Road rights detection methods and systems for autonomous vehicles

Abstract

This invention provides a road right-of-way detection method for autonomous vehicles, relating to the field of autonomous driving technology, comprising: Step S1: sensing and continuously updating the current environment through sensors to acquire detection information; Step S2: processing the detection information and acquiring measured road right-of-way and calculated road right-of-way; Step S3: predicting the trajectories of surrounding vehicles, using the predicted trajectory results as constraints, and obtaining predicted road right-of-way based on the calculated road right-of-way; Step S4: storing the road right-of-way information in the form of a database or file; Step S5: using an onboard communication system to transmit the vehicle's position and speed information to other vehicles, realizing the sharing and management of road right-of-way; Step S6: displaying the road right-of-way information to the user in a visual form. This invention can effectively improve the safety of autonomous vehicles, increase the driving efficiency of autonomous vehicles, and provide a foundation for achieving fully autonomous driving.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and more specifically, to a method and system for detecting right-of-way in unmanned vehicles. Background Technology

[0002] Autonomous vehicles exchange information with people, vehicles, and roads through onboard environmental perception systems and information terminals, enabling them to have intelligent environmental perception capabilities. They can automatically analyze the safety and danger of driving and reach the destination according to the driver's wishes, ultimately achieving the goal of replacing human operation.

[0003] Controlling autonomous vehicles essentially involves controlling their speed and direction, demanding not only tracking and comfort but also safety. Right-of-way (RW) provides a rigorous definition of this requirement. It refers to a vehicle's right to occupy the required space ahead at any given moment during its journey. In autonomous driving, right-of-way describes the road space needed for the vehicle's safe operation. Right-of-way detection technology is a key technology for achieving autonomous driving. Its development direction is to utilize high-precision, high-reliability sensors and communication technologies to achieve accurate detection and real-time adjustment of right-of-way, thereby ensuring safe driving and efficient operation of the vehicle.

[0004] The existing related technologies have the following drawbacks:

[0005] Existing right-of-way detection technologies mainly rely on single sensors, such as lidar or cameras, which are easily affected by environmental conditions and make it difficult to achieve all-weather, high-precision right-of-way detection. Furthermore, they lack sufficient understanding of the interactions of traffic participants, making it difficult to accurately predict the trajectories and intentions of other vehicles, resulting in inaccurate right-of-way calculations.

[0006] Furthermore, existing technologies rely on single-vehicle right-of-way perception and calculation, lacking information sharing between different vehicles, making collaborative autonomous driving difficult. The representation and visualization of right-of-way information are not intuitive enough, hindering human drivers from understanding and monitoring the vehicle's autonomous driving decisions. Summary of the Invention

[0007] To address the shortcomings of existing technologies, this invention provides a method and system for detecting right-of-way for unmanned vehicles.

[0008] According to the present invention, a road right-of-way detection method and system for unmanned vehicles are provided, the solution of which is as follows:

[0009] Firstly, a method for detecting right-of-way for autonomous vehicles is provided, the method comprising:

[0010] Step S1: Use sensors to perceive the current environment and continuously update it to obtain detection information;

[0011] Step S2: Process the detection information and obtain the measured right-of-way and the calculated right-of-way;

[0012] Step S3: Predict the trajectories of surrounding vehicles, use the predicted trajectories of surrounding vehicles as constraints, and obtain the predicted right-of-way based on the calculated right-of-way.

[0013] Step S4: Store the calculated and predicted right-of-way in a database or file.

[0014] Step S5: Using the vehicle-mounted communication system, the vehicle's location and speed information are transmitted to other vehicles to achieve the sharing and management of right-of-way.

[0015] Step S6: Display the right-of-way information to the user in a visual format.

[0016] Preferably, in step S2, the measured right-of-way is obtained by actually measuring the drivable space of the vehicle through sensors. The calculation of the right-of-way needs to be based on the measured right-of-way, taking into account the length, width and speed of the autonomous vehicle, and calculated using a right-of-way function.

