Automatic driving mixed traffic flow vehicle following prediction method and system

Abstract

The invention discloses an AV-MTF vehicle following prediction method and an AV-MTF vehicle following prediction system, an AV-MTF following vehicle classification model and a vehicle following prediction model are designed, and the output vehicle following acceleration, speed or trajectory can be used for vehicle following speed abnormity identification and vehicle management and control in an AV-MTF environment. The following vehicle classification model is used for judging the types of following vehicles according to the vehicle following motion information, and the vehicle following prediction model is used for predicting a sequence of vehicle following acceleration, speed or trajectory in a future period of time by combining the vehicle types and the vehicle motion information; according to the anomaly recognition algorithm, on the basis of one-time prediction of acceleration or a speed sequence, whether the difference between the predicted speed of a following vehicle and the actual collection speed of the following vehicle is within a reasonable range or not is detected in a self-adaptive mode to judge abnormal collection data of the vehicle. The method is simple and easy to implement, vehicle management and control can be better carried out for the AV-MTF environment, and then the road traffic efficiency and safety can be improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation and autonomous driving vehicles, and in particular to a method and system for predicting vehicle following in autonomous driving mixed traffic flow. Background Art

[0002] It will take a long time for autonomous vehicles (AV) to go from landing to full development. AV-Mixed Traffic Flow (AV-MTF) where AV and human-driven vehicles (HV) coexist will exist for a long time in the future. However, most of the existing data-driven vehicle following models based on deep learning algorithms perform speed prediction modeling for traditional HV environments, ignoring the different following motion characteristics of AV and HV in AV-MTF environments. Accurately constructing an AV-MTF vehicle following prediction model can better manage and control vehicles in AV-MTF environments, which is conducive to improving road traffic efficiency and safety. Summary of the invention

[0003] Purpose of the invention: In view of the problems existing in the prior art, the purpose of the present invention is to establish a method and system for predicting vehicle following in mixed traffic flow in autonomous driving, so as to accurately predict the vehicle following acceleration, speed or trajectory.

[0004] Technical solution: In order to achieve the purpose of the above invention, the present invention provides the following technical solution:

[0005] A method for predicting the following speed of vehicles in mixed traffic flow and identifying abnormalities in an autonomous driving environment comprises the following steps:

[0006] (1) Obtaining the motion information of the lead vehicle and the following vehicle in the AV-MTF;

[0007] (2) After obtaining the following vehicle information within a period of time, the following vehicle classification model is used to determine the following vehicle category based on the following vehicle motion information, wherein the vehicle category includes AV and HV; the feature vector used to determine the following vehicle category includes the speed of the leading vehicle, the speed of the following vehicle, the acceleration of the following vehicle, and the distance between the two vehicles at multiple moments;

[0008] (3) combining the vehicle category with the vehicle motion information as the input of a vehicle following prediction model, and outputting the predicted acceleration, speed or trajectory sequence for a period of time in the future through the vehicle following prediction model; the vehicle following prediction model is used to predict the vehicle following acceleration, speed or trajectory sequence based on the vehicle motion information for a period of time and the vehicle category determined by the following vehicle classification model;

[0009] (4) Based on the one-time predicted acceleration or speed sequence, the abnormal speed of the vehicle is identified, or the vehicle is managed and controlled in the AV-MTF environment based on the vehicle trajectory output by the vehicle following prediction model; in the autonomous driving mixed traffic flow following abnormal speed identification algorithm, the predicted following speed of the vehicle and the actual collected speed are compared, and the error value between the two is calculated and compared with the set threshold, thereby realizing the identification of abnormal collected data; wherein the predicted following speed is directly predicted by the vehicle following prediction model or calculated from the following acceleration predicted by the vehicle following prediction model.

[0010] Preferably, the car-following vehicle classification model is a car-following vehicle classification model based on an Attention-LSTM model. The Attention-LSTM model is composed of a plurality of LSTM units connected in series, and an Attention module is added before the model output.

