A method and system for unmanned vehicle dispatch management

Abstract

The application discloses a kind of vehicle scheduling management method and system for unmanned, the method includes the following steps: obtaining the task priority and constraint condition of unmanned vehicle;According to the pre-planned unmanned vehicle driving path and starting time, control unmanned vehicle to reach destination;Vehicle detection is carried out in the parking lot of destination, obtain the parking space of unmanned vehicle, and automatically park unmanned vehicle into position based on parking rule;Real-time monitoring is carried out to vehicle and task, obtain the real-time state of vehicle and task, and real-time monitoring and processing abnormal situation;The system includes scheduling preparation module, road driving scheduling module, parking scheduling module and state monitoring module.Make vehicle transportation more efficient, safe and reliable, realize the total driving cost of all unmanned vehicles lowest scheduling order, realize the scheduling and parking of multiple vehicles intelligently and efficiently.

Description

Technical Field

[0001] This invention relates to the field of vehicle management technology, and more specifically, to a vehicle dispatching and management method and system for autonomous driving. Background Technology

[0002] Vehicle dispatch management refers to the management process of planning and controlling vehicles to optimize their use and efficiency. Vehicle dispatch management typically includes the following aspects:

[0003] 1. Vehicle Dispatch Plan: Based on the company's business needs and vehicle resources, develop a vehicle dispatch plan and arrange vehicle transportation tasks, including route planning, loading and unloading times, and transportation volume.

[0004] 2. Vehicle dispatch implementation: Implement vehicle dispatch plans and guide drivers to complete vehicle transportation tasks according to the plans.

[0005] 3. Vehicle monitoring: Real-time monitoring of vehicle location, speed, and route is conducted using technologies such as GPS to ensure safe and smooth transportation.

[0006] 4. Vehicle maintenance and management: Regularly maintain and service vehicles to ensure safe and reliable operation.

[0007] 5. Vehicle dispatching data analysis: By analyzing vehicle transportation data, we can understand the bottlenecks and problems in vehicle transportation, optimize vehicle dispatching plans and transportation routes, improve transportation efficiency and reduce costs.

[0008] Existing vehicle scheduling and management methods rely on fixed paths, resulting in low overall efficiency. For example, Chinese Patent No. 202010941886.5 discloses a vehicle parking scheduling and management method and related components. This method calculates the shortest path based on a shortest path algorithm, identifies the corresponding vacant parking space as the optimal scheduling space, generates scheduling information, and sends it to the current vehicle, thus improving parking space utilization. However, the above method still has the following shortcomings in practical applications: While using algorithms for path optimization to achieve optimal vehicle scheduling can help vehicles be scheduled in an orderly manner, it may lead to excessive waiting times when multiple vehicles are scheduled simultaneously, leaving room for further optimization in terms of overall efficiency.

[0009] No effective solutions have yet been proposed to address the problems in the relevant technologies. Summary of the Invention

[0010] In view of the problems in related technologies, the present invention proposes a vehicle scheduling and management method and system for autonomous driving, so as to overcome the above-mentioned technical problems existing in the existing related technologies.

[0011] Therefore, the specific technical solution adopted by the present invention is as follows:

[0012] According to one aspect of the present invention, a vehicle scheduling and management method for autonomous driving is provided, the method comprising the following steps:

[0013] S1. Obtain the task priority and constraints of the autonomous vehicle;

[0014] S2. Based on the pre-planned autonomous vehicle driving route and start time, control the autonomous vehicle to reach the destination;

[0015] S3. Conduct vehicle detection at the destination parking lot, obtain parking spaces for autonomous vehicles, and automatically park the autonomous vehicles into the spaces based on parking rules;

[0016] S4. Monitor vehicles and tasks in real time, obtain their real-time status, and monitor and handle abnormal situations in real time.

[0017] Furthermore, obtaining the task priority and constraints of the autonomous vehicle includes the following steps:

[0018] S11. Before scheduling autonomous vehicles, clarify the scheduling requirements and constraints of autonomous vehicles to obtain the scheduling scenario.