[0017] The formula for calculating right-of-way is:

[0018]

[0019] Where, d real γ represents the distance required for the vehicle to travel safely at present; L represents the maximum safe driving angle range for the vehicle at present; W represents the vehicle's length; v represents the vehicle's current speed; d represents the distance directly in front of the vehicle; and t represents time. i This represents time i during the vehicle's movement.

[0020] Preferably, step S3 includes: a trajectory prediction model for surrounding vehicles, with the input being historical trajectory information of surrounding vehicles and road map information; its form is: the coordinates of each surrounding vehicle based on the current autonomous vehicle coordinate system within the past T time steps;

[0021] Historical trajectory information and road map information are sensed and processed by onboard sensors, and the output is the future trajectory distribution of surrounding vehicles. It is assumed that the future trajectory distribution of surrounding vehicles conforms to a Gaussian mixture model, and its form is as follows:

[0022]

[0023] Where s = s 1：tThe T trajectories are obtained from the regression of the trajectory predictor; μ represents the mean of the T trajectories under a Gaussian distribution; ∑ represents the variance of the T trajectories under a Gaussian distribution; p i This represents the probability of each trajectory after softmax calculation;

[0024] The trajectory prediction results of surrounding vehicles are used as constraints, and different types of vehicles have different risk levels;

[0025] RW′(d real ,γ)=RW(d real ,γ)-p(s)×C

[0026] Where RW represents the calculated right-of-way, RW′ represents the predicted right-of-way, p(s) represents the future trajectory distribution of vehicles, and C represents the weight coefficient of different vehicle categories;

[0027] The predicted right-of-way is obtained by subtracting the future trajectory distribution of surrounding vehicles from the calculated right-of-way.

[0028] Preferably, in addition to right-of-way information, step S6 also includes the display of vehicle status and road condition information, supporting multiple display methods including radar charts, maps, 3D maps, and virtual reality, and enabling user interaction while displaying information.

[0029] Secondly, a right-of-way detection system for autonomous vehicles is provided, the system comprising:

[0030] Sensor module: Perceives the current environment and continuously updates it, acquiring detection information, including cameras, LiDAR, millimeter-wave radar, and infrared radar;

[0031] Data processing module: processes the detection information and obtains the measured right-of-way and the calculated right-of-way;

[0032] Right-of-way prediction module: Predicts the trajectories of surrounding vehicles, uses the predicted trajectories of surrounding vehicles as constraints, and obtains the predicted right-of-way based on the calculated right-of-way.

[0033] Right-of-way storage module: Stores calculated and predicted right-of-way in the form of a database or files;

[0034] Right-of-way sharing module: Utilizing the vehicle-mounted communication system, the module transmits vehicle location and speed information to other vehicles, enabling the sharing and management of right-of-way.

[0035] Right-of-way visualization module: Displays right-of-way information to users in a visual format.

[0036] Preferably, in the data processing module, the measured right-of-way is obtained by actually measuring the drivable space of the vehicle through sensors. The calculation of the right-of-way needs to be based on the measured right-of-way, taking into account the length, width and speed of the autonomous vehicle, and calculated using a right-of-way function.

[0037] The formula for calculating right-of-way is:

[0038]

[0039] Where, d real γ represents the distance required for the vehicle to travel safely at present; L represents the maximum safe driving angle range for the vehicle at present; W represents the vehicle's length; v represents the vehicle's current speed; d represents the distance directly in front of the vehicle; and t represents time. i This represents time i during the vehicle's movement.

[0040] Preferably, the right-of-way prediction module includes: a trajectory prediction model for surrounding vehicles, with the input being historical trajectory information of surrounding vehicles and road map information; its form is: the coordinates of each surrounding vehicle based on the current autonomous vehicle coordinate system within the past T time steps;

[0041] Historical trajectory information and road map information are sensed and processed by onboard sensors, and the output is the future trajectory distribution of surrounding vehicles. It is assumed that the future trajectory distribution of surrounding vehicles conforms to a Gaussian mixture model, and its form is as follows:

[0042]

[0043] Where s = s 1：t The T trajectories are obtained from the regression of the trajectory predictor; μ represents the mean of the T trajectories under a Gaussian distribution; ∑ represents the variance of the T trajectories under a Gaussian distribution; p i This represents the probability of each trajectory after softmax calculation;

[0044] The trajectory prediction results of surrounding vehicles are used as constraints, and different types of vehicles have different risk levels;

[0045] RW′(d real ,γ)=RW(d real ,γ)-p(s)×C

[0046] Where RW represents the calculated right-of-way, RW′ represents the predicted right-of-way, p(s) represents the future trajectory distribution of vehicles, and C represents the weight coefficient of different vehicle categories;

[0047] The predicted right-of-way is obtained by subtracting the future trajectory distribution of surrounding vehicles from the calculated right-of-way.