[0011] Preferably, the method for constructing the car-following vehicle classification model comprises the following steps:

[0012] (1) Obtain the motion information of the leading car and the following car in the AV-MTF of T time steps from time t-T+1 to time t, including the speed v of the leading car l , following car speed v f , following car acceleration a f , the distance between the two vehicles Δx, and the relative speed Δv;

[0013] (2) Based on the Attention-LSTM neural network algorithm, a following vehicle classification model is constructed. Appropriate input information is selected from the relevant motion information of the pilot vehicle and the following vehicle. 1 (·) After training and calculation, the AV-MTF following vehicle category is identified:

[0014] Ω=F 1 (I 1 )

[0015] In the formula, the pilot vehicle speed v is selected l , following car speed v f , following car acceleration a f , the distance between the two vehicles Δx constitutes the characteristic vector I of the following vehicle category 1 , Ω represents the category of the following vehicle in AV-MTF, Ω∈{0,1}, where 0 represents AV, 1 represents HV, and F 1 (·) is the Attention-LSTM model.

[0016] Preferably, the input of the vehicle following prediction model is:

[0017] I 3 =Concat(I2 ,Ω)

[0018] In the formula, select the following car speed v f , the distance between the two vehicles Δx, and the relative speed Δv constitute the characteristic vector I of the following vehicle motion information 2 , Concat(·) means connection, I 3 Input information to the vehicle following prediction model.

[0019] Preferably, the vehicle following prediction model is implemented based on a Transformer model, and the model construction method comprises the following steps:

[0020] (1) The AV-MTF vehicle following prediction model is constructed based on the Transformer algorithm. Appropriate input information is selected from the relevant motion information of the leading vehicle and the following vehicle to form the input information of the following speed prediction module. The input information must include the historical information of the selected parameter before the time t:

[0021] I 3 =Concat(I 2 ,Ω)

[0022] (2) After the Transformer model is trained and calculated, the predicted vehicle following speed is output. This study also considers the impact of the following vehicle category and inputs it into the model to establish the AV-MTF following speed vehicle following acceleration, speed and trajectory prediction model:

[0023] O 1 =F 2 (I 3 )

[0024] In the formula, O 1 is the predicted vehicle following acceleration, speed and trajectory sequence, F 2 (·) is the Transformer model.

[0025] (3) The output of the prediction model is the acceleration, speed or trajectory sequence of the following vehicle. If the output is the following vehicle acceleration sequence, the speed and trajectory of the vehicle can be calculated based on the acceleration of the following vehicle:

[0026] v i+1 =v i +a i Δt

[0027] x i+1 =x i +v i Δt

[0028] In the formula, a iis the vehicle following acceleration at time i, Δt is the time interval between data sampling and model output, v i is the vehicle following speed at time i, x i is the vehicle position at time i.

[0029] If the vehicle following speed is output, the vehicle motion trajectory can be calculated based on the vehicle following speed sequence:

[0030] x i+1 =x i +v i Δt

[0031] The model can also directly output the future trajectory x of the vehicle i+1 ,...,x i+L .

[0032] Preferably, in step (4), based on the AV-MTF vehicle following speed abnormality recognition algorithm, the recognition and recording of abnormal collected data are realized, including the following steps:

[0033] (1) Based on the one-time prediction of acceleration or speed sequence, the predicted vehicle following speed and the actual collected speed are compared moment by moment, and the error between the two is calculated. The AV-MTF vehicle following speed anomaly recognition algorithm uses the absolute percentage error between the predicted vehicle following speed and the actual collected following speed as the measurement index for anomaly recognition, and calculates the absolute percentage error between the predicted value and the actual value:

[0034]

[0035] In the formula, To predict the vehicle following speed at time t, is the actual collected following speed at time t, and d(t) is the absolute percentage error at time t;

[0036] (2) During the recognition process, the deviation between the current speed prediction value and the actual collected value is calculated. When the absolute percentage error d(t) between the predicted value and the actual value exceeds the set threshold α, it means that the deviation between the predicted value and the actual value is large. The maximum number of iterations of the abnormal recognition algorithm is set to the length of the prediction sequence. When abnormal data is identified, the iteration process ends and the time corresponding to the abnormal data is output. In this way, the abnormal collected data can be detected and identified, and the time corresponding to the abnormal data is recorded. The judgment method is:

[0037]

[0038] In the formula, α is the threshold for setting the average percentage error, R(t) is the abnormal data recognition result, 0 represents that the data at that moment is abnormal data, and 1 represents that the data at that moment is normal data.

