Traffic lights optimization is one of the principal components to lessen the traffic flow and travel time in an urban area. The present article seeks to introduce a novel procedure to design the traffic lights in a city using evolutionary-based optimization algorithms in combination with an ontology-based driving behavior simulation framework. Accordingly, an ontology-based knowledge base is introduced to provide a machine-understandable knowledge of roads and intersections, traffic rules, and driving behaviors. Then, a simulation environment is developed to inspect car behavior in real time. To optimize the traffic lights, a sine-based equation was defined for each traffic light, and the total travel time of the vehicles was considered as the cost function in the optimization algorithm. The optimization was performed with 5, 10, 15, 20, 25, and 30 vehicles in the urban areas. Based on the results, in contrast to uncontrolled intersections without traffic lights, optimized traffic lights can significantly contribute to total travel time-saving. To conclude, due to an escalation in the number of vehicles, the significance of optimized traffic lights has encountered an increase, and unoptimized traffic lights could increase total travel time even more than a city deprived of any traffic light.

As Intelligent Transport Systems (ITS) advances, more and more people will have the opportunities to drive vehicles with autonomous capabilities. This rise in number of semi-autonomous vehicles also gives rise to several challenges with regards on how human factors come into play in interacting with the vehicle's Automated Driving System (ADS). One important interaction of an ADS with Level 3 Conditional Automated Driving capabilities is Request-to-Intervene (RTI), which alerts drivers to takeover the vehicle during an automated driving session, however, the driver is not necessarily ready to receive the authority. To see whether an ADS can detect the readiness of the user for RTI, in this preliminary study we evaluated the mental states of ADS users in naturalistic driving conditions by comparing them with those of drivers and passengers. The mental states were evaluated by measuring their heart rate and by calculating specific features of Heart Rate Variability (HRV), specifically NN50 and pNN50 indices, during driving events (turning, lane changing, and stopping) and no-events. The results showed the NN50 and pNN50 values of manual driving were significantly different from those of ADS driving and passenger, suggesting that ADS driving has a higher level of relaxed state. In addition, events such as lane-changing in the ADS driving did not induce significantly different NN50 and pNN50 from nonevent situation, which may imply the participants did not pay attention to such events.

An autonomous drive system for a vehicle includes at least one environment perception sensor, a perception module, a location module, an intention prediction module, and a control module. The perception module is configured to receive signals from the at least one environment perception sensor and detect and track at least two remote vehicles in one or both of a current lane and a neighboring lane. The location module is configured to determine a location of the vehicle. The intention prediction module is configured to generate predicted trajectories for the at least two remote vehicles. The control module is configured to receive signals from the at least one environment perception sensor and receive the predicted trajectories from the intention prediction module. The control module determines a location and time for a lane change based on the predicted trajectories and controls the vehicle to change lanes at the determined location and time.

Fog computing has been advocated as an enabling technology for computationally intensive services in connected smart vehicles. Most existing works focus on analyzing and optimizing the queueing and workload processing latencies, ignoring the fact that the access latency between vehicles and fog/cloud servers can sometimes dominate the end-to-end service latency. This motivates the work in this paper, where we report a five-month urban measurement study of the wireless access latency between a connected vehicle and a fog computing system supported by commercially available multi-operator LTE networks. We propose AdaptiveFog, a novel framework for autonomous and dynamic switching between different LTE operators that implement fog/cloud infrastructure. The main objective here is to maximize the service confidence level, defined as the probability that the tolerable latency threshold for each supported type of service can be guaranteed. AdaptiveFog has been implemented on a smart phone app, running on a moving vehicle. The app periodically measures the round-trip time between the vehicle and fog/cloud servers. An empirical spatial statistic model is established to characterize the spatial variation of the latency across the main driving routes of the city. To quantify the performance difference between different LTE networks, we introduce the weighted Kantorovich-Rubinstein (K-R) distance. An optimal policy is derived for the vehicle to dynamically switch between LTE operators’ networks while driving. Extensive analysis and simulation are performed based on our latency measurement dataset. Our results show that AdaptiveFog achieves around 30% and 50% improvement in the confidence level of fog and cloud latency, respectively.