[0019] S12. Based on the obtained scheduling scenario, collect the task destination, travel route and start time of the scheduling task to obtain task information;

[0020] S13. Based on the scheduling scenario and task information, determine the number of unmanned vehicles, their payload capacity, and their driving range.

[0021] Furthermore, the process of detecting vehicles at the destination parking lot and obtaining parking spaces for autonomous vehicles includes the following steps:

[0022] Install a binocular camera for video measurement at the entrance of the parking lot at the destination, and calibrate the binocular camera in advance;

[0023] Send a request to obtain the size information of the autonomous vehicle. If the size information of the autonomous vehicle is received in response, determine the parking space of the autonomous vehicle based on the size information.

[0024] If the feedback cannot obtain the size information of the autonomous vehicle, then the autonomous vehicle will drive into the measurement area.

[0025] The dimensions of the autonomous vehicles within the measurement area are measured using the calibrated binocular cameras.

[0026] After the dimensions are measured, the parking space for the autonomous vehicle is determined based on the obtained dimensional information.

[0027] Furthermore, the step of measuring the dimensions of the autonomous vehicle within the measurement area using the calibrated binocular camera includes the following steps:

[0028] Two images of the autonomous vehicle are acquired from different positions using a calibrated binocular camera, and the projection points on the two images of the autonomous vehicle are obtained.

[0029] Obtain any point P of the autonomous vehicle w And obtain point P w The optical axis coordinates in the coordinate systems of the two cameras of the stereo camera are obtained simultaneously, along with the homogeneous coordinates of the two projection points in their respective coordinate systems and the coordinates of point P. w Homogeneous coordinates in the world coordinate system;

[0030] The calibration provides the projection transformation matrix for two images of an autonomous vehicle captured by a binocular camera. It combines the projection transformation matrix with the linear theory of camera imaging, utilizing the coordinates of two optical axes, the homogeneous coordinates of the two projection points in their respective coordinate systems, and point P. w Using homogeneous coordinates in the world coordinate system, we obtain the straight line passing through the two sets of optical centers and the projection point in the binocular camera, and point P... w The intersection of two straight lines leads to point P. w 3D coordinates;

[0031] By determining the three-dimensional coordinates of each vertex on the autonomous vehicle, the three-dimensional data dimensions of the autonomous vehicle are calculated.

[0032] Furthermore, when installing a binocular camera for video measurement at the entrance of the parking lot at the destination, and calibrating the binocular camera in advance, a regularly arranged square pattern is used as a calibration plate, and the size of the square is known, with its vertices serving as reference points for calibration.

[0033] Furthermore, the automatic parking of the autonomous vehicle based on parking rules includes the following steps:

[0034] Establish communication connections with each driverless vehicle entering the parking lot and obtain their location;

[0035] Each autonomous vehicle is driven to its destination parking space according to the shortest path principle;

[0036] Calculate the total operating cost of all driverless vehicles:

[0037] U N =∑ i∈N U i (si )

[0038] In the formula, s i Let be the set of strategies for the i-th autonomous vehicle;

[0039] U i Let U be the function that minimizes the driving cost of the i-th autonomous vehicle. N Let N be the driving cost function for all autonomous vehicles, where N is a non-zero natural number.

[0040] By having all autonomous vehicles cooperate, and obtaining the scheduling ranking with the lowest total driving cost based on the cooperation model:

[0041]

[0042] In the formula, P is the total driving cost obtained by cooperating with all autonomous vehicles;

[0043] s i Let be the set of strategies for the i-th autonomous vehicle;

[0044] U i Let N be the function that minimizes the driving cost of the i-th autonomous vehicle, where N is a non-zero natural number.

[0045] σ represents the initial scheduling order. The driving cost function is used for the initial scheduling sorting of the i-th autonomous vehicle.