[0048] Preferably, the right-of-way visualization module includes not only right-of-way information but also the display of vehicle status and road condition information, supporting multiple display methods including radar charts, maps, 3D maps, and virtual reality, and enabling user interaction while displaying information.

[0049] Thirdly, a computer-readable storage medium storing a computer program is provided, which, when executed by a processor, implements the steps in the right-of-way detection method for the unmanned vehicle.

[0050] Fourthly, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps in the right-of-way detection method for the unmanned vehicle.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] 1. The right-of-way detector proposed in this invention can detect the surrounding road environment of autonomous vehicles in real time, obtain road condition information and right-of-way information, and provide support for the safe driving of autonomous vehicles. Compared with existing right-of-way determination methods based on map matching and road sign identification, this invention has higher real-time performance and robustness;

[0053] 2. The right-of-way sharing mechanism proposed in this invention enables collaborative operation among different autonomous vehicles. Compared with existing independently operating autonomous vehicles, collaborative autonomous driving can improve traffic efficiency, reduce traffic congestion, and achieve more intelligent traffic management;

[0054] 3. The right-of-way visualization scheme proposed in this invention can intuitively display the surrounding environment information of autonomous vehicles, making it easier for users to understand the current road conditions and the operation of autonomous vehicles, thereby improving the user's riding experience.

[0055] Other beneficial effects of the present invention will be explained in detail through the introduction of specific technical features and technical solutions in specific embodiments. Those skilled in the art should be able to understand the beneficial technical effects brought about by these technical features and technical solutions through the introduction of these technical features and technical solutions. Attached Figure Description

[0056] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0057] Figure 1 This is a schematic diagram of the process of the present invention;

[0058] Figure 2 This is a schematic diagram of an onboard sensor and its detection mechanism.

[0059] Figure 3 The radar chart to be created. Detailed Implementation

[0060] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the scope of protection of the present invention.

[0061] This invention provides a method for detecting right-of-way for autonomous vehicles. First, a sensor module actively senses and continuously updates the current environment. Then, a data processing module obtains measured and calculated right-of-way information. The right-of-way can be stored or shared with other vehicles. Based on the predicted right-of-way, the vehicle's movement is constrained. Finally, a right-of-way visualization module displays the information visually to the user, enabling human-machine collaborative control.

[0062] Reference Figure 1 and Figure 2 As shown, the method specifically includes the following:

[0063] Step S1: Autonomous vehicles actively perceive and continuously update their current environment using onboard sensor systems, including cameras, lidar, millimeter-wave radar, infrared radar, etc.

[0064] Step S2: Process the information detected by the sensor module to obtain the measured right-of-way and the calculated right-of-way. The measured right-of-way is obtained by measuring the drivable space of the vehicle through the actual sensors; and based on the measured right-of-way, the calculated right-of-way is obtained by comprehensively considering the length, width, and speed of the autonomous vehicle using a right-of-way function.

[0065] The measured right-of-way is obtained by actually measuring the drivable space of the vehicle through sensors. The calculation of the right-of-way needs to be based on the measured right-of-way, taking into account the length, width and speed of the autonomous vehicle, and is calculated using the right-of-way function.

[0066] The formula for calculating right-of-way is:

[0067]

[0068] Where, d real The vector represents the distance required for the vehicle to travel safely at present; γ represents the maximum safe angle range for the vehicle to travel at present; L represents the length of the vehicle; W represents the width of the vehicle; v represents the current speed of the vehicle (the speed of the vehicle's center of gravity); d represents the current distance directly in front of the vehicle; and t represents time. i This represents time i during the vehicle's movement.

