A vehicle trajectory reconstruction method adapted to mixed traffic flow and multiple scenarios

Abstract

The present invention discloses a vehicle trajectory reconstruction method that is adaptable to multiple scenarios of mixed traffic flows, and the steps are as follows: S1. Collect information such as the position and speed of surrounding manually driven vehicles. S2. Divide the reconstructed scenarios into full-perception scenarios, semi-perception scenarios, and conventional traffic flow scenarios according to the types of adjacent floating vehicles, and generate research scenario data considering the penetration rate of floating vehicles. S3. Generate time series using sliding window technology. S4. In conventional traffic flow scenarios, use the intelligent driver model IDM to reconstruct vehicles at different floating vehicle penetration rates. S5. In semi-perception scenarios, use the fusion model IDM-LSTM to reconstruct vehicle trajectories with fragmented observations, and use the IDM model to reconstruct trajectories of vehicles with a large amount of missing trajectory information. S6. In full-perception scenarios, it is possible to obtain fragmented observation trajectories of all vehicles, introduce a weight module to fuse the IDM model with the long short-term memory neural network, and reconstruct the missing vehicle trajectories.

Description

Technical Field

[0001] The present invention belongs to the field of traffic perception and big data analysis, and specifically relates to a vehicle trajectory reconstruction method adapted to multiple scenarios of mixed traffic flows. Background Art

[0002] Vehicle trajectories contain rich spatiotemporal information about traffic flows and are widely used in driving pattern recognition, traffic safety, traffic state estimation, traffic flow modeling, signal optimization and control, and traffic energy consumption estimation. Obtaining complete vehicle trajectories is crucial for accurately describing traffic flow states and enabling these applications. However, raw data often contains a large number of missing segments, which poses a challenge to integrating them into traffic flow models.

[0003] Currently, a large number of detection devices are installed to monitor traffic conditions. These devices are mainly divided into fixed detectors and mobile detectors. Research shows that by 2050, the proportion of connected and autonomous vehicles will exceed 20%, indicating that future mixed traffic flows will be composed of human-driven vehicles, connected vehicles, and autonomous vehicles. In mixed traffic flows, autonomous and connected vehicles can collect complete vehicle trajectory information, overcoming the limitation of fixed detectors that can only obtain single-point traffic information. Based on these advantages, autonomous and connected vehicles have promoted the development of applications such as vehicle following behavior simulation, basic map construction, and overtaking behavior. However, due to the low penetration rate of autonomous and connected vehicles, they can only provide fragmented observations rather than complete traffic trajectory information. The limited availability of observation data limits the improvement of trajectory reconstruction model accuracy.

[0004] The above analysis demonstrates that reconstructing vehicle trajectories in mixed traffic flows is far from easy. Key challenges include: 1) Fixed detectors can only provide traffic status information at specific locations, while the low penetration rate of autonomous vehicles means that the trajectories of most human-driven vehicles remain undetected; 2) The data formats obtained by fixed and mobile detectors are inconsistent, and fusing these two types of data to reconstruct irregular trajectories requires careful consideration of these differences.

[0005] Current trajectory reconstruction methods are primarily categorized as data-driven and traffic flow theory-based. Data-driven methods focus on inferring the spatiotemporal distribution of trajectory points based on the characteristics of trajectory data. Machine learning-based methods are common and excel in short-term trajectory prediction, but their prediction error tends to increase as the length of the trajectory segment to be reconstructed increases. Traffic flow theory-based methods offer better interpretability of driving behavior, but the reconstruction accuracy is not as high as that of data-driven methods. Summary of the Invention

[0006] In response to the problems existing in the prior art, the present invention provides a vehicle trajectory reconstruction method that is adaptable to multiple scenarios of mixed traffic flows. In a mixed traffic flow environment, the present invention takes highways as the research object, and collects information such as the trajectory position, speed, and passing time of surrounding manually driven vehicles through fixed roadside detectors and autonomous driving vehicles; the research scenarios are divided into full perception scenarios, semi-perception scenarios, and conventional traffic flow scenarios; different trajectory reconstruction methods are used for different trajectory reconstruction scenarios, so that the reconstructed vehicle trajectory is more accurate.

[0007] To solve the above technical problems, the present invention provides the following technical solution: a vehicle trajectory reconstruction method adapted to multiple scenarios of mixed traffic flow, comprising the following steps:

[0008] S1. Collect the trajectory position, speed and passing time information of surrounding manually driven vehicles;

[0009] S2. Divide the target scene into three scenarios based on the type of adjacent floating vehicles: full perception scenario, semi-perception scenario, and regular traffic flow scenario. Consider the penetration rate of floating vehicles and generate trajectory data for the three scenarios.

[0010] S3. Use a sliding window approach to divide vehicle trajectories and divide the dataset into training, validation, and test sets according to specific proportions.