[0046] Furthermore, when the calculation yields the scheduling order with the lowest total travel cost, the optimal scheduling order for the cooperative model is obtained through a genetic algorithm.

[0047] The fitness function in the genetic algorithm is:

[0048]

[0049] In the formula, ω is the scheduling threshold of the cooperative model;

[0050] U i g Let U be the driving cost function of the i-th autonomous vehicle using the g-th strategy. i Let be the function that minimizes the driving cost of the i-th autonomous vehicle;

[0051] When the conditions in the fitness function are met, the optimal scheduling order is achieved.

[0052] Furthermore, when establishing a communication connection for each autonomous vehicle entering the parking lot, the autonomous vehicle communicates with the dispatch center in real time to achieve rapid data transmission and processing, and the communication of the autonomous vehicle is encrypted, data is backed up, and battery capacity is monitored.

[0053] Furthermore, when obtaining the location of the other party, the autonomous vehicle is equipped with a global positioning system, lidar and vehicle-mounted camera to achieve positioning, and while the autonomous vehicle is driving on the road, it monitors traffic flow in real time by acquiring monitoring data from traffic monitoring facilities.

[0054] According to another aspect of the present invention, a vehicle dispatch management system for unmanned driving is provided, the system including a dispatch preparation module, a road driving dispatch module, a parking dispatch module and a status monitoring module.

[0055] The scheduling preparation module is used to obtain the task priority and constraints of the autonomous vehicle.

[0056] The road driving scheduling module is used to control the autonomous vehicle to reach its destination according to the pre-planned driving route and start time.

[0057] The parking scheduling module is used to detect vehicles at the destination parking lot, obtain parking spaces for autonomous vehicles, and automatically park the autonomous vehicles in the spaces based on parking rules.

[0058] The status monitoring module is used to monitor vehicles and tasks in real time, obtain the real-time status of vehicles and tasks, and monitor and handle abnormal situations in real time.

[0059] The beneficial effects of this invention are as follows:

[0060] (1) The present invention provides a vehicle dispatching and management method and system for unmanned driving, which makes vehicle transportation more efficient, safe and reliable, and improves the transportation efficiency and competitiveness of enterprises. The present invention makes full use of traffic monitoring facilities, global positioning system, lidar and vehicle camera, so that unmanned vehicles can determine distance and locate each other.

[0061] (2) When parking an unmanned vehicle, the present invention obtains the size of the unmanned vehicle and determines the unmanned vehicle to a suitable parking space. At the same time, when the size of the unmanned vehicle cannot be obtained, the relevant vehicle can be accurately measured by a binocular camera, so that vehicles without size data can also be arranged to a suitable parking space, thereby realizing automated measurement and improving parking efficiency.

[0062] (3) This invention achieves the scheduling and sorting of all unmanned vehicles with the lowest total driving cost through a cooperative model, thereby realizing intelligent and efficient scheduling and parking of multiple vehicles, and further optimizing the overall efficiency. Attached Figure Description

[0063] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 This is a flowchart of a vehicle scheduling and management method for autonomous driving according to an embodiment of the present invention;

[0065] Figure 2 This is a schematic diagram of a vehicle dispatch and management system for unmanned driving according to an embodiment of the present invention.

[0066] In the picture:

[0067] 1. Dispatch preparation module; 2. Road driving dispatch module; 3. Parking dispatch module; 4. Status monitoring module. Detailed Implementation

[0068] To further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. These drawings are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementation methods and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0069] According to an embodiment of the present invention, a vehicle scheduling and management method and system for autonomous driving are provided.

[0070] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, according to an embodiment of the present invention, a vehicle scheduling and management method for autonomous driving is provided, the method comprising the following steps:

[0071] S1. Obtain the task priority and constraints of the autonomous vehicle;

[0072] The constraints include the following:

[0073] The number of driverless vehicles: The number of vehicles needs to be reasonably arranged based on the relationship between the workload and the number of vehicles, as well as factors such as vehicle operating costs and availability.