[0069] It should be noted that the following aspects are considered when calculating right-of-way:

[0070] 1) Vehicle parameters: Different types and sizes of vehicles have different safe distances d and safe angles θ, which directly affect their right-of-way.

[0071] 2) Driving status: The greater the vehicle's speed v, the greater its reaction time and braking distance, so it is necessary to obtain a longer right-of-way distance in advance to ensure safe driving.

[0072] 3) Surrounding traffic flow: When the surrounding traffic flow q is larger, it is more difficult for autonomous vehicles to obtain right-of-way, and the right-of-way range will be reduced accordingly.

[0073] 4) Available road conditions; the larger the available distance s, the clearer the road ahead, and the greater the right-of-way that the autonomous vehicle can obtain.

[0074] In summary, the right-of-way calculation formula can combine information from multiple sources to calculate the right-of-way required for the safe driving of autonomous vehicles in the current environment, providing a reference for their driving control and decision-making, so as to achieve safe and efficient autonomous driving.

[0075] Reference Figure 3 As shown, step S3: predict the trajectories of surrounding vehicles, use the trajectory prediction results of surrounding vehicles as constraints, and obtain the predicted right-of-way based on the calculated right-of-way.

[0076] Specifically, right-of-way mapping involves mapping the calculated right-of-way results onto a radar map. The trajectory prediction model for surrounding vehicles takes as input historical trajectory information of surrounding vehicles and road map information; its form is: the coordinates of each surrounding vehicle within the current autonomous vehicle coordinate system over the past T time steps.

[0077] Historical trajectory information and road map information are sensed and processed by onboard sensors, and the output is the future trajectory distribution of surrounding vehicles. It is assumed that the future trajectory distribution of surrounding vehicles conforms to a Gaussian mixture model, and its form is as follows:

[0078]

[0079] Where s = s 1：t Let T represent the T trajectories obtained from the trajectory predictor regression. μ represents the mean of the T trajectories under a Gaussian distribution. ∑ represents the variance of the T trajectories under a Gaussian distribution. i This represents the probability of each trajectory after softmax calculation.

[0080] The trajectory prediction results of surrounding vehicles are used as constraints, and different types of vehicles have different risk levels;

[0081] RW′(d real ,γ)=RW(d real ,γ)-p(s)×C

[0082] Where RW represents the calculated right-of-way, RW′ represents the predicted right-of-way, p(s) represents the future trajectory distribution of vehicles, and C represents the weight coefficient of different vehicle categories;

[0083] The predicted right-of-way is obtained by subtracting the future trajectory distribution of surrounding vehicles from the calculated right-of-way.

[0084] Step S4: This step stores historical right-of-way information for autonomous vehicles, facilitating subsequent analysis and research. This module can store calculated and predicted right-of-way information in a database or file format for easy querying and analysis by users.

[0085] Step S5: Used to transmit vehicle location, speed and other information to other vehicles using the vehicle communication system, thereby realizing the sharing and management of right-of-way.

[0086] Step S6: This step displays right-of-way information to the user in a visual format, allowing them to easily understand the current right-of-way situation. This module can display right-of-way information in the form of radar charts, maps, etc., making it easier for users to observe and make decisions regarding overtaking or changing lanes.

[0087] Vehicle status display: In addition to right-of-way information, vehicle status can be displayed to users in a visual format, including vehicle position, speed, acceleration, etc. This helps users better understand the vehicle's movement status and make more accurate decisions.

[0088] Traffic information display: In addition to right-of-way information, traffic information can be presented to users in a visual format, including road conditions and traffic flow. This helps users better understand the current road situation and make more informed decisions.

[0089] Support for multiple display methods: In addition to radar charts and maps, it also supports various display methods such as 3D maps and virtual reality. This allows users to understand right-of-way information and vehicle status more intuitively, improving the user experience.

[0090] User interaction support: In addition to displaying information, it can also support user interaction. For example, users can click on a location on the map to obtain right-of-way information and traffic conditions for that location. This makes it easier for users to obtain the information they need and improves user satisfaction.