[0011] S4. Under normal traffic flow scenarios, obtain the trajectory data of the floating vehicle itself and reconstruct the vehicle using the intelligent driver model under different floating vehicle penetration rates;

[0012] S5. In the semi-perception scenario, the vehicle with a fragmented trajectory is reconstructed using the fusion model IDM-LSTM. The vehicle with missing trajectory information is reconstructed using the intelligent driver model.

[0013] S6. In the full perception scenario, obtain the fragmented trajectory information of all vehicles, introduce a weight module to fuse the intelligent driver model with the long short-term memory neural network, namely IDM-LSTM, to reconstruct the missing vehicle trajectories.

[0014] Furthermore, in the aforementioned step S1, a vehicle passing through the target road section is detected by the fixed detector at the starting point of the road side and numbered as i, and the time when vehicle i passes the fixed detector position at the starting point is recorded as b i , the time it takes for vehicle i to pass the end of the study section is e i , retrieve the vehicle trajectory according to the vehicle number, and obtain the vehicle trajectory observation set Tra of vehicle i on the target road section i ={s(i,t),v(i,t),a(i,t),l(i,t),t}t∈[b i ,e i ],

[0015] The trajectory set of all vehicles Tra={Tra1,…,Tra k ,…,Tra n}, where s(i,t) is the longitudinal distance traveled by vehicle i on the target section at time t, v(i,t) is the speed of vehicle i on the study section at time t, a(i,t) is the acceleration of vehicle i on the study section at time t, and l(i,t) is the lane number of vehicle i on the study section at time t.

[0016] Furthermore, in the aforementioned step S2, the target scene is divided into a full-perception scene, a semi-perception scene, and a regular traffic flow scene according to the types of adjacent floating vehicles. Specifically, the types of the two adjacent floating vehicles are determined in the target scene. If both of the two adjacent floating vehicles are autonomous vehicles, the target scene is named a full-perception scene; if one is an autonomous vehicle and the other is a manually driven vehicle that can only obtain its own vehicle driving status information, the target scene is named a semi-perception scene; if both of the two adjacent floating vehicles are manually driven vehicles, the target scene is named a regular traffic flow scene.

[0017] Furthermore, in the aforementioned step S2, the penetration rate of floating vehicles is considered and trajectory data for three scenarios is generated, as follows:

[0018] Based on the fact that the floating cars are evenly distributed, the interval d between the floating cars ij As follows:

[0019] d ij =100*p r (1)

[0020] Where p r is the penetration rate of autonomous vehicles, d ij Represents the interval between floating cars i and j, and introduces a random factor u to consider the non-uniform distribution between floating cars.

[0021]

[0022] Where p i Is a probability generated by a random program. If this probability is less than the random factor, the current vehicle is set as a floating vehicle. i =1, otherwise it is not a floating car f i =0.

[0023] Furthermore, the aforementioned step S3 includes the following sub-steps:

[0024] S3.1. Use the sliding window method to divide the vehicle trajectory, and select the history sequence length as l h , the reconstruction length is lp , then the time segments of the historical sequence Tra(h,i) and the reconstructed sequence Tra(p,i) of the i-th sample are as follows:

[0025] Tra(h,i)∈[t start ,t start +l h ] (3)

[0026] Tra(p,i)∈[t start +l h +1,t start +l h +l p ] (4)

[0027] The vehicle's position, speed, acceleration, lane, and other information are all within this time range, and the time series data All_Tra expression is obtained as follows:

[0028] All_Tra={Tra(h,1),Tra(p,1),…,Tra(h,k),Tra(p,k),…,Tra(h,n),Tra(p,n)} (5)

[0029] Where, t start is the start time of each sample;

[0030] S3.2. According to the stratified sampling principle, the time series data is divided into training set, validation set and test set according to the preset ratio, where Train_set, Val_set and Test_set represent the training set, validation set and test set respectively:

[0031] Train_set=m1*All_Tra (6)

[0032] Val_set=m2*All_Tra (7)

[0033] Test_set=m3*All_Tra (8)

[0034] Tra is the total number of vehicle trajectory samples, m1, m2, and m3 are the corresponding scaling coefficients.

[0035] Furthermore, the aforementioned step S4 includes the following steps:

[0036] S4.1. In the intelligent driver model, the leading vehicle and following vehicle of vehicle i are determined based on lane information, position information, and time information, as follows:

[0037]

[0038] Where is_front indicates whether vehicle j is the leading vehicle in front of vehicle i, and is_back indicates whether vehicle j is the following vehicle of vehicle i. A value of 1 indicates that vehicle j is the leading vehicle or the following vehicle, and a value of 0 indicates that vehicle j is not the leading vehicle or the following vehicle. S4.2. Use the intelligent driver model to estimate the missing vehicle trajectory information. The intelligent driver model (IDM) model reconstructs the other missing vehicle trajectory segments based on the observation segments of the leading vehicle. The intelligent driver model (IDM) is as follows:

[0039]

[0040] Δv′(i,t)=v′(i,t)-v′(i-1,t) (14)

[0041] d′(i,t)=s′(i-1,t)-s′(i,t)-L i-1 (15)