[0039] Based on the same inventive concept, the present invention provides a system for predicting and identifying the following speed of vehicles in mixed traffic flow under autonomous driving, comprising:

[0040] The motion information acquisition module is used to obtain the motion information of the pilot car and the following car in the AV-MTF;

[0041] A vehicle category identification module is used to identify the category of the following vehicle using a following vehicle classification model based on the following vehicle movement information after acquiring the following vehicle information within a period of time, wherein the vehicle categories include AV and HV; the feature vectors used to identify the category of the following vehicle include the speed of the leading vehicle, the speed of the following vehicle, the acceleration of the following vehicle and the distance between the two vehicles at multiple moments;

[0042] A prediction module is used to combine the vehicle category with the vehicle motion information as the input of the vehicle following prediction model, and output the predicted acceleration, speed or trajectory sequence for a period of time in the future through the vehicle following prediction model; the vehicle following prediction model is used to predict the vehicle following acceleration, speed or trajectory sequence based on the vehicle motion information within a period of time and the vehicle category determined by the following vehicle classification model;

[0043] The post-processing module is used to identify abnormal vehicle speed based on a one-time predicted acceleration or speed sequence, or to manage and control the vehicle in an AV-MTF environment based on the vehicle trajectory output by the vehicle following prediction model; in the autonomous driving mixed traffic flow following abnormal speed identification algorithm, the predicted following speed and the actual collected speed of the vehicle are compared, and the error value between the two is calculated and compared with the set threshold, thereby realizing the identification of abnormal collected data; wherein the predicted following speed is directly predicted by the vehicle following prediction model or calculated from the following acceleration predicted by the vehicle following prediction model.

[0044] The present invention also provides a computer system, including a memory, a processor, and a computer program / instruction stored in the memory and executable on the processor, wherein the computer program / instruction, when executed by the processor, implements the steps of the automatic driving mixed traffic flow vehicle following prediction method.

[0045] The present invention also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the automatic driving mixed traffic flow vehicle following prediction method.

[0046] Beneficial effects: Compared with the prior art, the present invention has the following beneficial effects: the present invention is oriented to the AV-MTF scenario composed of AVs and HVs, establishes a following vehicle classification model and a vehicle following prediction model, and proposes a vehicle following speed abnormality recognition algorithm. The present invention combines the following vehicle classification model with the speed vehicle following prediction model, effectively improving the accuracy of vehicle following acceleration, speed or trajectory prediction. In addition, the vehicle following speed abnormality recognition algorithm has a high recognition accuracy rate for abnormal speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a method for predicting the following speed of vehicles in mixed traffic flow and identifying anomalies in an autonomous driving system provided by an embodiment of the invention;

[0048] Figure 2 4 is a flow chart of the AV-MTF vehicle following speed abnormality identification algorithm in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0050] The embodiment of the present invention provides a method for predicting the following of vehicles in mixed traffic flow in an autonomous driving environment. The method is based on a deep learning algorithm and determines the type of following vehicles and predicts the following acceleration, speed or trajectory sequence of following vehicles according to the following motion information of the vehicles, so as to realize the recognition, management and control of abnormal following speed of vehicles. By correctly judging the type of following vehicles and inputting it into the model as key information, the prediction effect of the following acceleration, speed or trajectory of vehicles can be improved, thereby improving the accuracy of speed abnormality recognition and better managing and controlling vehicles in the AV-MTF environment.

[0051] See also Figure 1 The method for predicting a vehicle following a mixed traffic flow in an autonomous driving system provided by an embodiment of the present invention specifically comprises the following steps:

[0052] (1) Obtaining the motion information of the lead vehicle and the following vehicle in the AV-MTF;

[0053] (2) After obtaining the following vehicle information within a period of time, the following vehicle classification model is used to determine the following vehicle category based on the following vehicle motion information, wherein the vehicle category includes AV and HV; the feature vector used to determine the following vehicle category includes the speed of the leading vehicle, the speed of the following vehicle, the acceleration of the following vehicle, and the distance between the two vehicles at multiple moments;

[0054] (3) combining the vehicle category with the vehicle motion information as the input of a vehicle following prediction model, and outputting the predicted acceleration, speed or trajectory sequence for a period of time in the future through the vehicle following prediction model; the vehicle following prediction model is used to predict the vehicle following acceleration, speed or trajectory sequence based on the vehicle motion information for a period of time and the vehicle category determined by the following vehicle classification model;

[0055] (4) Based on the one-time predicted acceleration or speed sequence, the abnormal speed of the vehicle is identified, or the vehicle is managed and controlled in the AV-MTF environment based on the vehicle trajectory output by the vehicle following prediction model; in the autonomous driving mixed traffic flow following abnormal speed identification algorithm, the predicted following speed of the vehicle and the actual collected speed are compared, and the error value between the two is calculated and compared with the set threshold, thereby realizing the identification of abnormal collected data; wherein the predicted following speed is directly predicted by the vehicle following prediction model or calculated from the following acceleration predicted by the vehicle following prediction model.