[0091] This invention also provides a right-of-way detection system for autonomous vehicles. This system can be implemented by executing the steps of the right-of-way detection method for autonomous vehicles. That is, those skilled in the art can understand the right-of-way detection method for autonomous vehicles as a preferred embodiment of the right-of-way detection system. The system specifically includes the following:

[0092] Sensor module: Autonomous vehicles actively perceive and continuously update their current environment using onboard sensor systems, including cameras, lidar, millimeter-wave radar, infrared radar, etc.

[0093] Data processing module: Processes the information detected by the sensor module to obtain measured right-of-way and calculated right-of-way. Measured right-of-way is obtained by using the vehicle's drivable space as actually measured by the sensors; and calculated right-of-way is obtained based on the measured right-of-way, taking into account the autonomous vehicle's length, width, and speed, using a right-of-way function.

[0094] The measured right-of-way is obtained by actually measuring the drivable space of the vehicle through sensors. The calculation of the right-of-way needs to be based on the measured right-of-way, taking into account the length, width and speed of the autonomous vehicle, and is calculated using the right-of-way function.

[0095] The formula for calculating right-of-way is:

[0096]

[0097] Where, d real The vector represents the distance required for the vehicle to travel safely at present; γ represents the maximum safe angle range for the vehicle to travel at present; L represents the length of the vehicle; W represents the width of the vehicle; v represents the current speed of the vehicle (the speed of the vehicle's center of gravity); d represents the current distance directly in front of the vehicle; and t represents time. i This represents time i during the vehicle's movement.

[0098] It should be noted that the following aspects are considered when calculating right-of-way:

[0099] 1) Vehicle parameters: Different types and sizes of vehicles have different safe distances d and safe angles θ, which directly affect their right-of-way.

[0100] 2) Driving status: The greater the vehicle's speed v, the greater its reaction time and braking distance, so it is necessary to obtain a longer right-of-way distance in advance to ensure safe driving.

[0101] 3) Surrounding traffic flow: When the surrounding traffic flow q is larger, it is more difficult for autonomous vehicles to obtain right-of-way, and the right-of-way range will be reduced accordingly.

[0102] 4) Available road conditions; the larger the available distance s, the clearer the road ahead, and the greater the right-of-way that the autonomous vehicle can obtain.

[0103] In summary, the right-of-way calculation formula can combine information from multiple sources to calculate the right-of-way required for the safe driving of autonomous vehicles in the current environment, providing a reference for their driving control and decision-making, so as to achieve safe and efficient autonomous driving.

[0104] Right-of-way prediction module: Predicts the trajectories of surrounding vehicles, uses the predicted trajectories of surrounding vehicles as constraints, and obtains the predicted right-of-way based on the calculated right-of-way.

[0105] Specifically, right-of-way mapping involves mapping the calculated right-of-way results onto a radar map. The trajectory prediction model for surrounding vehicles takes as input historical trajectory information of surrounding vehicles and road map information; its form is: the coordinates of each surrounding vehicle within the current autonomous vehicle coordinate system over the past T time steps.

[0106] Historical trajectory information and road map information are sensed and processed by onboard sensors, and the output is the future trajectory distribution of surrounding vehicles. It is assumed that the future trajectory distribution of surrounding vehicles conforms to a Gaussian mixture model, and its form is as follows:

[0107]

[0108] Where s = s 1：t Let T represent the T trajectories obtained from the trajectory predictor regression. μ represents the mean of the T trajectories under a Gaussian distribution. ∑ represents the variance of the T trajectories under a Gaussian distribution. i This represents the probability of each trajectory after softmax calculation.

[0109] The trajectory prediction results of surrounding vehicles are used as constraints, and different types of vehicles have different risk levels;

[0110] RW′(d real ,γ)=RW(d real ,γ)-p(s)×C

[0111] Where RW represents the calculated right-of-way, RW′ represents the predicted right-of-way, p(s) represents the future trajectory distribution of vehicles, and C represents the weight coefficient of different vehicle categories;

[0112] The predicted right-of-way is obtained by subtracting the future trajectory distribution of surrounding vehicles from the calculated right-of-way.

