Ramp landing continuous passing speed control system based on vehicle-road collaboration

Abstract

The present invention discloses a ramp landing continuous passing speed control system based on vehicle-road collaboration, and the system main control of the vehicle is connected to all vehicle-mounted terminals, speed control systems and traffic management centers. The driving data collected by the vehicle-mounted terminals is transmitted to the traffic management center through the system main control; the roadside equipment collects the vehicle driving data of the current road, and transmits the information to the traffic management center through the communication network; the signal control center server receives the green light time of all signal lights, converts it into green light information and transmits it to the traffic management center; the traffic management center analyzes the green light information of all signal lights and vehicle driving data information received, and synchronizes the green light information to the system main control of the vehicle; the speed control system receives the command of the system main control, adaptively adjusts the speed, and ensures passage within the green light time of the landing ramp intersection. The present invention effectively improves the traffic efficiency and driving experience of vehicles at the intersection of the ramp landing.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and in particular to a ramp landing continuous passing speed control system based on vehicle-road collaboration. Background Art

[0002] The expressway landing ramp is located at the entrance road of the intersection. Vehicles leaving the main line sometimes encounter a red light as soon as they arrive at the ground intersection, and sometimes even encounter an extreme situation where the green light just turns red. The traffic on the landing ramp continues to queue up and spread at the entrance road of the ground intersection until it spreads to the main line of the expressway, causing traffic congestion on the main line of the expressway.

[0003] However, the prior art lacks a system for linkage control between vehicles exiting the expressway and the signal lights at the intersection where the ramp lands.

[0004] Therefore, how to effectively reduce the probability of traffic on the expressway landing ramp encountering red lights at the ground intersection, improve traffic efficiency and driving experience, and at the same time alleviate the congestion level of the ramp back blocking the main line has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] In view of the above-mentioned defects of the prior art, the present invention provides a ramp continuous passage speed control system based on vehicle-road collaboration, which aims to effectively reduce the probability of traffic on the expressway ramp encountering red lights at the ground intersection, improve traffic efficiency and driving experience, and alleviate the congestion level of the ramp back blocking the main line.

[0006] To achieve the above-mentioned purpose, the present invention discloses a ramp landing continuous passing speed control system based on vehicle-road collaboration, including a system main control, a vehicle terminal, a speed control system, a number of roadside equipment, a signal control center server, and a traffic management center;

[0007] The system master is connected to all the vehicle terminals, the speed control system, and the traffic management center;

[0008] Each of the vehicle-mounted terminals is used to collect the driving data of the corresponding vehicle in real time, and send the collected driving data to the system master control, and then send it to the traffic management center through the system master control;

[0009] Each of the roadside devices is installed on the road where vehicles travel, and its main function is to collect current vehicle travel data and transmit the information to the traffic management center for processing through the communication network. The traffic management center determines the relevant information and transmits it to the system master control with the corresponding information request through the network;

[0010] The signal control center server is connected to all the traffic lights on the road, receives the green light time of all the traffic lights in real time, converts it into green light information and transmits it to the traffic management center;

[0011] The traffic management center analyzes the received green light information of all the signal lights and the vehicle driving data, synchronizes the green light information to the system main control of the vehicle, and provides real-time road condition information and driving assistance services for the corresponding vehicle;

[0012] The speed control system is connected to the system main control, receives commands from the system main control, and adaptively adjusts the speed to ensure passage within the green light time at the landing ramp intersection.

[0013] Preferably, the driving data includes position data, speed data and direction data corresponding to the vehicle.

[0014] More preferably, the system master controls the driving route according to the starting and ending points, determines the main line exit of the expressway and the corresponding ground intersection, and prompts the corresponding vehicle whether to enter the speed control system;

[0015] When any of the vehicles is determined to enter the speed control system, the speed control system adapts itself to the design speed of the road where it is located, so that the corresponding vehicle can pass through the ground intersection smoothly when the light turns green;

[0016] When any of the vehicles enters the speed control system, the driving speed of the corresponding vehicle is controlled by the speed control system, and the steering wheel is still controlled by the driver;

[0017] When the corresponding vehicle leaves the ground intersection, exiting the speed control system;

[0018] If any of the vehicles does not enter the speed control system during driving, the speed control system will automatically plan the driving route in the background and calculate the corresponding green light information of the ground intersection in real time until the corresponding vehicle actively turns on the speed control system.