[0074] The payload capacity of each autonomous vehicle needs to be rationally allocated based on the task type and task requirements in the scheduling scenario.

[0075] Driving range of autonomous vehicles: Since autonomous vehicles are generally electric vehicles, their driving range is an important constraint. It is necessary to rationally arrange the vehicle's driving route and charging station according to mission requirements and scheduling scenarios to ensure that the vehicle can complete the mission and return to the base.

[0076] Traffic rules and restrictive regulations: Autonomous vehicles must abide by traffic rules on the road, including traffic lights, lanes, speed limits, etc., and must also travel on sections of road where autonomous vehicles are permitted to travel.

[0077] Environmental safety: Environmental safety needs to be considered, such as avoiding vehicle operation in severe weather or poor road conditions.

[0078] In one embodiment, obtaining the task priority and constraints of the autonomous vehicle includes the following steps:

[0079] S11. Before scheduling autonomous vehicles, clarify the scheduling requirements and constraints of autonomous vehicles to obtain the scheduling scenario;

[0080] S12. Based on the obtained scheduling scenario, collect the task destination, travel route and start time of the scheduling task to obtain task information;

[0081] S13. Based on the scheduling scenario and task information, determine the number of unmanned vehicles, their payload capacity, and their driving range.

[0082] S2. Based on the pre-planned autonomous vehicle driving route and start time, control the autonomous vehicle to reach the destination;

[0083] S3. Conduct vehicle detection at the destination parking lot, obtain the parking space for the autonomous vehicle, and automatically park the autonomous vehicle in the space based on the parking rules; the parking rules are the internal traffic rules stipulated by the parking lot, such as: entrance and exit rules, driving direction rules, driving speed rules, etc.

[0084] In one embodiment, the process of detecting vehicles at the destination parking lot and obtaining parking spaces for autonomous vehicles includes the following steps:

[0085] Install a binocular camera for video measurement at the entrance of the parking lot at the destination, and calibrate the binocular camera in advance;

[0086] Send a request to obtain the size information of the autonomous vehicle. If the size information of the autonomous vehicle is received in response, determine the parking space of the autonomous vehicle based on the size information.

[0087] If the feedback cannot obtain the size information of the autonomous vehicle, then the autonomous vehicle will drive into the measurement area.

[0088] The dimensions of the autonomous vehicles within the measurement area are measured using the calibrated binocular cameras.

[0089] After the dimensions are measured, the parking space for the autonomous vehicle is determined based on the obtained dimensional information.

[0090] Binocular stereo vision is an imaging principle that mimics human binocular vision. It uses two cameras to capture the same scene simultaneously, and then uses computer algorithms to fuse the two images into a three-dimensional image, thereby enabling the perception of the distance and depth of objects.

[0091] In one embodiment, the step of measuring the size of the autonomous vehicle within the measurement area using a calibrated binocular camera includes the following steps:

[0092] (The binocular camera has two camera coordinate systems) After calibration, the binocular camera acquires two images of the autonomous vehicle from different positions and obtains the projection points on the two images of the autonomous vehicle.

[0093] Obtain any point P of the autonomous vehicle w And obtain point P w The optical axis coordinates in the coordinate systems of the two cameras of the stereo camera are obtained simultaneously, along with the homogeneous coordinates of the two projection points in their respective coordinate systems and the coordinates of point P. w Homogeneous coordinates in the world coordinate system;

[0094] The calibration provides the projection transformation matrix for two images of an autonomous vehicle captured by a binocular camera. It combines the projection transformation matrix with the linear theory of camera imaging, utilizing the coordinates of two optical axes, the homogeneous coordinates of the two projection points in their respective coordinate systems, and point P. w Using homogeneous coordinates in the world coordinate system, we obtain the straight line passing through the two sets of optical centers and the projection point in the binocular camera, and point P... w The intersection of two straight lines leads to point P. w 3D coordinates;

[0095] By determining the three-dimensional coordinates of each vertex on the autonomous vehicle, the three-dimensional data dimensions of the autonomous vehicle are calculated.