[0113] Right-of-way storage module: This module stores historical right-of-way information for autonomous vehicles, facilitating subsequent analysis and research. It can store calculated and predicted right-of-way information in a database or file format for easy querying and analysis by users.

[0114] Right-of-way sharing module: This module uses the vehicle communication system to transmit information such as the vehicle's location and speed to other vehicles, thereby enabling the sharing and management of right-of-way.

[0115] Right-of-way visualization module: This module displays right-of-way information to users in a visual format, making it easier for them to understand the current right-of-way situation. It can present this information in the form of radar charts, maps, etc., allowing users to observe and make decisions regarding overtaking or lane changing.

[0116] Vehicle status display: In addition to right-of-way information, vehicle status can be displayed to users in a visual format, including vehicle position, speed, acceleration, etc. This helps users better understand the vehicle's movement status and make more accurate decisions.

[0117] Traffic information display: In addition to right-of-way information, traffic information can be presented to users in a visual format, including road conditions and traffic flow. This helps users better understand the current road situation and make more informed decisions.

[0118] Support for multiple display methods: In addition to radar charts and maps, it also supports various display methods such as 3D maps and virtual reality. This allows users to understand right-of-way information and vehicle status more intuitively, improving the user experience.

[0119] User interaction support: In addition to displaying information, it can also support user interaction. For example, users can click on a location on the map to obtain right-of-way information and traffic conditions for that location. This makes it easier for users to obtain the information they need and improves user satisfaction.

[0120] This invention provides a road right-of-way detection method and system for autonomous vehicles, which enables autonomous vehicles to capture and analyze surrounding road conditions through road right-of-way detectors in complex environments that are constantly changing and uncertain. This helps users ensure driving safety and ultimately achieve fully autonomous driving.

[0121] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0122] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A method for detecting right-of-way for unmanned vehicles, characterized in that, include: Step S1: Use sensors to perceive the current environment and continuously update it to obtain detection information; Step S2: Process the detection information and obtain the measured right-of-way and the calculated right-of-way; Step S3: Predict the trajectories of surrounding vehicles, use the predicted trajectories of surrounding vehicles as constraints, and obtain the predicted right-of-way based on the calculated right-of-way. Step S4: Store the calculated and predicted right-of-way in a database or file. Step S5: Using the vehicle-mounted communication system, the vehicle's location and speed information are transmitted to other vehicles to achieve the sharing and management of right-of-way. Step S6: Display the right-of-way information to the user in a visual format; In step S2, the measured right-of-way is obtained by actually measuring the drivable space of the vehicle through sensors. The calculation of the right-of-way needs to be based on the measured right-of-way, taking into account the length, width and speed of the autonomous vehicle, and is calculated using the right-of-way function. The formula for calculating right-of-way is: in, This indicates the distance the vehicle needs to travel safely at this point. This indicates the maximum range of safe driving angles for the vehicle. Indicates the length of the vehicle. Indicates the width of the vehicle; Indicates the vehicle's current speed. This indicates the distance directly in front of the vehicle. Represents time, Indicates the vehicle is in motion i time; Step S3 includes: a trajectory prediction model for surrounding vehicles, with the input being historical trajectory information of surrounding vehicles and road map information; its form is: the coordinates of each surrounding vehicle based on the current autonomous vehicle coordinate system within the past T time steps. Historical trajectory information and road map information are sensed and processed by onboard sensors, outputting the future trajectory distribution of surrounding vehicles. The future trajectory distribution of surrounding vehicles conforms to a Gaussian mixture model, and its form is as follows: Where p(s) represents the future trajectory distribution of surrounding vehicles; M represents the total number of predicted trajectories of surrounding vehicles; T represents the total number of time steps obtained by the trajectory predictor regression; and St represents the trajectory coordinate state of surrounding vehicles obtained by regression at the t-th time step. Let represent the mean of the i-th trajectory under a Gaussian distribution at time t; This represents the variance of the i-th trajectory under a Gaussian distribution at time t. This represents the probability of each trajectory after softmax calculation; The trajectory prediction results of surrounding vehicles are used as constraints, and different types of vehicles have different risk levels; - in, Indicates the calculation of right-of-way. Indicates predicted right-of-way. This represents the future trajectory distribution of the car, and C represents the weighting coefficient of different car categories; The predicted right-of-way is obtained by subtracting the future trajectory distribution of surrounding vehicles from the calculated right-of-way. The calculation of right-of-way also needs to take into account the surrounding traffic flow and available road conditions.