[0019] More preferably, the driving speed of any of the vehicles on the main line of the expressway and the driving speed on the ramp are both within the allowable speed change range of the design speed of the road.

[0020] Preferably, each of the vehicle-mounted terminals acquires the navigation information in the CAN bus of the corresponding vehicle in real time, determines the target driving direction of the corresponding vehicle, and determines the target candidate lane according to the target driving direction, and then determines the number of leading vehicles on all the target candidate lanes, and selects the target candidate lane with the least number of existing vehicles as the target lane;

[0021] Alternatively, the target lane is selected according to the lengths of waiting vehicles on all the target candidate lanes.

[0022] More preferably, the target lane is determined by acquiring the front vehicle data information and the remaining passing time of the signal lights of all the target candidate lanes;

[0023] The front vehicle data information is used to determine whether the corresponding front vehicle can pass through the intersection, including the number of the front vehicles, the speed of the front vehicle, and the distance between the front vehicle and the stop line.

[0024] More preferably, the method for predicting whether any of the preceding vehicles can pass through the intersection and outputting a recommended speed is: using the acquired number of all preceding vehicles, the speeds of all preceding vehicles, the remaining passing time, and the distances of all preceding vehicles from the stop line as input values ​​of the model for calculation.

[0025] More preferably, the model is obtained by integrating LSTM and SVM, and the number of all the preceding vehicles, the speeds of all the preceding vehicles, the remaining travel time, and the distances of all the preceding vehicles from the stop line are input into the LSTM for prediction to obtain the passing probability of the corresponding vehicle;

[0026] After the LSTM outputs the passing probability of the corresponding vehicle, the passing probability of the corresponding vehicle is used as the input value of the SVM. The passing probability of the corresponding vehicle is classified by the support vector machine to determine the most appropriate passing probability, and the passing speed recommendation is determined by the most appropriate passing probability.

[0027] More preferably, the LSTM includes three thresholds, specifically: input gate i t 、Forget gate t and output gate o t ;

[0028] Input Gate i t Used to control the impact of the current input on the unit state;

[0029] Forget Gate t Determine how much of the state of the previous time step is retained;

[0030] Output gate o t Control the current unit output state, where t represents the time point;

[0031] The input gate i t =σ(W i ·[h t-1 ,x t ]+b i );

[0032] C~ t =tanh(W C ·[h t-1 ,x t ]+bC );

[0033] The forget gate f t =σ(W f ·[h t-1 ,x t ]+b f );

[0034] The output gate o t =σ(W o ·[h t-1 ,x t ]+b o );

[0035] Cell state equation at time t: C t =f t ·C t-1 +i t ·C~ t , where C t represents the cell state of the LSTM at time t, representing the model memory;

[0036] Among them, h t =o t tanh(C t ).

[0037] σ: represents the activation of the sigmoid function;

[0038] x t : Input data of the current time step;

[0039] h t-1 : The hidden state of the previous time step, carrying the previous time information;

[0040] c t-1 : The cell state of the previous time step (Cell State);

[0041] C t : cell state at the current time step;

[0042] C~ t : Candidate cell state, calculated by tanh function;

[0043] W: weight;

[0044] b: is the bias value;

[0045] h t : represents the output of the hidden state.

[0046] Beneficial effects of the present invention:

[0047] The present invention realizes a ramp continuous passage speed control system based on vehicle-road collaboration. After determining the driving route, the vehicle speed is controlled after calculation in combination with the green light time at the intersection of the ramp, and the vehicle passes through the intersection during the green light period at the ground intersection, avoiding the unpleasant experience of frequently waiting for red lights at the intersection.

[0048] The present invention solves the problem of vehicles frequently waiting for red lights on landing ramps, gives full play to the design function of continuous passage of vehicles with green lights on the ramps, reduces the queue length at the intersection entrance, and effectively reduces the possibility of ramp queues blocking the main line in extreme cases.

[0049] The concept, specific structure and technical effects of the present invention will be further described below in conjunction with the accompanying drawings to fully understand the purpose, characteristics and effects of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic structural diagram of an embodiment of the present invention is shown.

[0051] Figure 2 A schematic diagram of the working process of a green light continuous passage speed control system in one embodiment of the present invention is shown.

[0052] Figure 3 A schematic diagram showing the green light continuous passing speed principle of a speed control system in one embodiment of the present invention is shown.