[0096] In one embodiment, when installing a binocular camera for video measurement at the entrance of the parking lot at the destination, and calibrating the binocular camera in advance, a regularly arranged square pattern is used as a calibration plate, and the size of the square is known, with its vertices serving as reference points for calibration.

[0097] In one embodiment, automatically parking the autonomous vehicle based on parking rules includes the following steps:

[0098] Establish communication connections with each driverless vehicle entering the parking lot and obtain their location;

[0099] Each autonomous vehicle is driven to its destination parking space according to the shortest path principle;

[0100] Calculate the total operating cost of all driverless vehicles:

[0101] U N =∑ i∈N U i (s i )

[0102] In the formula, s i Let be the set of strategies for the i-th autonomous vehicle;

[0103] U i Let U be the function that minimizes the driving cost of the i-th autonomous vehicle. N Let N be the driving cost function for all autonomous vehicles, where N is a non-zero natural number.

[0104] By having all autonomous vehicles cooperate, and obtaining the scheduling ranking with the lowest total driving cost based on the cooperation model:

[0105]

[0106] In the formula, P is the total driving cost obtained by cooperating with all autonomous vehicles;

[0107] s i Let be the set of strategies for the i-th autonomous vehicle;

[0108] U i Let N be the function that minimizes the driving cost of the i-th autonomous vehicle, where N is a non-zero natural number.

[0109] σ represents the initial scheduling order. The driving cost function is used for the initial scheduling sorting of the i-th autonomous vehicle.

[0110] In one embodiment, when the scheduling order with the lowest total travel cost is obtained through calculation, the optimal scheduling order of the cooperative model is obtained through a genetic algorithm. The genetic algorithm is an optimization algorithm that simulates natural evolution. By simulating basic operations such as heredity, crossover, and mutation in biological evolution, it seeks the optimal solution or near-optimal solution to the problem.

[0111] The fitness function in the genetic algorithm is:

[0112]

[0113] In the formula, ω is the scheduling threshold of the cooperative model;

[0114] U i g Let U be the driving cost function of the i-th autonomous vehicle using the g-th strategy. i Let be the function that minimizes the driving cost of the i-th autonomous vehicle;

[0115] When the conditions in the fitness function are met, the optimal scheduling order is achieved.

[0116] In one embodiment, when establishing a communication connection for each autonomous vehicle entering the parking lot, the autonomous vehicle communicates with the dispatch center in real time to achieve rapid data transmission and processing, and the communication of the autonomous vehicle is encrypted, data is backed up, and battery capacity is monitored.

[0117] Autonomous vehicles typically employ various communication technologies. For short distances, they utilize Bluetooth or Wi-Fi for wireless communication, offering advantages such as low cost and low power consumption, but with limited transmission distance. For long distances, they utilize mobile communication networks for wireless communication, offering advantages such as stable signal and wide coverage, but network congestion and signal interference can affect communication quality.

[0118] In one embodiment, when obtaining the location of the other party, the autonomous vehicle is equipped with a global positioning system, lidar and vehicle-mounted camera to achieve positioning, and while the autonomous vehicle is driving on the road, it monitors traffic flow in real time by acquiring monitoring data from traffic monitoring facilities.

[0119] S4. Monitor vehicles and tasks in real time, obtain their real-time status, and monitor and handle abnormal situations. For example, issue an alarm when a vehicle malfunction is detected, or adjust parking plans when insufficient driving range is detected.

[0120] like Figure 2 As shown, according to another embodiment of the present invention, a vehicle dispatch management system for unmanned driving is disclosed, the system including a dispatch preparation module 1, a road driving dispatch module 2, a parking dispatch module 3 and a status monitoring module 4.

[0121] The scheduling preparation module 1 is used to obtain the task priority and constraints of the autonomous vehicle.

[0122] The road driving scheduling module 2 is used to control the autonomous vehicle to reach its destination according to the pre-planned driving route and start time of the autonomous vehicle.

