Method and device for controlling speed of vehicle passing through non-signalized intersection

Abstract

The invention discloses a vehicle speed control method and device when passing through a non-signalized intersection, and belongs to the technical field of speed control, and the method comprises the steps: determining an observation region and a regulation and control region of the non-signalized intersection; acquiring a speed sequence of any vehicle in the observation area, and determining a predicted speed sequence of the vehicle in the regulation and control area according to the speed sequence based on a grey prediction method; according to the predicted speed sequence, the current position and the driving path, whether operation conflicts exist in the regulation and control area is judged; when it is judged that the running conflict exists, optimizing the predicted speed sequence through a particle swarm algorithm until the optimized target speed sequence does not have the running conflict, and controlling the vehicle to pass through the regulation and control area based on the target speed sequence; predicting future behaviors of the vehicle through the prediction speed sequence to judge whether running conflicts exist or not; the speed is systematically adjusted through the particle swarm algorithm, the target speed sequence is obtained from the whole situation, and the reliability of speed control is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of speed control, and particularly to a vehicle speed control method and device when passing through an un-signalized intersection. Background Art

[0002] As an important part of intelligent logistics, autonomous vehicles are gradually changing the operation mode of the logistics industry. However, at un-signalized intersections, autonomous vehicles face complex traffic environments and potential safety hazards. These intersections lack the guidance of traffic lights, and the interaction and decision-making between vehicles require more refined and intelligent control methods.

[0003] However, current methods and technologies for the control of autonomous vehicles at intersections mainly focus on path planning, obstacle avoidance, and emergency stopping, emphasizing single-vehicle autonomous decision-making, lacking multi-vehicle collaborative optimization, prone to local optimality, and may also lead to lagging control strategies, thus affecting the safety and traffic efficiency of autonomous vehicles.

[0004] Therefore, in the process of controlling the speed of vehicles passing through un-signalized intersections, the existing technology has the problem of being difficult to make a systematic optimal adjustment for the whole. Summary of the Invention

[0005] In view of this, it is necessary to provide a vehicle speed control method and device when passing through an un-signalized intersection to solve the problem that in the process of controlling the speed of vehicles passing through un-signalized intersections, the existing technology is difficult to make a systematic optimal adjustment for the whole.

[0006] To solve the above problems, in a first aspect, the present invention provides a vehicle speed control method when passing through an un-signalized intersection, including: Determine the observation area and regulation area of the un-signalized intersection; Obtain the speed sequence of any vehicle in the observation area, and determine the predicted speed sequence of the vehicle in the regulation area based on the grey prediction method according to the speed sequence; Judge whether there is a running conflict in the regulation area according to the predicted speed sequence, the current position, and the driving path; When it is judged that there is a running conflict, optimize the predicted speed sequence through the particle swarm algorithm until there is no running conflict in the optimized target speed sequence, and control the vehicle to pass through the regulation area based on the target speed sequence.

[0007] In a possible implementation manner, determining the observation area and regulation area of the un-signalized intersection includes: Determine the monitoring area of the un-signalized intersection according to the monitoring range of the monitoring device for monitoring the un-signalized intersection; Divide the monitoring area into an observation area and a regulation area according to a preset ratio; Among them, the monitoring device is set at the center of the intersection area of the signal-free intersection or the circular area composed of multiple intersection areas; the intersection area is within the regulation area, and the observation area is located on the side of the regulation area far from the intersection area.

[0008] In a possible implementation manner, determining the predicted speed sequence of the vehicle in the regulation area based on the gray prediction method includes: Successively perform acceleration index transformation and geometric mean processing on the speed sequence to obtain a zero-speed sequence; Perform an accumulation operation on the zero-speed sequence to obtain a first speed sequence, and determine the mean value of the first speed sequence as the initial condition; Based on the initial condition, construct the whiting equation and gray differential equation of the gray prediction model to obtain the time response sequence of the first speed sequence; Restore the time response sequence to obtain the predicted speed sequence of the speed sequence.

[0009] In a possible implementation manner, judging whether there is a running conflict in the regulation area according to the predicted speed sequence, current position and driving path of any vehicle includes: Perform integral processing on the predicted speed sequence, and combine the current position and driving path to determine the predicted position of any vehicle at any moment; Judge whether the distance difference between the predicted positions of at least two vehicles at any specific moment is less than a preset distance threshold; If so, it is determined that there is a running conflict in the regulation area; If not, it is determined that there is no running conflict in the regulation area.

[0010] In a possible implementation manner, optimizing the predicted speed sequence by the particle swarm algorithm includes: Construct a speed planning model; Determine the constraint conditions of the speed planning model based on time constraints, speed interval constraints and path constraints; Obtain the conflict position where a running conflict occurs, and update the speed of the vehicle closest to the conflict position based on the speed update equation of the particle swarm optimization algorithm.