Driving is a complex task that requires the perception of the surrounding environment, decision making and control of the vehicle. Human drivers predict how surrounding objects move and decide an appropriate driving behavior. As with human drivers, autonomous driving vehicles should consider the condition of the surrounding environment and behave naturally so as not to disturb the traffic flow. We propose a reward function for learning how natural the driving is based on the hypothesis that the movement of surrounding vehicles becomes unpredictable when the ego vehicle takes an unnatural driving behavior. The reward function is based on the prediction error of a deep predictive network that models the transition of the surrounding environment. Occupancy grid image is used to perceive the surrounding environment and the predictions up to two seconds are used to calculate the reward function. We evaluated the reward function using both simulated and the real world data. We trained the prediction network using real driving data and trained a reinforcement learning agent based on the reward function. Then we compared the speed planned by the agent and a human driver, which showed a correlation of 0.52. We also confirmed the benefit of taking prediction into account by observing the behavior of the agent in a specific traffic scenario.

Low latency is required for connected and intelligent vehicle applications. For instance, safety applications have strict latency requirements. Mobile edge computing (MEC) improves the latency by bringing the computational resources closer to the data source. However, despite the improvements in latency by MEC, the latency will vary based on traffic load and signal conditions. We seek to answer the question: is the current latency environment acceptable for our application? This paper presents our Reliable Latency Decision (ReLaDec) algorithm. ReLaDec uses prior information and the last latency samples to decide whether the latency will be acceptable to our application. The decisions are done with predictable confidence and with ReLaDec the false positive decision rate never exceeds the set maximum value. We demonstrate the performance of the algorithm using 860000 latency samples that include stationary and driving data over multiple USA states.

Data representing driving behavior, as measured by various sensors installed in a vehicle, are collected as multi-dimensional sensor time-series data. These data often include redundant information, e.g., both the speed of wheels and the engine speed represent the velocity of the vehicle. Redundant information can be expected to complicate the data analysis, e.g., more factors need to be analyzed; even varying the levels of redundancy can influence the results of the analysis. We assume that the measured multi-dimensional sensor time-series data of driving behavior are generated from low-dimensional data shared by the many types of one-dimensional data of which multi-dimensional time-series data are composed. Meanwhile, sensor time-series data may be defective because of sensor failure. Therefore, another important function is to reduce the negative effect of defective data when extracting low-dimensional time-series data. This study proposes a defect-repairable feature extraction method based on a deep sparse autoencoder (DSAE) to extract low-dimensional time-series data. In the experiments, we show that DSAE provides high-performance latent feature extraction for driving behavior, even for defective sensor time-series data. In addition, we show that the negative effect of defects on the driving behavior segmentation task could be reduced using the latent features extracted by DSAE.

A promise of mobile edge computing (MEC) is improved communication latency. In particular, vehicular safety applications have strict latency requirements. Despite the improvements in latency by MEC, the latency will vary based on traffic load and signal conditions. We seek models that will help us answer the question: is the latency environment acceptable for our application? To this end, we collected 619 hours of pings over an LTE network and we evaluated 13 possible models. Our results show that when modeling the whole distribution, a mixture model of LogNormal distributions works best. When the emphasis is on the tail of the distribution, the double Pareto LogNormal distribution should be used. Finally, when only the tail needs to be modeled, then the generalized Pareto distribution should be used.

A system and method are provided and include a subject vehicle having vehicle actuation systems. A driving context database stores driving trends associated with driving locations. A state estimation module determines a current location of the subject vehicle. A global route planner module determines a route to an inputted destination. An action primitive planning module retrieves a driving trend associated with the current location, selects a sequence of action primitives based on the driving trend associated with the current location and based on the determined route, and generates waypoints for the subject vehicle to travel to based on the sequence of action primitives, each waypoint including location coordinates and a direction. A trajectory planner module determines a trajectory for the subject vehicle based on the waypoints. A vehicle control module controls the vehicle actuation systems based on the determined trajectory.