[0123] The parking scheduling module 3 is used to detect vehicles at the destination parking lot, obtain parking spaces for autonomous vehicles, and automatically park the autonomous vehicles into the spaces based on parking rules.

[0124] The status monitoring module 4 is used to monitor vehicles and tasks in real time, obtain the real-time status of vehicles and tasks, and monitor and handle abnormal situations in real time.

[0125] In summary, by utilizing the above-mentioned technical solutions of this invention, the vehicle scheduling and management method and system for autonomous driving made vehicle transportation more efficient, safe, and reliable, improving the transportation efficiency and competitiveness of enterprises. This invention fully utilizes traffic monitoring facilities, global positioning systems, lidar, and vehicle-mounted cameras, enabling autonomous vehicles to determine distances and locate each other. When parking autonomous vehicles, this invention obtains the dimensions of the autonomous vehicles and controls them to suitable parking spaces. Even when the dimensions of the autonomous vehicles cannot be obtained, precise measurements can be taken using binocular cameras, allowing vehicles without dimensional data to be placed in suitable parking spaces, achieving automated measurement and improving parking efficiency. This invention uses a cooperative model to achieve the scheduling order with the lowest total operating cost for all autonomous vehicles, thereby enabling intelligent and efficient scheduling and parking of multiple vehicles, further optimizing overall efficiency.

[0126] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A vehicle dispatching and management method for autonomous driving, characterized in that, The method includes the following steps: S1. Obtain the task priority and constraints of the autonomous vehicle; S2. Based on the pre-planned autonomous vehicle driving route and start time, control the autonomous vehicle to reach the destination; S3. At the destination parking lot, perform vehicle detection, obtain parking spaces for the autonomous vehicle, and automatically park the autonomous vehicle into the space based on parking rules. This includes: Establish communication connections with each autonomous vehicle entering the parking lot and obtain their location; guide each autonomous vehicle to its destination parking space according to the shortest path principle; calculate the total driving cost of all autonomous vehicles. IN Ni∈N IN i (with i ) In the formula, s i U represents the set of policies for the i-th autonomous vehicle. i Let U be the function that minimizes the driving cost of the i-th autonomous vehicle. N Let N be the driving cost function for all autonomous vehicles, and N be a non-zero natural number. The scheduling order with the lowest total driving cost is obtained by having all autonomous vehicles cooperate and using the cooperation model. In the formula, P represents the total driving cost obtained through cooperation of all autonomous vehicles; s i U represents the set of policies for the i-th autonomous vehicle. i Let be the function that minimizes the driving cost of the i-th autonomous vehicle, where N is a non-zero natural number, and σ is the initial scheduling order. The driving cost function for the initial scheduling sort of the i-th autonomous vehicle; S4. Monitor vehicles and tasks in real time, obtain their real-time status, and monitor and handle abnormal situations in real time.

2. The vehicle dispatching and management method for autonomous driving according to claim 1, characterized in that, The process of obtaining the task priority and constraints of the autonomous vehicle includes the following steps: S11. Before scheduling autonomous vehicles, clarify the scheduling requirements and constraints of autonomous vehicles to obtain the scheduling scenario. S12. Based on the obtained scheduling scenario, collect the task destination, travel route and start time of the scheduling task to obtain task information; S13. Based on the scheduling scenario and task information, determine the number of unmanned vehicles, their payload capacity, and their driving range.

3. The vehicle dispatching and management method for autonomous driving according to claim 2, characterized in that, The process of detecting vehicles at the destination parking lot and obtaining parking spaces for autonomous vehicles includes the following steps: Install a binocular camera for video measurement at the entrance of the parking lot at the destination, and calibrate the binocular camera in advance; Send a request to obtain the size information of the autonomous vehicle. If the size information of the autonomous vehicle is received in response, determine the parking space of the autonomous vehicle based on the size information. If the feedback cannot obtain the size information of the autonomous vehicle, then the autonomous vehicle will drive into the measurement area. The dimensions of the autonomous vehicles within the measurement area are measured using the calibrated binocular cameras. After the dimensions are measured, the parking space for the autonomous vehicle is determined based on the obtained dimensional information.