[0042] Where s * (v′(i,t),Δv′(i,t)) represents the expected distance, d′(i,t) represents the headway between the front and rear vehicles, Δv′(i,t) represents the speed difference between the front and rear vehicles, and a max , b represent the maximum acceleration and comfortable deceleration respectively, T safe is the safe headway, s0 is the headway distance at rest, v0 is the expected speed, L i-1 Indicates the vehicle length of the preceding vehicle;

[0043] S4.3. Adjust the reconstructed vehicle trajectory to ensure that the reconstructed vehicle trajectory is between the previous segment and the next segment, as shown in the following formula:

[0044] v′(i,t)=max(v′(i,t-1)+a′(i,t)Δt,0) (16)

[0045]

[0046] Furthermore, the aforementioned step S5 includes the following sub-steps:

[0047] S5.1. In the semi-perception scenario, some human-driven vehicle trajectories are reconstructed using the fusion model IDM-LSTM. Other vehicle trajectories are reconstructed using steps S4.1 to S4.3. Existing data is classified. If the historical sequence is missing, the intelligent driver model IDM is used for reconstruction. If the historical sequence data is complete, the fusion model IDM-LSTM is used for reconstruction.

[0048] S5.2. The fusion model IDM-LSTM is used for reconstruction. The LSTM model includes an input gate, a forget gate, and an output gate. By circulating trajectory information between different gate structures, the influence of the historical sequence on the reconstructed sequence is considered. The specific expressions are shown in Equations (18) to (23):

[0049] f t =σ(W f ·[h t-1 ,x t ]+b f ) (18)

[0050] i t =σ(W i ·[h t-1 ,x t ]+b i ) (19)

[0051]

[0052] o t =σ(W o [h t-1 ,x t ]+b o ) (twenty two)

[0053] h t =o t *tanh(C t ) (twenty three)

[0054] where f t is the output of the forget gate, i t is the output of the input gate, is a candidate cell state, C t is the unit state at the current moment, h t is the hidden state at the current moment, x t Represents the input data; W f , W i , W C , W o Respectively represent the weight matrix of the forget gate, the weight matrix of the input gate, the weight matrix of the hidden state update, and the weight matrix of the output gate; b f , b i , b C , b o Respectively represent the bias vector of the forget gate, the bias vector of the input gate, the bias vector of the hidden state update, and the bias vector of the output gate;

[0055] S5.3 adopts the method of fusion model IDM-LSTM to achieve the fusion of the two models through the weight module. The weight module is shown in expressions (24)-(25). By fusing the reconstruction results of the IDM model and the reconstruction results of the LSTM model, the prediction results of the IDM-LSTM model are obtained. The prediction results are used to calculate the loss of the LSTM model and to update the parameters in the training process, thereby enhancing the training process of the LSTM model.

[0056]

[0057] w IDM,i +w LSTM,i =1 (25)

[0058] Among them, s LSTM,i represents the reconstruction result of vehicle i by the LSTM model, s IDM,i represents the result of reconstruction of the intelligent driver model IDM, w IDM,i ,w LSTM,i They represent the weight coefficients of the intelligent driver model IDM and LSTM model, respectively, and represent the credibility of different models. IDM,i ,w LSTM,i The sum of is 1;

[0059] S5.4. The model error is evaluated using three evaluation indicators: MAE, RMSE and MAPE, as shown in the following formula:

[0060]

[0061] Furthermore, the aforementioned step S6 includes the following sub-steps:

[0062] S6.1. In the full perception scenario, first reconstruct the missing vehicle trajectory using the intelligent driver model (IDM), complete the vehicle trajectory reconstruction based on the car-following rule, and execute steps S4.1 to S4.3.

[0063] S6.2, the intelligent driver model IDM, the reconstruction result is used as input to the LSTM model to assist the LSTM model training process, and then execute step S5.3;

[0064] S6.3. Use the fusion model IDM-LSTM method to achieve the fusion of the two models through the weight module, and execute step S5.4 to reconstruct the vehicle trajectory in the full perception scenario.

[0065] Compared with the existing technology, the beneficial technical effects of the above technical solutions adopted in the present invention are as follows: Based on the mixed traffic flow environment, the present invention divides the trajectory reconstruction scenarios into three types: full perception scenarios, semi-perception scenarios and conventional traffic flow scenarios, and proposes a weighted module for combining the intelligent driver model and the long short-term memory network model, namely IDM-LSTM. In the conventional traffic flow scenario, the IDM model is used to reconstruct the vehicle trajectory; in the semi-perception scenario, the IDM model and the fusion model are used to reconstruct the vehicle trajectory respectively; in the full perception scenario, the fusion model is used to reconstruct the vehicle trajectory. The present invention proposes a vehicle trajectory reconstruction method suitable for multi-scenario mixed traffic flow. This method can accurately grasp the traffic flow status, which is of great significance for ensuring the smooth operation of highways and monitoring vehicle exhaust emissions. At the same time, this method also has significant academic value and application potential in refining traffic status evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a multi-scenario diagram of mixed traffic flow; in the figure, (a) is a schematic diagram of a conventional traffic flow scenario, (b) is a schematic diagram of a semi-perception scenario, and (c) is a schematic diagram of a full-perception scenario.