[0011] In a possible implementation manner, updating the speed of the vehicle closest to the conflict position includes: Based on the predicted speed sequence, the updated speed sequence and the current position, calculate the time difference for the vehicle to reach the conflict position; According to the time difference and the safety time difference, construct the cost function in the iterative process of the speed planning model; Select the predicted speed sequence when the cost function is the smallest as the target speed sequence.

[0012] In a possible implementation manner, the velocity update equation based on the particle swarm optimization algorithm is as follows:

[0013]

[0014]

[0015]

[0016]

[0017]

[0018] Wherein, k represents the current iteration number, is i the velocity of the particle in k the iteration, is i the position of the particle in k the iteration, is the non-linear inertia weight, and are the acceleration coefficients, and are random numbers , pbest and gbest are the individual best and the global best respectively, represents the set maximum velocity, r(0) is a random number distributed in [0, 1], represents the maximum number of iterations, a 、 b are constant coefficients.

[0019] In a second aspect, the present invention further provides a vehicle speed control device when passing through an unsignalized intersection, including: A zoning module, configured to determine an observation area and a regulation area of the unsignalized intersection; A speed sequence prediction module, configured to obtain the speed sequence of any vehicle in the observation area, and determine the predicted speed sequence of the vehicle in the regulation area based on the grey prediction method according to the speed sequence; A conflict judgment module, configured to judge whether there is a running conflict in the regulation area according to the predicted speed sequence, the current position and the driving path of any vehicle; A speed optimization module, configured to, when it is judged that there is a running conflict, optimize the predicted speed sequence through the particle swarm algorithm until there is no running conflict in the optimized target speed sequence, and control the vehicle to pass through the regulation area based on the target speed sequence.

[0020] In a third aspect, the present invention further provides an intelligent roadside device, including a memory and a processor, wherein, The memory is used for storing programs; The processor is coupled to the memory and is used for executing the programs stored in the memory to implement the steps in the vehicle speed control method when passing through an unsignalized intersection as described above.

[0021] In a fourth aspect, the present invention further provides a computer-readable storage medium for storing computer-readable programs or instructions, and when the programs or instructions are executed by a processor, the steps in the vehicle speed control method when passing through an unsignalized intersection as described above can be implemented.

[0022] The beneficial effects of adopting the above embodiments are as follows: The present invention provides a vehicle speed control method when passing through an unsignalized intersection. By monitoring the speed in the observation area, the speed sequence of the vehicle in the observation area is obtained; the predicted speed sequence in the regulation area is determined by the grey prediction method, realizing the prediction of the future behavior of the vehicle, thereby adaptively judging whether there are running conflicts; the predicted speed sequence is optimized by the particle swarm algorithm, and the speeds of all vehicles are systematically adjusted, realizing the acquisition of the target speed sequence of all vehicles from a global perspective, and greatly improving the reliability of speed control. Description of the Drawings

[0023] Figure 1 It is a schematic flowchart of an embodiment of the vehicle speed control method when passing through an unsignalized intersection provided by the present invention; Figure 2 It is a schematic flowchart of an embodiment of determining the observation area and regulation area of an unsignalized intersection provided by the present invention; Figure 3 It is a schematic diagram of the result of an embodiment of the monitoring area division result provided by the present invention; Figure 4 It is a schematic flowchart of an embodiment of determining the predicted speed sequence of a vehicle in the regulation area provided by the present invention; Figure 5 It is a schematic flowchart of an embodiment of the grey prediction model provided by the present invention; Figure 6 It is a schematic flowchart of an embodiment of optimizing the predicted speed sequence by the particle swarm algorithm provided by the present invention; Figure 7 It is a schematic flowchart of an embodiment of automatically detecting conflicts and iterating provided by the present invention; Figure 8 It is a schematic flowchart of an embodiment of updating the speed of the vehicle closest to the conflict position provided by the present invention; Figure 9Schematic flowchart of an embodiment of determining a target speed sequence by a particle swarm algorithm provided by the present invention; Figure 10 Schematic structural diagram of an embodiment of a vehicle speed control device when passing through an intersection without signals provided by the present invention; Figure 11 Block diagram of an embodiment of an intelligent roadside device provided by the present invention. Specific embodiments

[0024] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present invention.

[0025] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in the present invention illustrate the operations implemented according to some embodiments of the present invention. It should be understood that the operations in the flowchart may not be implemented in sequence, and steps without logical context relationships may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present invention. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.

[0026] The descriptions such as "first" and "second" involved in the embodiments of the present invention are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Therefore, the technical features defined with "first" and "second" may explicitly or implicitly include at least one such feature.

[0027] Referring to "embodiment" in this article means that the specific features, structures or characteristics described in connection with the embodiment may be included in at least one embodiment of the present invention. The appearance of this phrase in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0028] In order to solve the problem that it is difficult to make a systematic and optimal adjustment to the overall situation in the process of vehicle speed control when passing through an unsignalized intersection in the prior art, the present invention provides a vehicle speed control method and device when passing through an unsignalized intersection, which will be described in detail below.