4. The vehicle dispatching and management method for autonomous driving according to claim 3, characterized in that, The step of measuring the dimensions of the autonomous vehicle within the measurement area using the calibrated binocular camera includes the following steps: Two images of the autonomous vehicle are acquired from different positions using a calibrated binocular camera, and the projection points on the two images of the autonomous vehicle are obtained. Obtain any point P of the autonomous vehicle w And obtain point P w The optical axis coordinates in the coordinate systems of the two cameras of the stereo camera are obtained simultaneously, along with the homogeneous coordinates of the two projection points in their respective coordinate systems and the coordinates of point P. w Homogeneous coordinates in the world coordinate system; The calibration provides the projection transformation matrix for two images of an autonomous vehicle captured by a binocular camera. It combines the projection transformation matrix with the linear theory of camera imaging, utilizing the coordinates of two optical axes, the homogeneous coordinates of the two projection points in their respective coordinate systems, and point P. w Using homogeneous coordinates in the world coordinate system, we obtain the straight line passing through the two sets of optical centers and the projection point in the binocular camera, and point P... w The intersection of two straight lines leads to point P. w 3D coordinates; By determining the three-dimensional coordinates of each vertex on the autonomous vehicle, the three-dimensional data dimensions of the autonomous vehicle are calculated.

5. The vehicle dispatching and management method for autonomous driving according to claim 4, characterized in that, The process involves setting up a binocular camera for video measurement at the entrance of the parking lot at the destination, and calibrating the binocular camera in advance using a regularly arranged square pattern as a calibration plate, with the size of the square known and its vertices serving as reference points for calibration.

6. The vehicle dispatching and management method for autonomous driving according to claim 1, characterized in that, When the calculation yields the scheduling order with the lowest total travel cost, the optimal scheduling order for the cooperative model is obtained through a genetic algorithm. The fitness function in the genetic algorithm is: In the formula, ω is the scheduling threshold of the cooperative model; Let U be the driving cost function of the i-th autonomous vehicle using the g-th strategy. i Let be the function that minimizes the driving cost of the i-th autonomous vehicle; When the conditions in the fitness function are met, the optimal scheduling order is achieved.

7. A vehicle dispatching and management method for autonomous driving according to claim 6, characterized in that, When establishing a communication connection for each autonomous vehicle entering the parking lot, the autonomous vehicle communicates with the dispatch center in real time to achieve rapid data transmission and processing, and the communication of the autonomous vehicle is encrypted, data is backed up, and battery capacity is monitored.

8. A vehicle dispatching and management method for autonomous driving according to claim 7, characterized in that, When obtaining the location of the other party, the autonomous vehicle is equipped with a global positioning system, lidar and vehicle camera to achieve positioning, and while the autonomous vehicle is driving on the road, it monitors traffic flow in real time by acquiring monitoring data from traffic monitoring facilities.

9. A vehicle dispatching and management system for autonomous driving, used to implement the vehicle dispatching and management method for autonomous driving according to any one of claims 1-8, characterized in that, The system includes a scheduling preparation module, a road driving scheduling module, a parking scheduling module, and a status monitoring module; The scheduling preparation module is used to obtain the task priority and constraints of the autonomous vehicle. The road driving scheduling module is used to control the autonomous vehicle to reach its destination according to the pre-planned driving route and start time of the autonomous vehicle. The parking scheduling module is used to detect vehicles at the destination parking lot, obtain parking spaces for autonomous vehicles, and automatically park the autonomous vehicles into the spaces based on parking rules. The status monitoring module is used to monitor vehicles and tasks in real time, obtain the real-time status of vehicles and tasks, and monitor and handle abnormal situations in real time.

Images