[0067] Figure 2 This is a schematic diagram of the weight module.

[0068] Figure 3 It is a temporal and spatial distribution diagram of real vehicle trajectories under the embodiment.

[0069] Figure 4 It is the vehicle trajectory reconstruction result diagram; in the figure, (a) is the vehicle trajectory reconstruction result diagram based on the intelligent driver model IDM, (b) is the vehicle trajectory reconstruction result diagram based on the LSTM model, and (c) is the vehicle trajectory reconstruction result diagram based on the IDM-LSTM fusion model.

[0070] Figure 5 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0071] In order to better understand the technical content of the present invention, specific embodiments are given and described below with reference to the accompanying drawings.

[0072] Various aspects of the present invention are described herein with reference to the accompanying drawings, which show a number of illustrative embodiments. The embodiments of the present invention are not limited to those described in the accompanying drawings. It should be understood that the present invention can be implemented by any of the various concepts and embodiments described above, as well as the concepts and implementations described in detail below, because the concepts and embodiments disclosed herein are not limited to any particular implementation. In addition, some aspects disclosed herein may be used alone or in any appropriate combination with other aspects disclosed herein.

[0073] refer to Figure 5 The present invention provides a vehicle trajectory reconstruction method adapted to multiple scenarios of mixed traffic flows, comprising the following steps:

[0074] S1. Collect the trajectory position, speed and passing time information of surrounding manually driven vehicles;

[0075] S2. Divide the target scene into three scenarios based on the type of adjacent floating vehicles: full perception scenario, semi-perception scenario, and regular traffic flow scenario. Consider the penetration rate of floating vehicles and generate trajectory data for the three scenarios.

[0076] S3. Use a sliding window approach to divide vehicle trajectories and divide the dataset into training, validation, and test sets according to specific proportions.

[0077] S4. Under normal traffic flow scenarios, obtain the trajectory data of the floating vehicle itself and reconstruct the vehicle using the intelligent driver model under different floating vehicle penetration rates;

[0078] S5. In the semi-perception scenario, the vehicle with a fragmented trajectory is reconstructed using the fusion model IDM-LSTM. The vehicle with missing trajectory information is reconstructed using the intelligent driver model.

[0079] S6. In the full perception scenario, obtain the fragmented trajectory information of all vehicles, introduce a weight module to fuse the intelligent driver model with the long short-term memory neural network, namely IDM-LSTM, to reconstruct the missing vehicle trajectories.

[0080] like Figure 1 Figure 1 shows the three trajectory reconstruction scenarios studied in this paper. (a) is a schematic diagram of a conventional traffic flow scenario, (b) is a schematic diagram of a semi-perception scenario, and (c) is a schematic diagram of a fully-perception scenario. These scenario divisions serve as the basis for subsequently reconstructing vehicle trajectories using different trajectory reconstruction methods. Figure 2 The figure shows the model fusion module proposed in this paper. It combines the IDM model and the LSTM model through weighting. The combined model has better trajectory reconstruction effect than either model alone. By selecting appropriate trajectory reconstruction methods for different scenarios, the method proposed in this paper can significantly reduce the error of trajectory reconstruction.

[0081] Furthermore, as a preferred embodiment of the present invention, in step S1, a vehicle passing through the study section is detected by a fixed detector at the starting point of the road side and numbered as i, and the time when vehicle i passes the fixed detector position at the starting point is recorded as b i , the time it takes for vehicle i to pass the end of the study section is e i , retrieve the vehicle trajectory according to the vehicle number and obtain the vehicle trajectory observation set of vehicle i on the research section:

[0082] Tra i ={s(i,t),v(i,t),a(i,t),l(i,t),t}t∈[b i ,e i ],

[0083] The trajectory set of all vehicles Tra={Tra1,…,Tra k ,…,Tra n}, where s(i,t) is the longitudinal distance traveled by vehicle i on the study section at time t, v(i,t) is the speed of vehicle i on the study section at time t, a(i,t) is the acceleration of vehicle i on the study section at time t, and l(i,t) is the lane number of vehicle i on the study section at time t.

[0084] Furthermore, as a preferred embodiment of the present invention, the target scene is divided into a full perception scene, a semi-perception scene, and a regular traffic flow scene according to the type of adjacent floating vehicles. Specifically: (1) If the two adjacent floating vehicles are both autonomous vehicles that can perceive the vehicles in the surrounding environment, all vehicles in this scene can obtain fragmented vehicle trajectory information, which is named a full perception scene. (2) If one of the two adjacent floating vehicles is an autonomous vehicle and the other is a manually driven vehicle that can only obtain its own vehicle driving status information, then in the area between the two vehicles, only some vehicles can obtain sufficient fragmented vehicle trajectory information, and the trajectory information of the other vehicles is largely missing. This is named a semi-perception scene. (3) If the two adjacent floating vehicles are both manually driven vehicles, the trajectory information of other vehicles between the two floating vehicles is completely missing. In this scenario, trajectory reconstruction is more difficult, which is named a regular traffic flow scene.