In this paper, we propose a visualization method for driving behavior that helps people to recognize distinctive driving behavior patterns in continuous driving behavior data. Driving behavior can be measured using various types of sensors connected to a control area network. The measured multi-dimensional time series data are called driving behavior data. In many cases, each dimension of the time series data is not independent of each other in a statistical sense. For example, accelerator opening rate and longitudinal acceleration are mutually dependent. We hypothesize that only a small number of hidden features that are essential for driving behavior are generating the multivariate driving behavior data. Thus, extracting essential hidden features from measured redundant driving behavior data is a problem to be solved to develop an effective visualization method for driving behavior. In this paper, we propose using deep sparse autoencoder (DSAE) to extract hidden features for visualization of driving behavior. Based on the DSAE, we propose a visualization method called a driving color map by mapping the extracted 3-D hidden feature to the red green blue (RGB) color space. A driving color map is produced by placing the colors in the corresponding positions on the map. The subjective experiment shows that feature extraction method based on the DSAE is effective for visualization. In addition, its performance is also evaluated numerically by using pattern recognition method. We also provide examples of applications that use driving color maps in practical problems. In summary, it is shown the driving color map based on DSAE facilitates better visualization of driving behavior.

Prediction of driving behavior is important in safer advanced driving assistance systems to prevent potential risk of traffic accidents. To predict the driving behavior, driving style, i.e., the difference of tendency of driving behavior for each driver, is also important. We propose a prediction method for time-series driving behavior based on the driving style. The proposed method consists of a sequence-to-sequence (S2S) model and embeds driver information considering with the driving style into S2S model in order to improve prediction performance. We evaluated efficiency of the proposed method by two experiments using actual driving behavior data on a test track. We found that the proposed method could predict driving behavior better than comparative methods. We also found that the proposed method could change the driving style from one driver to another driver by changing driver information input to the proposed model.

To develop a new generation advanced driver assistance system that avoids a dangerous condition in advance, we need to predict driving behaviors. Since a nonparametric Bayesian method with a two-level structure successfully predicted the symbolized behaviors only, we applied a nonparametric Bayesian method with linear dynamical systems to predicting the driving behavior. The method called the beta process autoregressive hidden Markov model (BP-AR-HMM) segments driving behaviors into states each of which corresponds to an AR model and it predicts future behaviors using the estimated future state sequence and the dynamical systems therein. Here, the segmentation as well as the parameters of the dynamical systems are determined using given training data in an unsupervised way. We carried out experiments with real driving data and found that the BP-AR-HMM predicted driving behaviors better than other methods.

Analyzing driving behavior data is essential for developing driver assistance systems. Statistical segmentation is one of the important methods to realize the analysis. Driving behavior data actually include undesirable defects caused by external environment and sensor failures. Defects in the data cause a huge negative effect on the segmentation. In this paper, we showed that a feature extraction method based on a deep sparse autoencoder with fixed point (DSAE-FP) could reduce the negative effect of defective data in a driving behavior segmentation task. In the experiments, we used sticky hierarchical Dirichlet process hidden Markov model to segment the driving behavior. We compared the segmentation results using hidden features extracted by DSAE-FP and other comparative methods. Experimental results showed that segmentation results of non-defective dataset and defective dataset turned out most similar when DSAE-FP was used.

This study describes driving word2vec (DW2V), a new method for forming semantic representations of naturalistic driving data (NDD). To use big NDD for developing driver assistance systems or other information services, it is important to compress large amounts of data into an abstract and compact representation without losing semantic information. For this purpose, this study uses a symbolization method using a double articulation analyzer (DAA) assuming that NDD and human speech signals share an analogous structure, called a double articulation structure. The DAA can encode driving behavior data into sequences of driving words. However, the amount of semantic information contained in these sequences has not been clarified. Very few attempts have been made to develop a method for obtaining an adequate semantic representation of driving words that explains the relationship between different driving words. DW2V uses word2vec, proposed by Mikolov et al., to make a system learn the distributed semantic vector representation of symbolized naturalistic driving data (SNDD). Through experiments, we show that DW2V can restore the semantic relationships between different driving scenes from only a set of sequences of driving words, i.e., SNDD. In addition to quantitative analysis, a qualitative analysis of DW2V and its potential applications are discussed.