[0053] Figure 4 A flow chart of the prediction of the probability of passage based on green light information in one embodiment of the present invention is shown.

[0054] Figure 5 A flow chart of intersection traffic decision-making based on green light information in one embodiment of the present invention is shown. DETAILED DESCRIPTION

[0055] Example

[0056] like Figure 1 As shown, the ramp landing continuous passing speed control system based on vehicle-road collaboration includes system main control, vehicle-mounted terminal, speed control system, several roadside equipment, signal control center server, and traffic management center;

[0057] The system master is connected to all vehicle terminals, speed control systems, and traffic management centers;

[0058] Each vehicle terminal is used to collect the driving data of the corresponding vehicle in real time, and send the collected driving data to the system master control, and then send it to the traffic management center through the system master control;

[0059] Each roadside device is installed on the road where vehicles travel. Its main function is to collect current vehicle driving data and transmit the information to the traffic management center through the communication network for processing. The traffic management center determines the relevant information and transmits it to the system master control with corresponding information request through the network;

[0060] The signal control center server is connected to all traffic lights on the road, receives the green light time of all traffic lights in real time, converts it into green light information and transmits it to the traffic management center;

[0061] The traffic management center analyzes the green light information of all traffic lights and vehicle driving data received, synchronizes the green light information to the vehicle's system master control, and provides real-time road condition information and driving assistance services for the corresponding vehicles;

[0062] The speed control system is connected to the system master control, receives commands from the system master control, and adaptively adjusts the speed to ensure passage within the green light time at the landing ramp intersection.

[0063] The present invention utilizes the coordinated positioning of the vehicle-mounted terminal and the roadside equipment, which significantly improves the accuracy and real-time performance of information such as the vehicle position and driving speed.

[0064] In certain embodiments, the driving data includes position data, speed data, and direction data of the corresponding vehicle.

[0065] like Figure 2 As shown, the system master controls the route according to the starting and ending points, determines the main line exit of the expressway and the corresponding ground intersection, and prompts the corresponding vehicle whether to enter the speed control system;

[0066] When any vehicle enters the speed control system, the speed control system will adapt to the design speed of the road where it is located, so that the corresponding vehicle can pass through the ground intersection smoothly when the light turns green;

[0067] When any vehicle enters the speed control system, the speed of the corresponding vehicle is controlled by the speed control system, and the steering wheel is still controlled by the driver;

[0068] When the corresponding vehicle leaves the ground intersection, exit the speed control system;

[0069] If any vehicle does not enter the speed control system during driving, the speed control system will automatically plan the driving route in the background and calculate the corresponding green light information at the ground intersection in real time until the corresponding vehicle actively turns on the speed control system.

[0070] like Figure 3 As shown, in some embodiments, when the driving speed of any vehicle on the main line of the expressway and the driving speed on the ramp are both within the allowable speed range of the design speed of the road.

[0071] The present invention enables the vehicle to smoothly pass through the ground intersection when the light is green through reasonable vehicle speed control.

[0072] In some embodiments, each vehicle-mounted terminal acquires the navigation information in the CAN bus of the corresponding vehicle in real time, determines the target driving direction of the corresponding vehicle, and determines the target candidate lane according to the target driving direction, and then determines the number of leading vehicles on all target candidate lanes, and selects the target candidate lane with the least number of existing vehicles as the target lane;

[0073] Alternatively, the target lane is selected based on the length of waiting vehicles on all target candidate lanes.

[0074] In some embodiments, the target lane is determined by acquiring the front vehicle data information of all target candidate lanes and the remaining passing time of the signal lights;

[0075] The data information of the vehicle in front is used to determine whether the corresponding vehicle in front can pass through the intersection, including the number of vehicles in front, the speed of the vehicle in front, and the distance between the vehicle in front and the stop line.

[0076] In some embodiments, a method for predicting whether any preceding vehicle can pass through an intersection and outputting a recommended speed is to calculate the number of all preceding vehicles, the speeds of all preceding vehicles, the remaining travel time, and the distance of all preceding vehicles from the stop line as input values ​​of the model.