[0056] The following is a detailed description of the steps of an embodiment of the present invention using an Attention-LSTM-Transformer-based autonomous driving mixed traffic flow vehicle following prediction method, using a following vehicle classification model based on the Attention-LSTM algorithm and a vehicle following prediction model based on the Transformer algorithm.

[0057] The Attention-LSTM-Transformer-based automatic driving mixed traffic flow vehicle following prediction method described in an embodiment of the present invention is applied to a vehicle following scenario and specifically includes the following steps:

[0058] (1) The motion information of the lead vehicle and the following vehicle in the AV-MTF is obtained through the roadside equipment, including the speed, acceleration and distance between the two vehicles. The index numbers of the collected data are t-T+1,...,t in chronological order, with a total of T moments of motion information. The data collection time interval is 0.1s.

[0059] (2) AVs and HVs have different following motion characteristics. After obtaining the following motion information over a period of time, the Attention-LSTM following vehicle classification model can be used to identify the AV-MTF following vehicle category based on the vehicle following motion information. The vehicle category includes AVs and HVs.

[0060] ΩΔF 1 (I 1 )

[0061] In the formula, the pilot vehicle speed v is selected l , following car speed v f , following car acceleration af , the distance between the two vehicles Δx constitutes the characteristic vector I of the following vehicle category 1 , Ω represents the category of the following vehicle in AV-MTF, Ω∈{0,1}, where 0 represents AV, 1 represents HV, and F 1 (·) is the Attention-LSTM model.

[0062] LSTM is a special recurrent neural network (RNN) that is often used to process and predict time series data. By designing the memory unit and gating mechanism inside the LSTM unit, the gradient vanishing and gradient exploding problems of traditional RNN in processing sequences can be effectively solved.

[0063] Given the input x at time t t and the hidden state h at the previous moment t-1 , then the input gate i t 、Forget gate t , output gate o t The specific calculation method is as follows:

[0064] i t =σ(W ii x t +b ii +W hi h t-1 +b hi )

[0065] f t =σ(W if x t +b if +W hf h t-1 +b hf )

[0066] o t =σ(W io x t +b io +W ho h t-1 +b ho )

[0067] Where W and b are weight and bias terms respectively, and σ is the sigmoid activation function.

[0068] The candidate g at time t in the model t , cell status c t and the hidden state h t , which can be calculated by the following formula:

[0069] g t =σ(Wig x t +b ig +W hg h t-1 +b hg )

[0070] c t =f t ⊙c t-1 +i t ⊙g t

[0071] h t =o t ⊙tanh(c t )

[0072] Where tanh(·) is the hyperbolic tangent function, W and b are the weight and bias terms respectively, and ⊙ is the hadamard product.

[0073] (3) The following vehicle category is combined with the vehicle motion information as the input of the Transformer following speed vehicle following prediction model, and the vehicle following prediction model outputs the predicted acceleration, speed or trajectory sequence for a period of time in the future. This study also considers the impact of the following vehicle category and also inputs it into the model:

[0074] I 3 =Concat(I 2 ,Ω)

[0075] In the formula, select the following car speed v f , the distance between the two vehicles Δx, and the relative speed Δv constitute the characteristic vector I of the following vehicle motion information 2 , Concat(·) means connection, I 3 Input information for the speed vehicle following prediction model.

[0076] After the Transformer model training and calculation, the predicted vehicle following acceleration, speed or trajectory sequence is output.

[0077] The index numbers of the output sequence are t+1,...,t+L in chronological order, and the time interval of the output data is 0.1s. :

[0078] O 1 =F 2 (I 3 )

[0079] In the formula, O 1 is the predicted vehicle following acceleration, speed or trajectory sequence, F 2 (·) is the Transformer model.

[0080] The Transformer architecture abandons loops and convolutions and is completely based on the attention mechanism. It can consider all positions in the input sequence at the same time, so that it can better capture long-distance dependencies. Transformer has an encoder-decoder architecture. The encoder consists of multi-head attention and a feedforward neural network. After passing through these two sub-layers, the information is summed and normalized. The decoder is also a similar structure composed of multi-head attention and a feedforward neural network. The difference is that the decoder not only obtains the decoder input information, but also inputs the encoder output information.

