module: Divide the road grid module: divide the road space into spatial grid units of uniform size, and the length of each grid unit is l g , width is l d ; Safety potential field mapping module: maps the safety potential field after superposition processing with the discretized road space grid; Aggregate field strength calculation module: calculates the field strength aggregation value inside the entire space unit according to the field strength value of the grid unit boundary; Map generation module: Based on the values ​​of "aggregate field strength" in each discrete grid, the road risk map is obtained by performing spatiotemporal correlation; Warning information module: sends road risk map to the driver.

6. The road risk map generation system based on safety potential field according to claim 5, characterized in that: The data acquisition module specifically includes an attribute information acquisition module and a motion state information acquisition module: Attribute information acquisition module: Use visual perception equipment to identify the attributes of different traffic entities on the road. The attributes of traffic entities include: road sign and marking attributes, signal light parameter information, vehicle type information, and obstacle size information; Motion status information acquisition module: uses radar equipment and sensor equipment to acquire the motion information of different traffic entities. The motion information of traffic entities includes: position information, speed information, acceleration information and steering angle information.

7. The road risk map generation system based on safety potential field according to claim 5, characterized in that: The potential field model construction module includes a local potential field model construction module and a weight assignment module: Local potential field model construction module: According to the basic composition of road traffic, the safety potential field is divided into road line field, road boundary field and vehicle potential field, and the road line field model is constructed according to the safety potential field theory; the road boundary field model is constructed according to the vehicle operation characteristics; the vehicle potential field model is constructed according to the vehicle's own attributes and movement characteristics; Weight assignment module: assign weights to various potential field strengths based on the different potential field types corresponding to different traffic entities and the strength relationship of their impact on vehicle safety.

Images