[0029] As Figure 1 shown, Figure 1 is a schematic flowchart of an embodiment of the vehicle speed control method when passing through an unsignalized intersection provided by the present invention, including: S101: Determine the observation area and regulation area of the unsignalized intersection; In some embodiments of the present invention, an unsignalized intersection refers to an intersection where traffic flows in all directions are not controlled by traffic lights. Such intersections have the characteristic of free flow of traffic, but at the same time, there are also potential traffic safety hazards. There are various types of unsignalized intersections, among which the common ones are cross-shaped intersections and T-shaped intersections. A cross-shaped intersection is formed by the intersection of two roads, forming traffic flows in four directions. A T-shaped intersection is where one road intersects with another road, with one road being the main line and the other being the branch line. In addition, a roundabout intersection is also a special type of unsignalized intersection, consisting of a roundabout or disk, and vehicles circle around the roundabout to achieve intersection traffic.

[0030] In some embodiments of the present invention, the observation area is an area for collecting and analyzing vehicle information so that the system can predict potential conflict risks. In the observation area, it is necessary to focus on and collect information such as the driving state, speed, and direction of vehicles, and use this information to determine whether there is a possibility of conflict with other vehicles. The setting of the observation area helps to detect potential safety hazards in advance and provides sufficient time and space for autonomous vehicles to take corresponding avoidance or deceleration operations.

[0031] In some embodiments of the present invention, the regulation area is a controlled range, which is determined according to parameters such as the normal driving speed, braking ability, and braking distance of the vehicle. If other vehicles enter this range, the autonomous vehicle needs to perform corresponding avoidance or speed adjustment operations to ensure safe passage. The setting of the regulation area aims to reduce the risk of traffic accidents by adjusting the speed of vehicles entering this area.

[0032] S102: Obtain the speed sequence of any vehicle in the observation area, and determine the predicted speed sequence of the vehicle in the regulation area based on the grey prediction method according to the speed sequence; In some embodiments of the present invention, the speed sequence refers to arranging the speed data of the vehicle at different time points in chronological order to form a time series. This sequence reflects the speed change of the vehicle over continuous time.

[0033] In some embodiments of the present invention, grey prediction, also known as Grey Prediction or Grey Forecasting, is a method of establishing a mathematical model through a small amount of incomplete information, and then predicting the future development trend and situation of the system. Grey prediction is a prediction method based on grey system theory, which is mainly used to predict systems with uncertain factors or incomplete information. It is based on the development laws of objective things in the past and present, and uses scientific methods to describe and analyze the future development trend, and form scientific hypotheses and judgments.

[0034] In some embodiments of the present invention, the predicted speed sequence refers to a sequence composed of the speeds at which the vehicle may travel in the future obtained by learning the laws of the speed sequence.

[0035] S103: According to the predicted speed sequence, the current position, and the driving path, determine whether there is a running conflict in the regulation area; In some embodiments of the present invention, a running conflict refers to a risk situation of possible intersection or collision between different vehicles in terms of time and space. Specifically, when two or more vehicles are expected to occupy the same or adjacent spatial positions within the regulation area (i.e., the controlled range) at the same time or within a short time, a running conflict is formed.

[0036] S104: When it is determined that there is a running conflict, optimize the predicted speed sequence through the particle swarm algorithm until there is no running conflict in the optimized target speed sequence, and control the vehicle to pass through the regulation area based on the target speed sequence.

[0037] In some embodiments of the present invention, the particle swarm algorithm (Particle Swarm Optimization, PSO) is an optimization algorithm based on swarm intelligence, and its core idea originates from the study of the foraging behavior of bird flocks. The algorithm finds the optimal solution to the problem by simulating the information sharing and cooperation process among individuals in the bird flock. Specifically, the particle swarm algorithm regards the possible solutions in the optimization problem as particles, and these particles continuously move and update in the solution space to find the optimal solution. Each particle has two attributes: speed and position. The speed is a vector, including the speed magnitude and direction, and the position represents the coordinates where the particle is currently located. The optimal solution is found by updating the speed and position of the particle.

[0038] In this embodiment, by monitoring the speed in the observation area, the speed sequence of the vehicle in the observation area is obtained; by using the grey prediction method to determine the predicted speed sequence in the regulation area, the future behavior of the vehicle is predicted, so as to adaptively judge whether there is a running conflict; by using the particle swarm algorithm to optimize the predicted speed sequence and systematically adjust the speeds of all vehicles, the target speed sequence of all vehicles is obtained from a global perspective, greatly improving the reliability of speed control.