[0081] The multi-head attention module is the most important mechanism of Transformer. When processing sequence data, it can extract important information from the input by assigning different attention weights to information at different positions. The multi-head attention module is composed of h scaled dot-product attention (SDPA) connected together. Scaled dot-product attention is the transposed dot product of the query matrix Q and the key matrix K. It can calculate the correlation between each vector and weight the value matrix V according to the matching degree of Q and K. Its output is as follows:

[0082]

[0083] Where Q(Query), K(Key) and V(Value) are query, key and value matrices respectively. Refers to the square root of the key matrix.

[0084] Multi-head attention can calculate the relevance of any position in the sequence. Compared with SDPA, the multi-head attention module focuses on the global information of long sequences more effectively. After Q, K, and V are input to SDPA, this process is repeated h times. Finally, they are concatenated through the Concat layer to obtain a global self-attention feature map. The first multi-head attention module of the Transformer model decoder enables a mask to prevent the decoder from accessing the target sequence information after the position when generating the output of each position. The specific formula is:

[0085] Multihead(Q,K,V)=Concat(head 1 ,…,head h )W 0

[0086] head i =Attention(QW i Q ,KWi K ,VW i V ),i=1,2,...,h

[0087] In the formula, head i Represents the self-attention of the i-th head, the parameter matrix where d model is the model dimension, d q is the dimension of the query vector, d k is the dimension of the key vector, d v Is the dimension of the Value Vector.

[0088] Add&Norm consists of two parts: summation and normalization. It is used after multi-head attention and feedforward neural network. Add refers to adding the output result to the input information, and Norm refers to LayerNormalization. Taking summation and normalization after multi-head attention layer as an example, the calculation method is as follows:

[0089] Output=LayerNorm(X+MultiHeadAttention(X))

[0090] Where X represents the input of the multi-head attention layer, and MultiHeadAttention(X) is the output of X through the multi-head attention layer.

[0091] The input of the Transformer encoder and decoder needs to pass through the embedding module. When building the AV-MTF vehicle following prediction model, it is usually implemented using a linear layer. The Transformer model structure is different from the RNN and cannot utilize the input sequence information, which is very important for the AV-MTF vehicle following speed prediction modeling. Therefore, the Transformer model uses position encoding to implement the input of sequential information and adds the position encoding to the input and output embedding. The calculation formulas are:

[0092]

[0093]

[0094] In the formula, pos represents the position of the input information in the world, 2i refers to the even-numbered dimension, and 2i+1 refers to the odd-numbered dimension. Since the longest sequence length of input and output in this study is 50, d modelA smaller value is appropriate, such as 100. Input I of the encoder of the AV-MTF vehicle following prediction model 3 The expression is as follows:

[0095]

[0096] If the sampling interval of the vehicle following motion features in the dataset is 0.1s, the length T of the input vehicle motion feature sequence is set to 50, that is, Δx, Δv, v and Ω within t-5 to t-0.1 are combined into a parameter matrix with a dimension of 50×4 as the input to the encoder of the Transformer model.

[0097] During the model training process, the decoder uses the future speed sequence v(t+1),...,v(t+L) of the following vehicle as the output of the model, and uses a masking mechanism to prevent the decoder from accessing information after that moment when outputting information. The output of the decoder is also the predicted future vehicle following speed sequence. The length L of the input future speed sequence is set to 5. In the model prediction stage, the decoder no longer inputs the future speed sequence information of the following vehicle, and uses an autoregressive mechanism to gradually decode and generate the future vehicle following acceleration, speed or trajectory sequence. In the model testing process, assuming that t is the current moment, the input historical information is the parameter matrix of T moments from t-T+1 to t, and the acceleration, speed or trajectory of L time steps from t+1 to t+L is output. The formula is as follows:

[0098]

[0099] In the formula, F(·) represents the Transformer model of data input, and is also expressed as the mapping relationship between input and output variables. The length of the output vehicle speed sequence L is 5, that is, the model outputs the vehicle following acceleration sequence for the next 0.5 seconds as The vehicle following speed sequence is The vehicle following trajectory sequence is

[0100] If the output vehicle following acceleration sequence The speed and trajectory of the vehicle can be calculated based on the acceleration of the following vehicle; if the output vehicle following speed sequence The trajectory of the following vehicle can be calculated based on its speed; the model can also directly output the future trajectory of the vehicle The formula is as follows:

[0101] v i+1 =v i +a i Δt

[0102] x i+1 =x i +vi Δt

[0103] In the formula, a i is the vehicle following acceleration at time i, Δt is the time interval between data sampling and model output, v i is the vehicle following speed at time i, x i is the vehicle position at time i.