[0085] Furthermore, as a preferred embodiment of the present invention, the original data obtained is the vehicle trajectory data of the full sample, so in order to simulate the data missing situation in the three trajectory reconstruction scenarios, it is necessary to generate trajectory data under the corresponding scenarios. In the present invention, the penetration rate of autonomous driving vehicles p r Set to 5%, 10% and 15%. Assuming that most of the floating cars are evenly distributed, the interval d between the floating cars ij As shown in expression (1). Taking into account the randomness, the random factor u is introduced to consider the non-uniform distribution between floating cars as shown in expression (2). Expressions (1) and (2) are parallel relationships, not inclusive relationships. Among them, d ij represents the interval between floating cars i and j, p i Is a probability generated by a random program. If this probability is less than the random factor, the current vehicle is set as a floating vehicle. i =1, otherwise it is not a floating car f i =0;

[0086] d ij =100*p r (1)

[0087]

[0088] Furthermore, as a preferred embodiment of the present invention, step S3 includes the following sub-steps:

[0089] S3.1. Use the sliding window method to divide the vehicle trajectory, and select the history sequence length as l h , the reconstruction length is l p , then the time segments of the historical sequence Tra(h,i) and the reconstructed sequence Tra(p,i) of the i-th sample are as follows:

[0090] Tra(h,i)∈[t start ,t start +l h ] (3)

[0091] Tra(p,i)∈[t start +l h +1,t start +l h +l p ] (4)

[0092] The vehicle's position, speed, acceleration, lane, and other information are all within this time range, and the time series data All_Tra expression is obtained as follows:

[0093] All_Tra={Tra(h,1),Tra(p,1),…,Tra(h,k),Tra(p,k),…,Tra(h,n),Tra(p,n)} (5)

[0094] Where, t start is the start time of each sample;

[0095] S3.2. According to the stratified sampling principle, the time series data is divided into training set, validation set and test set in a ratio of 7:1:2, where Train_set, Val_set and Test_set represent the training set, validation set and test set respectively:

[0096] Train_set=0.7*All_Tra (6)

[0097] Val_set=0.1*All_Tra (7)

[0098] Test_set=0.2*All_Tra (8)

[0099] Tra is all vehicle trajectory samples.

[0100] Furthermore, as a preferred embodiment of the present invention, step S4 includes the following sub-steps:

[0101] S4.1. In the intelligent driver model, the following relationship of vehicles affects the model's input and output. The leading vehicle and following vehicle of vehicle i are determined using lane information, position information, and time information, as shown in the following equation:

[0102]

[0103] Where is_front indicates whether vehicle j is the leading vehicle in front of vehicle i, and is_back indicates whether vehicle j is the following vehicle of vehicle i. A value of 1 indicates that vehicle j is the leading vehicle or the following vehicle, and a value of 0 indicates that vehicle j is not the leading vehicle or the following vehicle. S4.2. Since the trajectory information of all manually driven vehicles is missing in conventional traffic flow scenarios, only the vehicle trajectory information of the floating vehicle itself can be obtained. Therefore, an intelligent driver model is used to estimate the missing vehicle trajectory information. The intelligent driver model (IDM) reconstructs the other missing vehicle trajectory segments based on the observation segments of the leading vehicle. The intelligent driver model (IDM) is as follows:

[0104]

[0105] Δv′(i,t)=v′(i,t)-v′(i-1,t) (14)

[0106] d′(i,t)=s′(i-1,t)-s′(i,t)-L i-1 (15)

[0107] Through the intelligent driver model IDM, we can reconstruct the other missing vehicle trajectory segments based on the observation segments of the preceding vehicle. * (v′(i,t),Δv′(i,t)) represents the expected distance, d′(i,t) represents the headway between the front and rear vehicles, Δv′(i,t) represents the speed difference between the front and rear vehicles, and a max , b represent the maximum acceleration and comfortable deceleration respectively, T safe is the safe headway, s0 is the headway distance at rest, v0 is the expected speed, L i-1 Indicates the vehicle length of the preceding vehicle;

[0108] S4.3. The vehicle trajectory reconstructed using the intelligent driver model (IDM) may conflict with the trajectory of the next observed segment. Therefore, the reconstructed vehicle trajectory needs to be adjusted to ensure that the reconstructed vehicle trajectory is between the previous segment and the next segment, as shown in the following formula:

[0109] v′(i,t)=max(v′(i,t-1)+a′(i,t)Δt,0) (16)

[0110]

[0111] Furthermore, as a preferred embodiment of the present invention, step S5 includes the following sub-steps:

[0112] S5.1. In the semi-perception scenario, some human-driven vehicle trajectories are reconstructed using the fusion model IDM-LSTM. Other vehicle trajectories are reconstructed using steps S4.1 to S4.3. Existing data is classified. If the historical sequence is missing, the intelligent driver model IDM is used for reconstruction. If the historical sequence data is complete, the fusion model IDM-LSTM is used for reconstruction.

