Driver Intention Recognition Method Using Continuous Hidden Markov Model

Recent research on the prediction of driver’s lane-changing behaviour requires vehicle surrounding information, as it is believed that driver’s decision on lane changing is made consciously based on those information. However, current research has shown that the usage of such surrounding information leads to high false alarm rate of lane-changing predict system [1]. Therefore this paper contributes to developing a lane-changing prediction method which uses vehicle state information only. From the perspective of the observer’s daily experience, this paper selects vehicle’s lateral trajectory and the spectrum of its lateral trajectory as input to predict drivers’ lane-changing intention. A Direction Convolutional LSTM (DCLSTM) network has been developed to predict drivers’ lane-changing behaviours. Recent pure LSTM methods proposed by researchers provide high accuracy when predicting the generation of drivers’ lane-changing intentions, but they have relatively low accuracy in predicting drivers’ lane-changing direction. DCLSTM retains pure LSTM network’s high accuracy in the prediction of drivers’ lane-changing intentions, while its prediction of drivers’ lane-changing directions is also accurate. All the training and testing data are extracted from the NGSIM dataset.

An intention identification method is proposed in this paper, which is based on vehicle running state and driving behavior interaction. The driving simulator experiment is designed to obtain vehicle driving time series data of lane keeping and lane changing. Based on the stage division of lane changing process, the lane changing intention stage can be obtained. It is found that the length of lane changing intention stage approximately obeys the normal distribution, and the length of left lane changing intention stage is greater than that of right lane changing. When exploring the influencing factors on the length of lane changing intention stage, it is found that the length of intention stage is approximately linearly correlated with the average speed of vehicles. Finally, based on the vehicle running state and intention stage, a continuous hidden Markov model based on Gaussian probability density function is established, which can effectively identify the driver's lane changing intention with high recognition accuracy and great real-time performance. The average accuracy of the model is 90%, the advanced time of left and right lane changing intention is 1.5s and 1.4s.

Driving intention recognition is an important aspect of Advanced Driving Assistance Systems (ADAS) for giving drivers suggestions to maneuver safely. The intention recognition algorithms in ADAS are often developed using Machine Learning-based models. The model's input, such as environmental (ENV) and eye-tracking (ET) features affect the model's recognition performance. In this contribution, an Artificial Neural Network-based state machine is used for lane changing intention recognition. Three lane changing behaviors are considered, left/right lane change and lane keeping. Here, data consisting of ENV and ET information are collected using a driving simulator and eye-tracker. The aim is to investigate the effect of different feature types on the model's intention recognition performance. First, a 10-cross validation is performed to evaluate the model's performance, using only ENV and both ENV and ET features. The validation results show that the model with only ENV features performs better with respect to different metrics. Thus in the test, only ENV features are used to evaluate the performance. Accuracy values of higher than 80 % are achieved. Furthermore, the recognition performance of the model is compared with other Machine Learning models. The approach introduced outperforms other models in most metrics.

A major aspect in the development of advanced driving assistance systems (ADASs) is the research in developing human driving behavior prediction and recognition models. Recent contributions focus on developing these models for estimating different driving behaviors like lane or speed change. Thus, the models are incorporated into the ADAS to generate warnings and hints for safe maneuvers. Driving behavior recognition and prediction models are generally developed based on machine learning (ML) algorithms and are proven to generate accurate estimations. Previous review research contributions tend to focus on ML-based models for the prediction and recognition of speed change, trajectory change, and even driving styles. Due to high number of driving errors occurring during a lane change, a state-of-art review of different ML-based models for lane-changing behavior prediction and recognition is helpful to present a comparison between different models in terms of structure, influencing input variables, and performance. This enables the integration of the most efficient model for the development of ADASs to avoid accidents during a lane change. First, definitions and terms related to the model’s task and evaluation metrics used to evaluate the model’s performance are described to improve the readability. Then, the different input variables of the models affecting the lane-changing behaviors are presented. Next, a review of the models developed based on well-known approaches, such as artificial neural network (ANN), hidden Markov model (HMM), and support vector machine (SVM), using different input variables is given. Three lane-changing behaviors are focused on here: left/right lane change and lane keeping. The advantages and disadvantages of the different ML models with a comparison are summarized as well. Finally, the improvements required in the future are discussed.