[0039] In some embodiments of the present invention, in order to control the speed of vehicles at an unsignalized intersection, it is necessary to set up monitoring devices to collect data and to divide the area in detail so as to better serve speed control. In S101, as Figure 2 shown Figure 2 is a schematic flowchart of an embodiment for determining the observation area and the regulation area of an unsignalized intersection provided by the present invention, including: S201: Determine the monitoring area of the unsignalized intersection according to the monitoring range of the monitoring devices for monitoring the unsignalized intersection; In some embodiments of the present invention, the monitoring devices can be selected from at least one of a camera, a lidar (LiDAR), a GPS speedometer, an inductive loop speedometer, a video speed measurement system, a wheel speed sensor, etc. as needed to measure the vehicle speed and to position the vehicle.

[0040] In some embodiments of the present invention, the monitoring area refers to the area range that can be observed by the monitoring devices, and will change accordingly according to the performance of the monitoring devices, which will not be elaborated here.

[0041] S202: Divide the monitoring area into an observation area and a regulation area according to a preset ratio; Among them, the monitoring devices are arranged at the center of the intersection area of the unsignalized intersection or the circular area composed of multiple intersection areas; the intersection area is within the range of the regulation area, and the observation area is located on the side of the regulation area far from the intersection area.

[0042] In some embodiments of the present invention, the preset ratio is preferably 1:1, as Figure 3 shown Figure 3 is a schematic diagram of the result of an embodiment of the division of the monitoring area provided by the present invention, that is, with the monitoring device as the center and the monitoring distance of the monitoring device as the radius, the range of the monitoring area is determined. Further, it is divided according to 1:1 of the radius, and the part far from the monitoring device is defined as the observation area, and the part including the location of the monitoring device is defined as the regulation area.

[0043] It should be noted that generally, except for roundabouts, monitoring devices cannot be set at the intersection positions of signal-free intersections. Therefore, in other embodiments, the range of the monitoring area can also be divided according to other methods, such as: determining the range of the monitoring area of the signal-free intersection through historical experience, the braking distance of vehicles, the speed range of vehicles, or other conditions; correspondingly, monitoring devices can also be set on each branch of the signal-free intersection to effectively obtain vehicle data on different branch sections to ensure that complete systematic data can be obtained.

[0044] In addition, the preset ratio can also be adjusted as needed, especially when the need to prioritize speed adjustment is required. When the number of vehicles passing through the signal-free intersection is large, it is obvious that the range of the regulation area needs to be increased, which will not be elaborated here.

[0045] In some embodiments of the present invention, in S102, first, in order to obtain the speed sequence of any vehicle in the observation area, when any vehicle enters the observation area from the outside, the running speed of the vehicle is obtained at preset time intervals to obtain the speed sequence.

[0046] In some embodiments of the present invention, the time interval can be adaptively controlled according to the speed of the vehicle. Preferably, the preset time interval is set to 0.5 seconds.

[0047] The speed sequence is a speed data packet obtained by arranging the obtained running speeds in chronological order. For example, for each time interval, the vehicle speed obtained is , then its corresponding speed sequence is .

[0048] Furthermore, in order to determine the predicted speed sequence of the vehicle in the regulation area based on the grey prediction method, as Figure 4 shown, Figure 4 is a schematic flowchart of an embodiment for determining the predicted speed sequence of the vehicle in the regulation area provided by the present invention, including: S401: Perform acceleration index transformation and geometric mean processing on the speed sequence in turn to obtain a zero-speed sequence; In some embodiments of the present invention, performing acceleration index transformation on the speed sequence to obtain an acceleration index transformation speed sequence. Specifically, each speed in the speed sequence is multiplied by an acceleration index transformation coefficient to obtain the corresponding acceleration index transformation speed, and then the acceleration index transformation speed sequence is determined. The formula involved is as follows:

[0049] , k = 1, 2, …, n

[0050] Among them, is the acceleration exponential transformation coefficient, is the k th acceleration exponential transformation speed, is the acceleration exponential transformation speed sequence.

[0051] Furthermore, it is also necessary to perform a geometric mean generation transformation on the acceleration exponential transformation speed sequence to obtain the zero-speed sequence. Specifically, the data in the acceleration exponential transformation speed sequence is accumulated to obtain the zero speed , and then the zero-speed sequence is determined. The formulas involved are as follows: , k = 1, 2, …, n

[0052] Among them, is the k th zero speed.

[0053] S402: Perform an accumulation operation on the zero-speed sequence to obtain the first speed sequence, and determine the mean value of the first speed sequence as the initial condition; In some embodiments of the present invention, when performing an accumulation operation on the zero-speed sequence to obtain the first speed sequence the formulas involved are as follows:

[0054] , k = 1, 2, …, n Among them, is the k th first speed.