[0104] (4) In the one-time prediction speed sequence Based on (can also be based on the acceleration sequence The AV-MTF vehicle following speed anomaly recognition algorithm predicts the vehicle following speed. and the actual collected following speed The absolute percentage error is used as a measure of anomaly identification, and the absolute percentage error between the predicted value and the actual value is calculated;

[0105]

[0106] In the formula, To predict the vehicle following speed at time t, is the actual collected following speed at time t, and d(t) is the absolute percentage error at time t.

[0107] During the recognition process, the deviation between the current speed prediction value and the actual collected value is calculated. When the absolute percentage error d(t) between the prediction value and the actual value exceeds the set threshold, it means that the deviation between the prediction value and the actual value is large, indicating that abnormal data has been collected during the vehicle following process. The judgment method is:

[0108]

[0109] In the formula, α is the threshold for setting the average percentage error, R(t) is the abnormal data recognition result, 0 represents that the data at that moment is abnormal data, and 1 represents that the data at that moment is normal data.

[0110] The maximum number of iterations of the anomaly recognition algorithm is set to the length of the prediction sequence. The present invention sets the maximum number of iterations to 5. When abnormal data is identified, the iteration process ends and the time corresponding to the abnormal data is output. Figure 2 The AV-MTF vehicle following speed anomaly identification algorithm flow is illustrated.

[0111] The embodiment of the present invention combines the following vehicle classification model and the vehicle following acceleration, speed or trajectory prediction model, based on the Attention-LSTM-Transformer model, and can achieve a short-term speed prediction error of the order of centimeters per second, avoiding the performance degradation of the traditional following model applied to the AV-MTF environment. At the same time, the Transformer model has a better effect than the traditional recurrent neural network in dealing with long-term dependency problems, and can ensure the stability and accuracy of the vehicle following prediction model. The prediction model can output different motion sequence information according to actual needs, specifically covering the vehicle's following acceleration, speed and trajectory information. Moreover, the above information can be mutually calculated through formulas, thereby giving the model more abundant application scenarios and more flexible usage methods. On this basis, a method for identifying abnormal following speed of vehicles in autonomous driving mixed traffic flow can be constructed to achieve adaptive detection and identification of abnormal collected data, and record the corresponding time of abnormal data occurrence, which is more flexible and efficient than other methods. The output vehicle acceleration, speed and trajectory sequence can be used for vehicle management and control research in the AV-MTF environment.

[0112] Based on the same inventive concept, an embodiment of the present invention provides an automatic driving mixed traffic flow vehicle following prediction system, comprising:

[0113] The motion information acquisition module is used to obtain the motion information of the pilot car and the following car in the AV-MTF;

[0114] A vehicle category identification module is used to identify the category of the following vehicle using a following vehicle classification model based on the following vehicle movement information after acquiring the following vehicle information within a period of time, wherein the vehicle categories include AV and HV; the feature vectors used to identify the category of the following vehicle include the speed of the leading vehicle, the speed of the following vehicle, the acceleration of the following vehicle and the distance between the two vehicles at multiple moments;

[0115] A prediction module is used to combine the vehicle category with the vehicle motion information as the input of the vehicle following prediction model, and output the predicted acceleration, speed or trajectory sequence for a period of time in the future through the vehicle following prediction model; the vehicle following prediction model is used to predict the vehicle following acceleration, speed or trajectory sequence based on the vehicle motion information within a period of time and the vehicle category determined by the following vehicle classification model;

[0116] The post-processing module is used to identify abnormal vehicle speed based on a one-time predicted acceleration or speed sequence, or to manage and control the vehicle in an AV-MTF environment based on the vehicle trajectory output by the vehicle following prediction model; in the autonomous driving mixed traffic flow following abnormal speed identification algorithm, the predicted following speed and the actual collected speed of the vehicle are compared, and the error value between the two is calculated and compared with the set threshold, thereby realizing the identification of abnormal collected data; wherein the predicted following speed is directly predicted by the vehicle following prediction model or calculated from the following acceleration predicted by the vehicle following prediction model.