A sequence prediction method for driving behavior data is proposed in this paper. The proposed method can predict a longer latent state sequence of driving behavior data than conventional sequence prediction methods. The proposed method is derived by focusing on the double articulation structure latently embedded in driving behavior data. The double articulation structure is a two-layer hierarchical structure originally found in spoken language, i.e., a sentence is a sequence of words and a word is a sequence of letters. Analogously, we assume that driving behavior data comprise a sequence of driving words and a driving word is a sequence of driving letters. The sequence prediction method is obtained by extending a nonparametric Bayesian unsupervised morphological analyzer using a nested Pitman-Yor language model (NPYLM), which was originally proposed in the natural language processing field. This extension allows the proposed method to analyze incomplete sequences of latent states of driving behavior and to predict subsequent latent states on the basis of a maximum a posteriori criterion. The extension requires a marginalization technique over an infinite number of possible driving words. We derived such a technique on the basis of several characteristics of the NPYLM. We evaluated this proposed sequence prediction method using three types of data: 1) synthetic data; 2) data from test drives around a driving course at a factory; and 3) data from drives on a public thoroughfare. The results showed that the proposed method made better long-term predictions than did the previous methods.

An unsupervised learning method, called double articulation analyzer with temporal prediction (DAA-TP), is proposed on the basis of the original DAA model. The method will enable future advanced driving assistance systems to determine driving context and predict possible scenarios of driving behavior by segmenting and modeling incoming driving-behavior time series data. In previous studies, we applied the DAA model to driving-behavior data and argued that contextual changing points can be estimated as changing points of chunks. A sequence prediction method, which predicts the next hidden state sequence, was also proposed in a previous study. However, the original DAA model does not model the duration of chunks of driving behavior and is not able to do a temporal prediction of the scenarios. Our DAA-TP method explicitly models the duration of chunks of driving behavior on the assumption that driving-behavior data have a two-layered hierarchical structure, i.e., double articulation structure. For this purpose, the hierarchical Dirichlet process hidden semi-Markov model is used for explicitly modeling the duration of segments of driving-behavior data. A Poisson distribution is also used to model the duration distribution of driving-behavior segments. The duration distribution of chunks of driving-behavior data is also theoretically calculated using the reproductive property of the Poisson distribution. We also propose a calculation method for obtaining the probability distribution of the remaining duration of current driving words as a mixture of Poisson distribution with a theoretical approximation for unobserved driving words. This method can calculate the posterior probability distribution of the next termination time of chunks by explicitly modeling all probable chunking results for observed data. The DAA-TP was applied to a synthetic data set having a double articulation structure to evaluate its model consistency. To evaluate the effectiveness of DAA-TP, we applied it to a driving-behavior data set recorded at actual factory circuits. The DAA-TP could predict the next termination time of chunks more accurately than the compared methods. We also report the qualitative results for understanding the potential capability of DAA-TP.

We propose a classification method based on a binary Gaussian process classifier to classify novice and experienced drivers using eye gaze that can reflect drivers' attention and skill. Gaze behavior during lane changing task were collected from both novice drivers and experienced drivers by using an eye tracking system and a driving simulator in this study. We applied the Gaussian process classifier to the two-dimensional coordination data of the gaze behavior, and compared the performance of Gaussian process classifier with those of Gaussian mixture models that had the different number of components. Our proposed method showed the superiority in classification performance to the methods based on the Gaussian mixture models.

We investigate a possible method for detecting a driver's negative adaptation to an automated driving system by analyzing consistency of driver decision making and driver gaze behavior during automated driving. We focus on an automated driving system equivalent to Level 2 automation per the NHTSA's definition. At this level of automation, drivers must be ready to take control of the vehicle in critical situations by monitoring the driving environment and vehicle behavior. Since drivers are not required to operate the pedals or steering wheel during automated driving, a driver's negative adaptation to an automated system needs to be detected from behavior other than vehicle operation. In this study, we focus on driver gaze behavior. We conduct a simulator study to compare the gaze behavior of fifteen drivers during conventional and automated driving. We also analyze the consistency of driver decision making when changing lanes during conventional and automated driving. Experimental results show that drivers who pay less attention to the road ahead during automated driving tend to be less sensitive to risk factors in the surrounding environment and also tend to make inconsistent lane change decisions during automated driving.