[0055] Furthermore, generally, the traditional grey prediction model of the stochastic oscillation sequence takes the first component of the sequence as the initial condition of the grey differential model, ignoring the influence of other components on the numerical fluctuation. Therefore, the overall utilization of information is not sufficient, resulting in a decrease in the prediction accuracy. In this application, the average value of the original speed sequence is selected as the initial condition of the grey model. Among them, the calculation formula of

[0056] S403: Based on the initial condition, construct the whiting equation and grey differential equation of the grey prediction model to obtain the time response sequence of the first speed sequence; It should be noted that in this embodiment, the average value of the selected sequence is used as the initial condition of the whitening equation and the grey differential equation, where The calculation formula of

[0057] In some embodiments of the present invention, taking as the initial condition, the whitening equation of the model is:

[0058] where a and b are the parameters to be estimated of the model, t is the time.

[0059] By integration, the grey differential equation of the GM(1,1) model is:

[0060] where k = 2, 3, …, n .

[0061] Then, based on the initial condition , the time response sequence of the GM(1,1) model is:

[0062] where the parameters a and b are obtained by least squares estimation.

[0063] ，

[0064] The restored value is , k = 1, 2, …, n.

[0065] In this embodiment, by establishing the model whitening equation and the time response sequence with the average value of the selected sequence as the initial condition, all the observed information can be fully utilized, and the prediction accuracy is greatly improved.

[0066] S404: Restore the time response sequence to obtain the predicted speed sequence of the speed sequence.

[0067] In some embodiments of the present invention, restoring the sequence gives , where:

[0068] where k = 2, 3, … n .

[0069] While

[0070] Further restoration gives

[0071] where represents the predicted value of the main sequence, k = 2, 3, … n .

[0072] To illustrate the process of constructing the grey prediction model, as Figure 5 shown, Figure 5 is a schematic flow diagram of an embodiment of the grey prediction model provided by the present invention, where the speed sequence is a sequence composed of speed values monitored in the observation area, is the predicted speed sequence.

[0073] In this embodiment, the speed prediction is performed according to the speed sequence through the grey prediction model, and the possible running speed of the vehicle in the regulation area is obtained predictively, that is, the predicted speed sequence, so that the position reached by the vehicle at any moment in the regulation area can be determined, facilitating subsequent data analysis and regulation.

[0074] In some embodiments of the present invention, in S103, after determining the predicted speed sequence of the vehicle, in order to determine whether there is a running conflict in the regulation area, first, the predicted speed sequence is integrated, and combined with the current position and the driving path, the predicted position of any vehicle at any moment is determined; then, it is judged whether the distance difference between the predicted positions of at least two vehicles at any specific moment is less than a preset distance threshold; If so, it is determined that there is a running conflict in the regulation area; If not, it is determined that there is no running conflict in the regulation area.

[0075] In some embodiments of the present invention, since the vehicle itself has a certain length and a certain point of the vehicle is located during the positioning process, therefore, in order to ensure the safety of the vehicle, when the distance difference between the predicted positions of two vehicles is less than the preset distance threshold, that is, it is determined that there is an overlap in time and space between the two, and it is also determined that there is a running conflict between the vehicles.

[0076] Specifically, the distance threshold can be adaptively set according to conditions such as the actual model of the vehicle and the running speed, which is not limited herein. Among them, the distance threshold is preferably the maximum value of the lengths of all vehicles or a fixed value. Generally, the distance threshold is set to 4 meters.

[0077] In this embodiment, the speed conditions of each vehicle from entering the regulation area to completely leaving the monitoring area are predicted through a gray prediction model. The instantaneous speed of the vehicle is obtained at a preset time interval, and then the position of the vehicle at each time point is calculated by means of integration. If two or more logistics vehicles overlap in space and time, it means that a conflict has occurred, realizing the integration of the future behavior of the vehicle into the speed control strategy, and being able to better ensure the timeliness of the speed control strategy.

[0078] In some embodiments of the present invention, in S104, when it is determined that there is a running conflict in the regulation area, it is necessary to systematically plan the speeds of all vehicles, such as Figure 6 shown Figure 6 is a schematic flowchart of an embodiment of optimizing the predicted speed sequence by a particle swarm algorithm provided by the present invention, including: S601: Construct a speed planning model; S602: Determine the constraint conditions of the speed planning model based on time constraints, speed interval constraints, and path constraints; In some embodiments of the present invention, the constraint conditions of the speed planning model are: Time constraint: There should be no overlap in the space-time domain where the vehicle reaches each potential conflict point; Speed interval constraint: V max , V max can be adjusted according to actual needs. In a specific embodiment, V max takes the value ; Path constraint: The path of each vehicle is known and fixed It should be noted that during the process of adjusting the speed, for multiple vehicles corresponding to the occurrence position of the running conflict, when the speed of the vehicle with a higher speed is less than V max , it is preferred that the vehicle accelerates through; when the speed of the vehicle with a higher speed is equal to V max , it is preferred that the vehicle with a lower speed decelerates through.