By solving driver’s optimal handling input, this paper presents a novel Lane Changing Assistance System (LCAS) which can provide guidance for driver’s lane changing behavior. In addition, vehicle handling inverse dynamics method is proposed to solve driver’s optimal handling input. Firstly, to recognize driver’s lane changing intention and decrease the false alarm rate of LCAS, a lane changing intention recognition model is established. Secondly, the handling inverse dynamics model is established; and then the inverse dynamics problem is converted into the optimal control problem. Finally, the optimal control problem is converted into a nonlinear programming problem based on GPM; then sequential quadratic programming (SQP) is applied to get the solution. The direct collocation method (DCM) is used as the contrast verification of GPM. The simulation results show that the driver’s optimal handling input can be obtained according to driver’s lane changing intention in the proposed LCAS; and GPM has higher computational accuracy compared with DCM. This method may provide a reference for the research of LCAS and unmanned vehicles.

Simultaneous positive sequential vectors modeling and unsupervised feature selection via continuous hidden Markov models

This paper presents a parallel phoneme recognition algorithm based on the continuous Hidden Markov Model (HMM). The parallel phoneme recognition algorithm distributes 3-state HMMs of context dependent phonemes to the multiprocessors, computes output probabilities in parallel, and enhances the Viterbi beam search with a message passing mechanism. The algorithm is implemented in a multi-transputer system using distributed-memory MIMD multiprocessors. Experimental results show the feasibility of the parallel phoneme recognition algorithm in constructing a real-time parallel speech recognition system based on time-consuming continuous HMM.

Along with the rapid development of autonomous driving technology, autonomous vehicles are showing a trend of practicality and popularity. Autonomous vehicles perceive environmental information through sensors to provide a basis for the decision making of vehicles. Based on this, this paper investigates the lane-changing decision-making behavior of autonomous vehicles. First, the similarity between autonomous vehicles and moving molecules is sought based on a system-similarity analysis. The microscopic lane-changing behavior of vehicles is analyzed by the molecular-dynamics theory. Based on the objective quantification of the lane-changing intention, the interaction potential is further introduced to establish the molecular-dynamics lane-changing model. Second, the relationship between the lane-changing initial time and lane-changing completed time, and the dynamic influencing factors of the lane changing, were systematically analyzed to explore the influence of the microscopic lane-changing behavior on the macroscopic traffic flow. Finally, the SL2015 lane-changing model was compared with the molecular-dynamics lane-changing model using the SUMO platform. SUMO is an open-source and multimodal traffic experimental platform that can realize and evaluate traffic research. The results show that the speed fluctuation of autonomous vehicles under the molecular-dynamics lane-changing model was reduced by 15.45%, and the number of passed vehicles was increased by 5.93%, on average, which means that it has better safety, stability, and efficiency. The molecular-dynamics lane-changing model of autonomous vehicles takes into account the dynamic factors in the traffic scene, and it reasonably shows the characteristics of the lane-changing behavior for autonomous vehicles.

We propose new continuous hidden Markov model (CHMM) structure that integrates feature weighting component. We assume that each feature vector could include different subsets of features that come from different sources of information or different feature extractors. We modify the probability density function that characterizes the standard CHMM to include state and component dependent feature relevance weights. To learn the optimal feature weights from the training data, we modify the maximum likelihood based Baum-Welch algorithm and we derive the necessary conditions. The proposed approach is validated using synthetic and real data sets. The results are shown to outperform the standard CHMM.

A key issue in high-speed automatic driving scenarios, is the recognition of lane change intention of surrounding vehicles. Conventional methods are effective in frequent lane change scenarios. However, considering the variance of individual driving characteristics and measurement uncertainty, false intention recognition remains a major problem to be resolved. We propose an approach to reduce false lane change recognition by introducing the predicted trajectories of the target vehicles. A rule-based approach infers initial lane change intention and a sampling-based approach generates a predicted trajectory according to the inference. Considering the physical inertia, a constant acceleration motion model is used to generate another reference trajectory. The preparatory lane change intention updates in real-time if the predicted trajectory deviates from the reference trajectory. Results demonstrate the approach to improve the lane change intention recognition process.