[0113] S5.2. The fusion model IDM-LSTM is used for reconstruction. The LSTM model includes an input gate, a forget gate, and an output gate. The special gate structure is used to consider the long-term and short-term dependencies in time series data. The flow of trajectory information between different gate structures is used to consider the impact of historical sequences on the reconstructed sequence. Specifically, the expressions are shown in Equations (18) to (23):

[0114] f t =σ(W f ·[h t-1 ,x t ]+b f ) (18)

[0115] i t =σ(W i ·[h t-1 ,x t ]+b i ) (19)

[0116]

[0117] o t =σ(W o [h t-1 ,x t ]+b o ) (twenty two)

[0118] h t =o t *tanh(C t ) (twenty three)

[0119] where f t is the output of the forget gate, i t is the output of the input gate, is a candidate cell state, C t is the unit state at the current moment, h t is the hidden state at the current moment, x t Represents the input data; W f , W i , W C , W o Respectively represent the weight matrix of the forget gate, the weight matrix of the input gate, the weight matrix of the hidden state update, and the weight matrix of the output gate; b f , b i , b C , b o Respectively represent the bias vector of the forget gate, the bias vector of the input gate, the bias vector of the hidden state update, and the bias vector of the output gate;

[0120] S5.3 adopts the method of fusion model IDM-LSTM to achieve the fusion of the two models through the weight module. The weight module is shown in expressions (24)-(25). By fusing the reconstruction results of the IDM model and the reconstruction results of the LSTM model, the prediction results of the IDM-LSTM model are obtained. The prediction results are used to calculate the loss of the LSTM model and to update the parameters in the training process, thereby enhancing the training process of the LSTM model.

[0121]

[0122] w IDM,i +w LSTM,i =1 (25)

[0123] Among them, s LSTM,i represents the reconstruction result of vehicle i by the LSTM model, s IDM,i represents the result of reconstruction of the intelligent driver model IDM, w IDM,i ,w LSTM,i They represent the weight coefficients of the intelligent driver model IDM and LSTM model, respectively, and represent the credibility of different models. IDM,i ,w LSTM,i The sum of is 1;

[0124] S5.4. The model error is evaluated using three evaluation indicators: MAE, RMSE and MAPE, as shown in the following formula:

[0125]

[0126] Furthermore, as a preferred embodiment of the present invention, step S6 includes the following sub-steps:

[0127] S6.1. In the full perception scenario, first reconstruct the missing vehicle trajectories using the intelligent driver model (IDM). Complete vehicle trajectory reconstruction based on the following relationship and execute steps S4.1 to S4.3.

[0128] S6.2, the intelligent driver model IDM, the reconstruction result is used as input to the LSTM model to assist the LSTM model training process, and then execute step S5.3;

[0129] S6.3. Use the fusion model IDM-LSTM method to achieve the fusion of the two models through the weight module, and execute step S5.4 to reconstruct the vehicle trajectory in the full perception scenario.

[0130] The location selected for this embodiment is Highway 101 (also known as the Hollywood Freeway) in Los Angeles, California, USA, and the observation direction is from south to north. The road section is about 640 meters long, and the main road contains 5 lanes to ensure that a larger range of traffic flow dynamics can be covered. The data is recorded at a sampling frequency of 1 Hz, capturing key features such as vehicle position information, speed changes, and lane occupancy in the area to support in-depth analysis of traffic flow characteristics on multi-lane highways. In this study, real data was used to calibrate the intelligent driver model IDM. The model calibration parameters are shown in Table 1, where v0 represents the free flow speed, S represents the minimum distance between vehicles at rest, and a represents the distance between vehicles at rest. max represents the maximum acceleration, b represents the comfortable deceleration, T safe Indicates safe headway.

[0131] Table 1

[0132]

[0133] First, the trajectory data is processed and analyzed. The data is preprocessed, including the processing of missing values ​​and outliers. The data is converted to units. The distance unit in the original data is feet, which needs to be converted to meters, and the time is converted to seconds. The sampling interval in the original data is 1Hz. The present invention downsamples it to 10Hz to reduce the complexity of the model. Based on the data processing, the vehicle trajectory diagram is drawn. The vehicle trajectory diagram is as follows Figure 3 As shown in Figure 2, since the data used are at the peak period, there is an obvious shock wave propagation path.

[0134] Then the trajectory reconstruction scenarios are divided into three, and the corresponding trajectory data for the three scenarios are generated, taking into account the spatiotemporal distribution of autonomous driving vehicles at three penetration rates of 5%-15%.