[0079] In addition, in order to better ensure the operation of the vehicle, an optimization goal also needs to be set, that is: all vehicles can pass through the intersection safely in the shortest possible time.

[0080] In this embodiment, by adaptively setting relevant parameters during the vehicle operation, it can better ensure the rationality of the vehicle during the optimization process and the adaptability to the actual situation, thus ensuring the driving safety of the vehicle.

[0081] S603: Obtain the conflict position where the operation conflict occurs, and update the speed of the vehicle closest to the conflict position based on the velocity update equation of the particle swarm optimization algorithm.

[0082] In some embodiments of the present invention, the velocity update equation of the particle swarm optimization algorithm is:

[0083]

[0084]

[0085]

[0086]

[0087]

[0088] Wherein, k represents the current iteration number, is i the velocity of the particle in k the -th iteration, is i the position of the particle in k the -th iteration, is the non-linear inertia weight, and are the acceleration coefficients, and are random numbers , pbest and gbest are the individual best and the global best respectively, represents the set maximum velocity, r(0) is a random number distributed in [0, 1], represents the maximum number of iterations, a 、 b are constant coefficients.

[0089] In this embodiment, by constructing constraint conditions and combining the particle swarm optimization algorithm to update the speed, it can achieve automatic iterative calculation of the vehicle operation speed, and combined with the determination conditions of operation conflicts, it can achieve multi-faceted optimization to obtain a reasonable optimized speed sequence.

[0090] In some embodiments of the present invention, in order to intuitively show the optimization iteration steps of this embodiment, as Figure 7 shown,Figure 7 The flow chart of an embodiment for automatically detecting conflicts and iterating in the present invention. By taking the vehicle closest to the conflict point as a breakthrough point, adjusting the speed of this vehicle, then re-identifying conflicts, and then using the distance from the breakthrough point as a reference standard to control the speed of the vehicle, it is possible to achieve the maximum possible speed increase for the vehicle, so that all vehicles can pass through the intersection in the shortest possible time and reduce conflicts.

[0091] In some embodiments of the present invention, in S603, since there may be multiple reasonable predicted speed sequences obtained through optimization, in order to select the best among the best, as Figure 8 shown, Figure 8 The flow chart of an embodiment for updating the speed of the vehicle closest to the conflict position provided by the present invention includes: S801: Calculate the time difference for the vehicle to reach the conflict position based on the predicted speed sequence, the updated speed sequence, and the current position; S802: Construct the cost function in the iterative process of the speed planning model according to the time difference and the safety time difference; In some embodiments of the present invention, the safety time difference is the time required for a vehicle far from the conflict position to reach the conflict position based on the optimized speed. In other embodiments, the safety time difference can also be set as a fixed value according to actual needs, which is not limited here.

[0092] In some embodiments of the present invention, the time difference refers to the difference between the time for the vehicle to reach the conflict position based on the optimized speed and the time to reach the conflict position based on the initial predicted speed.

[0093] Cost function The expression is:

[0094] In the formula, n is the total number of vehicles, is the time difference, is the safety time difference.

[0095] S803: Select the predicted speed sequence when the cost function is the smallest as the target speed sequence.

[0096] In this embodiment, by taking the cost function as a reference standard, all predicted speed sequences that meet the constraint conditions are screened twice to determine the optimal target speed sequence.

[0097] It should be noted that in this embodiment, with the goal of minimizing the change in time, correspondingly, that is, enabling all vehicles to minimize the speed mutation as much as possible, thereby improving the stability and safety of vehicle operation.

[0098] Further, in order to better demonstrate the optimization and iteration steps of this embodiment, as Figure 9 shown, Figure 9 FIG. Figure 9 is a schematic flowchart of an embodiment of a method for determining a target speed sequence by a particle swarm algorithm provided by the present invention. The speed is iterated by the particle swarm algorithm, and the cost function is used as a criterion to evaluate the quality of the predicted speed sequence, realizing the automatic determination of a better target speed sequence and meeting the high-efficiency requirements of speed control.

[0099] In this embodiment, by monitoring the speed in the observation area, the speed sequence of the vehicle in the observation area is obtained; the predicted speed sequence in the regulation area is determined by the grey prediction method, realizing the prediction of the future behavior of the vehicle, and thus adaptively judging whether there is a running conflict; the predicted speed sequence is optimized by the particle swarm algorithm, and the speeds of all vehicles are systematically adjusted, realizing the acquisition of the target speed sequence of all vehicles from a global perspective, greatly improving the reliability of speed control. Further, by using the cost function as a reference standard, the predicted speed sequences that meet the constraint conditions are secondarily screened, realizing the reduction of the speed mutation of the vehicle as much as possible and improving the stability and safety of the vehicle operation.