In spotting for phrases in text images, speed and accuracy are important considerations. In a hidden Markov model (HMM) based spotter recognition time is dominated by the time required to compute the state conditional observation probabilities. These probabilities are a measure of how well the data match each state in the model. In this paper discrete and continuous hidden Markov models are compared based on speed and accuracy in spotting for phrases in text images. For the discrete HMM, vector quantization is used to associate each continuous feature vector with a discrete value. For the continuous HMMs, the observation distributions for the feature vectors are modeled by either a single Gaussian, or a mixture of two Gaussians. Comparisons were made on a subset of the UW English Document Image Database I. The best accuracy was observed when a mixture of two Gaussians was used in the continuous HMM. The discrete HMM provides for faster spotting particularly when long phrases are used.

Multi metric functional connectivity analysis based on continuous hidden Markov model with application in early diagnosis of Alzheimer’s disease

Lane change (LC) behavior has critical effects on traffic flows and safety due to its complex interactions with surrounding vehicles. To ensure safe lane changes and prevent potential crashes, it is important to recognize the potential crash risk of lane change in real time. This study proposes an improved risk estimation (IRE) model to evaluate the potential collision risk of lane change (LCR) vehicle groups. The safety margin is introduced to consider the deceleration capability of vehicles to measure the reaction time of drivers during the LC. Then the IRE model is established, incorporating the collision probability and collision severity measured based on the safety margin. The trajectory data, extracted from the highD dataset, are used and 1536 LC samples are investigated. We compare the LCR under different contextual factors, including vehicle types (cars and trucks), two lane change directions (left and right lane change, LLC and RLC), and traffic flows (low and high traffic). It was found that truck drivers keep higher LCR compared with car drivers due to limited brake capacity, and the left lane change results in higher LCR compared with the right lane change. Additionally, lane change is associated with higher crash risk in high traffic flow, as compared to low traffic flow. The understanding of the crash risk of lane change behavior under different contextual factors, can be useful for real-time crash prediction and devising traffic management strategies.

It is important to diagnose the bearing fault to prevent the serious accident of equipment. This paper introduces a bearing fault identification scheme based on envelope power spectrum analysis, linear discriminate analysis and continuous hidden Markov model. First the envelope power spectrum features are extracted from amplitude demodulated vibration signals from fault bearings. Then, linear discriminate analysis is employed to reduce the feature dimensions, which are helpful for improving the computing speed and diagnosing accuracy. At last, the new linear discriminate analysis features are input into continuous hidden Markov model to train the models under different conditions, respectively. In bearing fault identification, test data are input into the pretrained continuous hidden Markov models, and the bearing state can be detected by the output of continuous hidden Markov model. To validate the effectiveness of the proposed method, experimental samples of four bearing conditions at different fault sizes and loads are utilized to test the continuous hidden Markov model and back-propagation neural network. The result shows that continuous hidden Markov model and linear discriminate analysis-based method have higher accuracy and efficiency than back-propagation neural network.

Accurate identification of lane-changing intention can effectively assist intelligent driving vehicles in terms of decision-making and trajectory planning, which plays a significant role in enhancing driving safety by reducing traffic accidents caused by lane-changing. Based on the trajectory characteristics and vehicle interaction information, an attention-enhanced bidirectional multi-layer residual long-short term memory neural network (Attention Enhanced Residual-MBi-LSTM) model is proposed for lane change intention recognition in this paper. Firstly, an EWMA filter is employed to smooth the noisy data collected from the vehicle. Then a four-layer bidirectional residual LSTM memory (Residual-MBi-LSTM) structure is used to extract lane-changing features from the historical driving trajectories of ego-vehicle and vehicle interaction information. Besides, the attention mechanism is added to adjust the weight of data in different time frames. After that, the current lane-changing probability is calculated and output by the Softmax function. Finally, the vehicle lane-changing intention recognition model is firstly trained and then verified in the HighD dataset. According to the HIL experiment, the proposed model has the ability to identify driver intention on average of 2.07 seconds in advance.