2. The road right-of-way detection method for unmanned vehicles according to claim 1, characterized in that, In addition to right-of-way information, step S6 also includes the display of vehicle status and road condition information, supporting multiple display methods including radar charts, maps, and virtual reality, and enabling user interaction while displaying information.

3. A right-of-way detection system for unmanned vehicles, characterized in that, include: Sensor module: Perceives the current environment and continuously updates it, acquiring detection information, including cameras, LiDAR, millimeter-wave radar, and infrared radar; Data processing module: processes the detection information and obtains the measured right-of-way and the calculated right-of-way; Right-of-way prediction module: Predicts the trajectories of surrounding vehicles, uses the predicted trajectories of surrounding vehicles as constraints, and obtains the predicted right-of-way based on the calculated right-of-way. Right-of-way storage module: Stores calculated and predicted right-of-way in the form of a database or files; Right-of-way sharing module: Utilizing the vehicle-mounted communication system, the module transmits vehicle location and speed information to other vehicles, enabling the sharing and management of right-of-way. Right-of-way visualization module: Displays right-of-way information to users in a visual format; In the data processing module, the measured right-of-way is obtained by actually measuring the drivable space of the vehicle through sensors. The calculation of the right-of-way needs to be based on the measured right-of-way, taking into account the length, width and speed of the autonomous vehicle, and is calculated using the right-of-way function. The formula for calculating right-of-way is: in, This indicates the distance the vehicle needs to travel safely at this point. This indicates the maximum range of safe driving angles for the vehicle. Indicates the length of the vehicle. Indicates the width of the vehicle; Indicates the vehicle's current speed. This indicates the distance directly in front of the vehicle. Represents time, Indicates the vehicle is in motion i time; The right-of-way prediction module includes: a trajectory prediction model for surrounding vehicles, with the input being the historical trajectory information of surrounding vehicles and road map information; its form is: the coordinates of each surrounding vehicle based on the current autonomous vehicle coordinate system within the past T time steps; Historical trajectory information and road map information are sensed and processed by onboard sensors, outputting the future trajectory distribution of surrounding vehicles. The future trajectory distribution of surrounding vehicles conforms to a Gaussian mixture model, and its form is as follows: Where p(s) represents the future trajectory distribution of surrounding vehicles; M represents the total number of predicted trajectories of surrounding vehicles; T represents the total number of time steps obtained by the trajectory predictor regression; and St represents the trajectory coordinate state of surrounding vehicles obtained by regression at the t-th time step. Let represent the mean of the i-th trajectory under a Gaussian distribution at time t; This represents the variance of the i-th trajectory under a Gaussian distribution at time t. This represents the probability of each trajectory after softmax calculation; The trajectory prediction results of surrounding vehicles are used as constraints, and different types of vehicles have different risk levels; - in, Indicates the calculation of right-of-way. Indicates predicted right-of-way. This represents the future trajectory distribution of the car, and C represents the weighting coefficient of different car categories; The predicted right-of-way is obtained by subtracting the future trajectory distribution of surrounding vehicles from the calculated right-of-way. The calculation of right-of-way also needs to take into account the surrounding traffic flow and available road conditions.

4. The right-of-way detection system for unmanned vehicles according to claim 3, characterized in that, In addition to right-of-way information, the right-of-way visualization module also displays vehicle status and road condition information, and supports multiple display methods including radar charts, maps, and virtual reality. It also allows for user interaction while displaying information.

5. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the right-of-way detection method for unmanned vehicles as described in any one of claims 1 to 2.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is executed by the processor, it implements the steps of the right-of-way detection method for unmanned vehicles as described in any one of claims 1 to 2.

Images