[0100] In order to better implement the vehicle speed control method when passing through an unsignalized intersection in the embodiment of the present invention, correspondingly, the embodiment of the present invention also provides a vehicle speed control device when passing through an unsignalized intersection, as Figure 10 shown, Figure 10 FIG. Figure 10 is a schematic structural diagram of an embodiment of a vehicle speed control device when passing through an unsignalized intersection provided by the present invention. The vehicle speed control device 1000 when passing through an unsignalized intersection includes: A zoning module 1001, configured to determine an observation area and a regulation area of the unsignalized intersection; A speed sequence prediction module 1002, configured to obtain the speed sequence of any vehicle in the observation area, and determine the predicted speed sequence of the vehicle in the regulation area based on the grey prediction method according to the speed sequence; A conflict judgment module 1003, configured to judge whether there is a running conflict in the regulation area according to the predicted speed sequence, current position and driving path of any vehicle; A speed optimization module 1004, configured to, when it is judged that there is a running conflict, optimize the predicted speed sequence by the particle swarm algorithm until there is no running conflict in the optimized target speed sequence, and control the vehicle to pass through the regulation area based on the target speed sequence.

[0101] As Figure 11 shown, Figure 11 FIG. Figure 11 is a schematic structural block diagram of an embodiment of an intelligent roadside device provided by the present invention. The intelligent roadside device 1100 includes a processor 1101, a memory 1102 and a display 1103. Figure 11Only some components of the intelligent roadside device 1100 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively.

[0102] In some embodiments, the processor 1101 can be a central processing unit (CPU), a microprocessor, or other data processing chips, which are used to run the program code stored in the memory 1102 or process data, such as the vehicle speed control method when passing through an unsignalized intersection in the present invention.

[0103] In some embodiments, the processor 1101 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processor 1101 can be local or remote. In some embodiments, the processor 1101 can be implemented on a cloud platform. In one embodiment, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination of the above.

[0104] In some embodiments, the memory 1102 can be an internal storage unit of the intelligent roadside device 1100, such as the hard disk or memory of the intelligent roadside device 1100. In some other embodiments, the memory 1102 can also be an external storage device of the intelligent roadside device 1100, such as a plug-in hard disk equipped on the intelligent roadside device 1100, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc.

[0105] Furthermore, the memory 1102 can also include both the internal storage unit of the intelligent roadside device 1100 and the external storage device. The memory 1102 is used to store the application software installed in the intelligent roadside device 1100 and various types of data.

[0106] In some embodiments, the display 1103 can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. The display 1103 is used to display the information in the intelligent roadside device 1100 and to display a visual user interface. The components 1101-1103 of the intelligent roadside device 1100 communicate with each other through a system bus.

[0107] In one embodiment, when the processor 1101 executes the vehicle speed control program when passing through an unsignalized intersection in the memory 1102, the following steps can be achieved: Determine the observation area and regulation area of the unsignalized intersection; Obtain the speed sequence of any vehicle in the observation area, and determine the predicted speed sequence of the vehicle in the regulation area based on the speed sequence according to the grey prediction method; Judge whether there is a running conflict in the regulation area according to the predicted speed sequence, the current position and the driving path; When it is judged that there is a running conflict, optimize the predicted speed sequence through the particle swarm algorithm until there is no running conflict in the optimized target speed sequence, and control the vehicle to pass through the regulation area based on the target speed sequence.

[0108] Determine the observation area and the regulation area of the unsignalized intersection; Obtain the speed sequence of any vehicle in the observation area, and determine the predicted speed sequence of the vehicle in the regulation area based on the speed sequence according to the grey prediction method; Judge whether there is a running conflict in the regulation area according to the predicted speed sequence, the current position and the driving path of any vehicle; When it is judged that there is a running conflict, optimize the predicted speed sequence through the particle swarm algorithm until there is no running conflict in the optimized target speed sequence, and control the vehicle to pass through the regulation area based on the target speed sequence.

[0109] It should be understood that when the processor 1101 executes the vehicle speed control program when passing through the unsignalized intersection in the memory 1102, in addition to the above functions, other functions can also be realized. For specific details, reference can be made to the description of the corresponding method embodiments above.

[0110] Furthermore, the type of the intelligent roadside device 1100 mentioned in the embodiments of the present invention is not specifically limited. The intelligent roadside device 1100 can be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of the portable electronic device include, but are not limited to, portable electronic devices equipped with IOS, android, microsoft or other operating systems. The above portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (such as a touch panel). It should also be understood that in some other embodiments of the present invention, the intelligent roadside device 1100 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (such as a touch panel).

[0111] Correspondingly, an embodiment of the present application further provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the programs or instructions are executed by a processor, the steps or functions in the vehicle speed control method when passing through the unsignalized intersection provided by the above method embodiments can be realized.

[0112] Those skilled in the art can understand that all or part of the processes of implementing the methods of the above embodiments can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a disk, an optical disc, a read-only memory or a random access memory, etc.