[0077] In some embodiments, the model is obtained by fusion of LSTM and SVM, and the number of all leading vehicles, the speed of all leading vehicles, the remaining passing time, and the distance of all leading vehicles from the stop line are input into LSTM for prediction to obtain the passing probability of the corresponding vehicle;

[0078] After LSTM outputs the passing probability of the corresponding vehicle, the passing probability of the corresponding vehicle is used as the input value of SVM. The passing probability of the corresponding vehicle is classified by the support vector machine to determine the most appropriate passing probability, and the passing speed recommendation is determined by the most appropriate passing probability.

[0079] In some embodiments, LSTM includes three thresholds, specifically: input gate i t 、Forget gate t and output gate o t ;

[0080] Wherein, t represents the time;

[0081] Input Gate i t =σ(W i ·[h t-1 ,x t ]+b i );

[0082] C~ t =tanh(W C ·[h t-1 ,x t ]+b C );

[0083] Forget Gate t =σ(W f ·[h t-1 ,x t ]+b f );

[0084] Output gate o t =σ(W o ·[h t-1 ,x t ]+b o );

[0085] Cell state equation at time t: C t =f t ·C t-1 +i t ·C~ t , where C t Represents the cell state of LSTM at time t;

[0086] Among them, h t =o t tanh(C t ).

[0087] σ: represents the activation of the sigmoid function;

[0088] x t : Input data of the current time step;

[0089] h t-1 : The hidden state of the previous time step, carrying the previous time information;

[0090] c t-1 : The cell state of the previous time step (Cell State);

[0091] C t : cell state at the current time step;

[0092] C~ t : Candidate cell state, calculated by tanh function;

[0093] W: weight;

[0094] b: is the bias value;

[0095] h t : represents the output of the hidden state.

[0096] like Figure 4 As shown, the present invention can use the number of leading vehicles, vehicle speed, remaining communication time, and distance to the stop line as input values ​​at each moment in LSTM when making predictions, and calculate the input value at the current moment with the output value of the previous Cell based on the three thresholds of LSTM to obtain a prediction result and output the vehicle passing probability. It can be seen that the greater the passing probability, the more likely the vehicle is to pass the current intersection within the current green light time. Therefore, when the green light time is about to end, several vehicles behind the stop line may not be able to pass the intersection, so it is necessary to classify and select this situation.

[0097] When any vehicle cannot pass the current intersection within the current green light time, because the vehicle in front is in a parking state or a coasting state, in order to avoid the parking waiting time of the vehicle behind, the speed can be adjusted. Figure 5 The described passing speed suggestion method corrects the speed.

[0098] like Figure 5 As shown, the vehicle determines whether it can pass through the ground intersection within the current green light time. If it can pass through the ground intersection within the current traffic light time, the speed range can be calculated according to the remaining travel time, and the speed range is constrained according to the speed limit to obtain the target speed range; if it cannot pass through the ground intersection within the current green light time, the start time and end time of the next green light are obtained, and the passable time is determined according to the number of vehicles ahead in the target lane. At the same time, the passable speed range is determined according to the passable time, and the speed range is constrained according to the speed limit; after determining the target speed range, the vehicle can pass through the ground intersection according to the speed in the target speed range.

[0099] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A ramp landing continuous passing speed control system based on vehicle-road collaboration; it is characterized by: Including system master control, vehicle terminal, speed control system, several roadside equipment, signal control center server, and traffic management center; The system master is connected to all the vehicle-mounted terminals, the speed control system, and the traffic management center; Each of the vehicle-mounted terminals is used to collect the driving data of the corresponding vehicle in real time, and send the collected driving data to the system master control, and then send it to the traffic management center through the system master control; Each of the roadside devices is installed on the road where vehicles travel, and its main function is to collect current vehicle travel data and transmit the information to the traffic management center for processing through the communication network. The traffic management center determines the relevant information and transmits it to the system master control with the corresponding information request through the network; The signal control center server is connected to all the traffic lights on the road, receives the green light time of all the traffic lights in real time, converts it into green light information and transmits it to the traffic management center; The traffic management center analyzes the received green light information of all the signal lights and the vehicle driving data, synchronizes the green light information to the system main control of the vehicle, and provides real-time road condition information and driving assistance services for the corresponding vehicle; The speed control system is connected to the system main control, receives commands from the system main control, and adaptively adjusts the speed to ensure passage within the green light time at the landing ramp intersection.

2. The ramp landing continuous passing speed control system based on vehicle-road collaboration according to claim 1 is characterized in that: The driving data includes position data, speed data and direction data corresponding to the vehicle.