[0117] Based on the same inventive concept, an embodiment of the present invention provides a computer system, including a memory, a processor, and a computer program / instructions stored in the memory and executable on the processor. When the computer program / instructions are executed by the processor, the steps of the autonomous driving mixed traffic flow vehicle following prediction method are implemented.

[0118] Based on the same inventive concept, an embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the autonomous driving mixed traffic flow vehicle following prediction method.

Claims

1. A method for predicting vehicle following in mixed traffic flow in an autonomous driving environment, characterized in that: The steps include: (1) Obtaining the motion information of the leading vehicle and the following vehicle in the autonomous driving mixed traffic flow AV-MTF; (2) After obtaining the following vehicle information within a period of time, the following vehicle classification model is used to determine the following vehicle category based on the following vehicle motion information, where the vehicle category includes an autonomous driving vehicle AV and a manually driven vehicle HV; the feature vector used to determine the following vehicle category includes the speed of the lead vehicle, the speed of the following vehicle, the acceleration of the following vehicle, and the distance between the two vehicles at multiple times; (3) combining the vehicle category with the vehicle motion information as the input of a vehicle following prediction model, and outputting the predicted acceleration, speed or trajectory sequence for a period of time in the future through the vehicle following prediction model; the vehicle following prediction model is used to predict the vehicle following acceleration, speed or trajectory sequence based on the vehicle motion information for a period of time and the vehicle category determined by the following vehicle classification model; (4) Based on the one-time predicted acceleration or speed sequence, the abnormal speed of the vehicle is identified, or the vehicle is managed and controlled in the AV-MTF environment based on the vehicle trajectory output by the vehicle following prediction model; in the autonomous driving mixed traffic flow following abnormal speed identification algorithm, the predicted following speed of the vehicle and the actual collected speed are compared, and the error value between the two is calculated and compared with the set threshold, thereby realizing the identification of abnormal collected data; wherein the predicted following speed is directly predicted by the vehicle following prediction model or calculated from the following acceleration predicted by the vehicle following prediction model.

2. The method for predicting vehicle following in mixed traffic flow in autonomous driving according to claim 1, characterized in that: The following vehicle classification model is a following vehicle classification model based on the Attention-LSTM model. The Attention-LSTM model is composed of multiple LSTM units connected together, and an Attention module is added before the model output.

3. The method for predicting vehicle following in mixed traffic flow in automatic driving according to claim 2, characterized in that: The method for constructing the following vehicle classification model includes: Get the motion information of the leading car and the following car in the AV-MTF of T time steps from time t-T+1 to time t, including the speed v of the leading car l , following car speed v f , following car acceleration a f , the distance between the two vehicles Δx and the relative speed Δv; Based on the Attention-LSTM neural network algorithm, a car-following vehicle classification model is constructed. Appropriate input information is selected from the relevant motion information of the pilot vehicle and the following vehicle. After the model F1(·) training calculation, the AV-MTF car-following vehicle category is determined: Ω=F1(I1) In the formula, the pilot vehicle speed v is selected l , following car speed v f , following car acceleration a f , the distance Δx between the two vehicles constitutes the feature vector I1 of the following vehicle category, Ω represents the category of the following vehicle in AV-MTF, Ω∈{0,1}, where 0 represents AV and 1 represents HV, and F1(·) is the Attention-LSTM model.

4. The method for predicting vehicle following in mixed traffic flow in autonomous driving according to claim 1, characterized in that: Inputs of the vehicle following prediction model: I3=Concat(I2,Ω) In the formula, select the following car speed v f , the distance between the two vehicles Δx, and the relative speed Δv constitute the feature vector I2 of the following vehicle motion information. Ω represents the category of the following vehicle in AV-MTF, Concat(·) represents the connection, and I3 is the input information of the vehicle following prediction model.