[0113] The vehicle speed control method, device, electronic device and storage medium when passing through a signal-free intersection provided by the present invention have been introduced in detail above. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for controlling vehicle speed when passing through an unsignalized intersection, characterized in that: include: Determine the observation and control areas of unsignalized intersections; Obtaining a speed sequence of any vehicle in the observation area, and determining a predicted speed sequence of the vehicle in the control area according to the speed sequence based on a grey prediction method; Determining whether there is an operation conflict in the control area according to the predicted speed sequence, the current position and the driving path; When it is determined that the operation conflict exists, the predicted speed sequence is optimized by a particle swarm algorithm until the optimized target speed sequence has no operation conflict, and the vehicle is controlled to pass through the control area based on the target speed sequence.

2. The method for controlling vehicle speed when passing through an unsignalized intersection according to claim 1, characterized in that: The determination of the observation area and the control area of ​​the unsignalized intersection includes: Determining a monitoring area of ​​the unsignalized intersection according to a monitoring range of a monitoring device that monitors the unsignalized intersection; Dividing the monitoring area into the observation area and the control area according to a preset ratio; Wherein, the monitoring equipment is arranged at the intersection area of ​​the unsignalized intersection or the center of a circular area composed of multiple intersection areas; the intersection area is within the scope of the control area, and the observation area is located on the side of the control area away from the intersection area.

3. The vehicle speed control method when passing through an unsignalized intersection according to claim 1, characterized in that: The method of determining the predicted speed sequence of the vehicle in the control area according to the speed sequence based on the grey prediction method includes: The speed sequence is subjected to acceleration exponential transformation and geometric mean processing in sequence to obtain a zero-number speed sequence; Performing an accumulation operation on the zero-speed sequence to obtain a first speed sequence, and determining a mean value of the first speed sequence as an initial condition; constructing a whitening equation and a grey differential equation of a grey prediction model based on the initial conditions to obtain a time response sequence of the first velocity sequence; The time response sequence is restored to obtain the predicted speed sequence of the speed sequence.

4. The method for controlling vehicle speed when passing through an unsignalized intersection according to claim 1, characterized in that: The determining whether there is an operation conflict in the control area according to the predicted speed sequence, the current position and the driving path includes: Integrating the predicted speed sequence and combining the current position and the driving path to determine the predicted position of any vehicle at any time; Determining whether there are at least two vehicles whose predicted positions have a distance difference less than a preset distance threshold at any specific time; If so, it is determined that there is an operation conflict in the regulatory region; If not, it is determined that the control area has no operation conflict.

5. The method for controlling vehicle speed when passing through an unsignalized intersection according to claim 1, characterized in that: The optimizing the predicted speed sequence by using a particle swarm algorithm comprises: Build a speed planning model; Determining the constraint conditions of the speed planning model based on time constraints, speed interval constraints and path constraints; The conflict position where the running conflict occurs is obtained, and the speed of the vehicle closest to the conflict position is updated based on the particle swarm optimization algorithm speed update equation.

6. The method for controlling vehicle speed when passing through an unsignalized intersection according to claim 5, characterized in that: The updating of the speed of the vehicle closest to the conflicting position comprises: Calculating a time difference between the vehicle and the conflicting position based on the predicted speed sequence, the updated speed sequence and the current position; Constructing a cost function of the speed planning model in an iterative process according to the time difference and the safety time difference; The predicted speed sequence with the minimum cost function is selected as the target speed sequence.

7. The method for controlling vehicle speed when passing through an unsignalized intersection according to claim 5, characterized in that: The speed update equation based on the particle swarm optimization algorithm is: in, k Indicates the current iteration number, for i Particles in k The speed in the iteration, for i Particles in k The position in the iteration, is the nonlinear inertia weight, and is the acceleration factor, and is a random number , pbest and gbest are the individual optimum and the global optimum respectively. Indicates the maximum speed setting. r(0) is a random number distributed in [0, 1], represents the maximum number of iterations, and a and b are constant coefficients.

8. A vehicle speed control device when passing through an unsignalized intersection, characterized in that: include: A zoning module to determine the observation and control zones of unsignalized intersections; A speed sequence prediction module, used for obtaining a speed sequence of any vehicle in the observation area, and determining a predicted speed sequence of the vehicle in the control area according to the speed sequence based on a grey prediction method; a conflict judgment module, used for judging whether there is an operation conflict in the control area according to the predicted speed sequence, current position and driving path of any vehicle; The speed optimization module is used to optimize the predicted speed sequence by a particle swarm algorithm when it is determined that there is an operation conflict, until the optimized target speed sequence has no operation conflict, and control the vehicle to pass through the control area based on the target speed sequence.

9. An intelligent roadside device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the vehicle speed control method when passing through an unsignalized intersection as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the vehicle speed control method when passing through an unsignalized intersection as described in any one of claims 1 to 7.

Images