[0135] Based on the constructed dataset and input parameters, different trajectory reconstruction methods were used to reconstruct vehicle trajectories for different trajectory reconstruction scenarios. In the conventional traffic flow scenario, the IDM model was used to reconstruct vehicle trajectories. The penetration rate of autonomous vehicles was set to 5%, and the penetration rate of floating vehicles was set to vary from 5% to 15%. The corresponding experimental results are shown in Table 2, Trajectory Reconstruction Error for the Conventional Traffic Flow Scenario. As can be seen from Table 2, the higher the penetration rate, the higher the trajectory reconstruction accuracy.

[0136] Table 2

[0137]

[0138] In the semi-perception scenario, the IDM and IDM-LSTM models were used to reconstruct vehicle trajectories. The corresponding model errors are shown in Table 3. The tests were conducted under three conditions: 5%, 10%, and 15% penetration rates for autonomous vehicles and floating vehicles. It was found that the penetration rate significantly affected trajectory reconstruction accuracy. Furthermore, the IDM-LSTM model often achieved higher accuracy than the IDM model under the same conditions.

[0139] Table 3 Trajectory reconstruction error in semi-perception scenario

[0140]

[0141]

[0142] In the full-perception scenario, the fusion model is used to reconstruct vehicle trajectories. Comparisons with other models are conducted, yielding the results shown in Table 4, which shows the trajectory reconstruction error table for the full-perception scenario. Under the same conditions, the IDM-LSTM model achieves higher accuracy, indicating that model fusion helps improve trajectory reconstruction accuracy.

[0143] Table 4

[0144]

[0145] Comprehensively considering the three trajectory reconstruction scenarios, the vehicle trajectory reconstruction method proposed in this invention, which is adaptable to multiple scenarios of mixed traffic flow, still has good performance and plays an important role in the trajectory reconstruction of connected vehicles under low penetration rates in the future.

[0146] Further, Figure 4 Figures (a), (b), and (c) show a comparison of the trajectories reconstructed by the three algorithms. The reconstructed vehicle trajectory points using our method are closer to the real situation. These results further demonstrate the superiority of our proposed algorithm and confirm the importance of selecting the appropriate method for reconstructing vehicle trajectories based on different scenarios.

[0147] While the present invention has been described above with reference to preferred embodiments, this is not intended to limit the present invention. Persons skilled in the art will readily appreciate that various modifications and variations can be made without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A vehicle trajectory reconstruction method adapted to mixed traffic flow and multiple scenarios, characterized by: The following steps are involved: S1. Collect the trajectory position, speed and passing time information of surrounding manually driven vehicles; S2. Divide the target scene into three scenarios based on the types of adjacent floating vehicles: full perception scenario, semi-perception scenario, and regular traffic flow scenario. Consider the penetration rate of floating vehicles and generate trajectory data for the three scenarios. Specifically, determine the types of two adjacent floating vehicles in the target scene. If both adjacent floating vehicles are autonomous vehicles, the target scene is named a full perception scenario. If one is an autonomous vehicle and the other is a manually driven vehicle that can only obtain its own vehicle driving status information, the target scene is named a semi-perception scenario. If both adjacent floating vehicles are manually driven vehicles, the target scene is named a regular traffic flow scenario. S3. Use a sliding window approach to divide vehicle trajectories and divide the dataset into training, validation, and test sets according to specific proportions. S4. In a conventional traffic flow scenario, obtain the trajectory data of the floating vehicle itself and reconstruct the vehicle using the intelligent driver model under different floating vehicle penetration rates; including the following steps: S4.

1. In the intelligent driver model, the vehicle is determined by lane information, location information and time information. The leading vehicle and the following vehicle are as follows: ， ， in Is a representation of the vehicle Is it a vehicle? The leading vehicle, Is a representation of the vehicle Is it a vehicle? A value of 1 indicates that it is a leading car or a following car, and a value of 0 indicates that it is not a leading car or a following car; S4.

2. Use the intelligent driver model to estimate the missing vehicle trajectory information. The intelligent driver model (IDM) is used to reconstruct the other missing vehicle trajectory segments based on the observation segments of the preceding vehicle. The intelligent driver model (IDM) is as follows: ， ， ， ， ， Where, represents the expected spacing, Indicates the headway between the front and rear vehicles. Indicates the speed difference between the front and rear vehicles. Represent the maximum acceleration and comfortable deceleration respectively, For safe headway, is the headway between vehicles at rest, is the desired speed, Indicates the vehicle length of the preceding vehicle; S4.

3. Adjust the reconstructed vehicle trajectory to ensure that the reconstructed vehicle trajectory is between the previous segment and the next segment, as shown in the following formula: ， ； S5. In the semi-perception scenario, the vehicle with a fragmented trajectory is reconstructed using the fusion model IDM-LSTM. The vehicle with missing trajectory information is reconstructed using the intelligent driver model. S6. In the full perception scenario, obtain the fragmented trajectory information of all vehicles, introduce a weight module to fuse the intelligent driver model with the long short-term memory neural network, namely IDM-LSTM, to reconstruct the missing vehicle trajectories.