3. The ramp landing continuous passing speed control system based on vehicle-road collaboration according to claim 2 is characterized in that: The system master controls the driving route according to the starting and ending points, determines the main line exit of the expressway and the corresponding ground intersection, and prompts the corresponding vehicle whether to enter the speed control system; When any of the vehicles is determined to enter the speed control system, the speed control system adapts itself to the design speed of the road where it is located, so that the corresponding vehicle can pass through the ground intersection smoothly when the light turns green; When any of the vehicles enters the speed control system, the driving speed of the corresponding vehicle is controlled by the speed control system, and the steering wheel is still controlled by the driver; When the corresponding vehicle leaves the ground intersection, exiting the speed control system; If any of the vehicles does not enter the speed control system during driving, the speed control system will automatically plan the driving route in the background and calculate the corresponding green light information of the ground intersection in real time until the corresponding vehicle actively turns on the speed control system.

4. The ramp landing continuous passing speed control system based on vehicle-road collaboration according to claim 2 is characterized in that: When the driving speed of any of the vehicles on the main line of the expressway and the driving speed on the ramp are both within the allowable speed change range of the design speed of the road.

5. The ramp landing continuous passing speed control system based on vehicle-road collaboration according to claim 1 is characterized in that: When any of the vehicles enters the speed control system, the driving speed of the corresponding vehicle is controlled by the speed control system, and the steering wheel is still controlled by the driver; When the corresponding vehicle leaves the ground intersection, the speed control system is exited.

6. The ramp landing continuous passing speed control system based on vehicle-road collaboration according to claim 1 is characterized in that: Each of the vehicle-mounted terminals acquires the navigation information in the CAN bus of the corresponding vehicle in real time, determines the target driving direction of the corresponding vehicle, and determines the target candidate lane according to the target driving direction, and then determines the number of leading vehicles on all the target candidate lanes, and selects the target candidate lane with the least number of existing vehicles as the target lane; Alternatively, the target lane is selected according to the lengths of waiting vehicles on all the target candidate lanes.

7. The ramp landing continuous passing speed control system based on vehicle-road collaboration according to claim 6 is characterized in that: Determine the target lane by acquiring the front vehicle data information and the remaining travel time of the signal lights of all the target candidate lanes; The front vehicle data information is used to determine whether the corresponding front vehicle can pass through the intersection, including the number of the front vehicles, the speed of the front vehicle, and the distance between the front vehicle and the stop line.

8. The ramp landing continuous passing speed control system based on vehicle-road collaboration according to claim 7 is characterized in that: The method for predicting whether any of the preceding vehicles can pass through the intersection and outputting a recommended speed is as follows: the number of all preceding vehicles, the speeds of all preceding vehicles, the remaining travel time, and the distances of all preceding vehicles from the stop line are calculated as input values ​​of the model.

9. The ramp landing continuous passing speed control system based on vehicle-road collaboration according to claim 8 is characterized in that: The model is obtained by integrating LSTM and SVM. The number of all the preceding vehicles, the speed of all the preceding vehicles, the remaining travel time, and the distance of all the preceding vehicles from the stop line are input into the LSTM for prediction to obtain the passing probability of the corresponding vehicle. After the LSTM outputs the passing probability of the corresponding vehicle, the passing probability of the corresponding vehicle is used as the input value of the SVM. The passing probability of the corresponding vehicle is classified by the support vector machine to determine the most appropriate passing probability, and the passing speed recommendation is determined by the most appropriate passing probability.

10. The ramp landing continuous passing speed control system based on vehicle-road collaboration according to claim 9 is characterized in that: The LSTM includes three thresholds: input gate i t 、Forget gate t and output gate o t ; Wherein, t represents the time; Input Gate i t =σ(W i ·[h t-1 ,x t ]+b i ); Forget Gate t =σ(W f ·[h t-1 ,x t ]+b f ); Output gate o t =σ(W o ·[h t-1 ,x t ]+b o ); The cell state equation at time t: Among them, C t Represents the cell state of LSTM at time t; Among them, h t =o t tanh(C t ). σ: represents the activation of the sigmoid function; x t : Input data of the current time step; h t-1 : The hidden state of the previous time step, carrying the previous time information; c t-1 : The cell state of the previous time step (Cell State); C t : The cell state at the current time step; Candidate cell states are calculated using the tanh function; W: weight; b: is the bias value; h t : represents the output of the hidden state.

Images