5. The method for predicting vehicle following in mixed traffic flow in autonomous driving according to claim 1, characterized in that: The vehicle following prediction model is implemented based on the Transformer model, and the model construction method includes: The AV-MTF vehicle following prediction model is constructed based on the Transformer algorithm. Appropriate input information is selected from the relevant motion information of the pilot vehicle and the following vehicle to form the input information of the vehicle following prediction model. The input information must include historical information of a period of time before the selected parameter t: I3=Concat(I2,Ω) In the formula, select the following car speed v f , the distance between the two vehicles Δx, and the relative speed Δv constitute the feature vector I2 of the following vehicle motion information, Ω represents the category of the following vehicle in AV-MTF, Concat(·) represents the connection, and I3 is the input information of the vehicle following prediction model; After the Transformer model training and calculation, the predicted vehicle following acceleration, speed or trajectory is output to establish the AV-MTF vehicle following prediction model: O1=F2(I3) Where O1 is the sequence of predicted vehicle following acceleration, speed or trajectory, and F2(·) is the Transformer model; If the vehicle following acceleration sequence is output, the vehicle speed and trajectory can be calculated based on the acceleration of the following vehicle: v i+1 =v i +a i Δt x i+1 =x i +v i Δt In the formula, a i is the vehicle following acceleration at time i, Δt is the time interval between data sampling and model output, v i is the vehicle following speed at time i, x i is the vehicle position at time i; If the vehicle following speed is output, the vehicle motion trajectory can be calculated based on the vehicle following speed sequence: x i+1 =x i +v i Δt The model can also directly output the future trajectory of the vehicle.

6. The method for predicting vehicle following in mixed traffic flow in autonomous driving according to claim 1, characterized in that: In step (4), the error value between the predicted following speed and the actual collected speed of the vehicle is calculated and compared with a set threshold value to realize the identification and recording of abnormal collected data, including the following steps: Based on the one-time prediction of acceleration or speed sequence, the predicted vehicle following speed and the actual collected speed are compared moment by moment, and the error between the two is calculated; the absolute percentage error between the predicted vehicle following speed and the actual collected following speed is used as a measurement indicator for abnormal identification, and the absolute percentage error between the predicted value and the actual value is calculated; In the formula, To predict the vehicle following speed at time t, is the actual collected following speed at time t, and d(t) is the absolute percentage error at time t; When the error value exceeds the set threshold, the abnormal data is detected and identified, and the time when the abnormal data appears is recorded; the judgment method is: In the formula, α is the threshold for setting the average percentage error, R(t) is the abnormal data recognition result, 0 represents that the data at that moment is abnormal data, and 1 represents that the data at that moment is normal data.

7. The method for predicting vehicle following in mixed traffic flow in an autonomous driving system according to claim 6, characterized in that: On the basis of a one-time prediction of the acceleration or velocity sequence, the maximum number of iterations is set to the length of the predicted acceleration or velocity sequence. When abnormal data is identified, the iteration process is terminated and the time corresponding to the abnormal data is output.

8. An automatic driving mixed traffic flow vehicle following prediction system, characterized in that: include: The motion information acquisition module is used to obtain the motion information of the pilot car and the following car in the autonomous driving mixed traffic flow AV-MTF; A vehicle category identification module is used to identify the category of a following vehicle using a following vehicle classification model based on the following vehicle movement information after acquiring the following vehicle information within a period of time, wherein the vehicle categories include autonomous driving vehicles AV and manually driven vehicles HV; the feature vectors used to identify the category of the following vehicle include the speed of the pilot vehicle, the speed of the following vehicle, the acceleration of the following vehicle, and the distance between the two vehicles at multiple moments; A prediction module is used to combine the vehicle category with the vehicle motion information as the input of the vehicle following prediction model, and output the predicted acceleration, speed or trajectory sequence for a period of time in the future through the vehicle following prediction model; the vehicle following prediction model is used to predict the vehicle following acceleration, speed or trajectory sequence based on the vehicle motion information within a period of time and the vehicle category determined by the following vehicle classification model; The post-processing module is used to identify abnormal vehicle speed based on a one-time predicted acceleration or speed sequence, or to manage and control the vehicle in an AV-MTF environment based on the vehicle trajectory output by the vehicle following prediction model; in the autonomous driving mixed traffic flow following abnormal speed identification algorithm, the predicted following speed and the actual collected speed of the vehicle are compared, and the error value between the two is calculated and compared with the set threshold, thereby realizing the identification of abnormal collected data; wherein the predicted following speed is directly predicted by the vehicle following prediction model or calculated from the following acceleration predicted by the vehicle following prediction model.

9. A computer system comprising a memory, a processor, and a computer program / instruction stored in the memory and executable on the processor, characterized in that: When the computer program / instructions are executed by the processor, the steps of the method for predicting vehicle following in mixed traffic flow while autonomous driving are implemented according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by the processor, the steps of the method for predicting vehicle following in mixed traffic flow while autonomous driving are implemented according to any one of claims 1 to 7.

Images