2. The vehicle trajectory reconstruction method adapted to mixed traffic flow in multiple scenarios according to claim 1 is characterized in that: In step S1, vehicles passing through the target road section are detected and numbered by the fixed detector at the beginning of the road side. , record vehicle The time to pass the fixed detector position at the start is ,vehicle The time to pass the end of the study section is , according to the vehicle number, the vehicle trajectory is retrieved and the vehicle The set of vehicle trajectory observations on the target road segment , The set of trajectories of all vehicles ,in, For vehicles Passing on the target road Longitudinal distance travelled at the time, For vehicles After studying the road The speed of time, For vehicles On the research section The acceleration of time, For vehicles On the research section The lane number at the moment.

3. The vehicle trajectory reconstruction method adapted to mixed traffic flow in multiple scenarios according to claim 1 is characterized in that: In step S2, the penetration rate of floating vehicles is considered and trajectory data for three scenarios is generated, as follows: Based on the fact that the floating cars are evenly distributed, the intervals between the floating cars As follows: ， Where, is the penetration rate of autonomous vehicles, Indicates floating car and floating cars The interval between At the same time, random factors are introduced Let's consider the non-uniform distribution among floating cars, ， Where, Is a probability generated by a random program. If this probability is less than the random factor, the current vehicle is set as a floating vehicle. Otherwise it is not a floating car .

4. The vehicle trajectory reconstruction method adapted to mixed traffic flow in multiple scenarios according to claim 1 is characterized in that: Step S3 includes the following sub-steps: S3.

1. Use the sliding window method to divide the vehicle trajectory, and the selected historical sequence length is , the reconstruction length is , then Historical sequence of samples and reconstructed sequence The time periods are as follows: ， ， The vehicle's position, speed, acceleration, and lane information are all within this time range, resulting in time series data. The expression is as follows: ， Where, is the start time of each sample; S3.

2. According to the principle of stratified sampling, the time series data is divided into training set, validation set and test set according to the preset ratio, where Represent the training set, validation set and test set respectively: ， ， ， are all vehicle trajectory samples, , , is the corresponding proportional coefficient.

5. The vehicle trajectory reconstruction method adapted to mixed traffic flow in multiple scenarios according to claim 1 is characterized in that: Step S5 includes the following sub-steps: S5.

1. In the semi-perception scenario, some human-driven vehicle trajectories are reconstructed using the fusion model IDM-LSTM. Other vehicle trajectories are reconstructed using steps S4.1 to S4.

3. Existing data is classified. If the historical sequence is missing, the intelligent driver model IDM is used for reconstruction. If the historical sequence data is complete, the fusion model IDM-LSTM is used for reconstruction. S5.

2. Reconstruction is performed using the fusion model IDM-LSTM. The LSTM model includes an input gate, a forget gate, and an output gate. By circulating trajectory information between different gate structures, the influence of the historical sequence on the reconstructed sequence is considered. The specific expression is as follows: ， ， ， ， ， ， in is the output of the forget gate, is the output of the input gate, is a candidate cell state, is the current cell state, is the hidden state at the current moment, Represents input data; , , , Respectively represent the weight matrix of the forget gate, the weight matrix of the input gate, the weight matrix of the hidden state update, and the weight matrix of the output gate; , , , Respectively represent the bias vector of the forget gate, the bias vector of the input gate, the bias vector of the hidden state update, and the bias vector of the output gate; S5.3 uses the IDM-LSTM fusion model method to achieve the fusion of the two models through the weight module. The weight module is shown below. By fusing the reconstruction results of the IDM model and the LSTM model, the prediction results of the IDM-LSTM model are obtained. The prediction results are used to calculate the loss of the LSTM model, update the parameters during the training process, and enhance the training process of the LSTM model. ， ， in, Indicates that the LSTM model reconstructs the vehicle The reconstruction result of represents the result of reconstruction of the intelligent driver model IDM, They represent the weight coefficients of the intelligent driver model IDM and LSTM model, respectively, and represent the credibility of different models. The sum of is 1; S5.

4. The model error is evaluated using three evaluation indicators: MAE, RMSE and MAPE, as shown in the following formula: ， ， 。 6. The vehicle trajectory reconstruction method adapted to mixed traffic flow in multiple scenarios according to claim 5 is characterized in that: Step S6 includes the following sub-steps: S6.

1. In the full perception scenario, first reconstruct the missing vehicle trajectory using the intelligent driver model (IDM), complete the vehicle trajectory reconstruction based on the car-following rule, and execute steps S4.1 to S4.

3. S6.2, the intelligent driver model IDM, the reconstruction result is used as input to the LSTM model to assist the LSTM model training process, and then execute step S5.3; S6.

3. Use the fusion model IDM-LSTM method to achieve the fusion of the two models through the weight module, and execute step S5.4 to reconstruct the vehicle trajectory in the full perception scenario.

Images