Search results

For autonomous vehicles, trajectory prediction of surrounding vehicles is beneficial to improving the situational awareness of dynamic and stochastic traffic environments, which is a crucial and indispensable element to realize highly automated driving.

In this paper, the overall framework consists of two parts: first, a novel driver characteristic and intention estimation (DCIE) model is built to indicate the higher-level information of the vehicle using its low-level motion variables; then, according to the estimation results of the DCIE model, a classified Gaussian process model is established for probabilistic vehicle trajectory prediction under different motion patterns.

The whole method is later applied and analyzed in the highway lane-change scenarios with the parameters of models learned from the public naturalistic driving data set. Compared with other traditional methods, the performance of this proposed approach is proved superior, demonstrated by the higher accuracy in the long prediction horizon and a more reasonable description of uncertainty.

This hierarchical approach is proposed to make trajectory prediction accurately both in the short term and long term, which can also deal with the uncertainties caused by the perception system or indeterminate vehicle behaviors.

This paper aims to predict the behaviour of the vehicles in a mixed driving scenario. This proposes a deep learning model to predict lane-changing scenarios in highways incorporating current and historical information and contextual features. The interactions among the vehicles are modelled using long-short-term memory (LSTM).

Predicting the surrounding vehicles' behaviour is crucial in any Advanced Driver Assistance Systems (ADAS). To make a decision, any prediction models available in the literature consider the present and previous observations of the surrounding vehicles. These existing models failed to consider the contextual features such as traffic density that also affect the behaviour of the vehicles. To forecast the appropriate driving behaviour, a better context-aware learning method should be able to consider a distinct goal for each situation is more significant. Considering this, a deep learning-based model is proposed to predict the lane changing behaviours using past and current information of the vehicle and contextual features. The interactions among vehicles are modeled using an LSTM encoder-decoder. The different lane-changing behaviours of the vehicles are predicted and validated with the benchmarked data set NGSIM and the open data set Level 5.

The lane change behaviour prediction in ADAS is gaining popularity as it is crucial for safe travel in a mixed driving environment. This paper shows the prediction of maneuvers with a prediction window of 5 s using NGSIM and Level 5 data sets. The proposed method gives a prediction accuracy of 97% on average for all lane-change maneuvers for both the data sets.

This research presents a strategy for predicting autonomous vehicle behaviour based on contextual features. The paper focuses on deep learning techniques to assist the ADAS.

There is a certain error in the satellite positioning of the vehicle. The error will cause the drift point of the positioning point, which makes the vehicle trajectory shift to the real road. This paper aims to solve this problem.

The key technology to solve the problem is map matching (MM). The low sampling frequency of the vehicle is far from the distance between adjacent points, which weakens the correlation between the points, making MM more difficult. In this paper, an MM algorithm based on priority rules is designed for vehicle trajectory characteristics at low sampling frequencies.

The experimental results show that the MM based on priority rule algorithm can effectively match the trajectory data of low sampling frequency with the actual road, and the matching accuracy is better than other similar algorithms, the processing speed reaches 73 per second.

In the algorithm verification of this paper, although the algorithm design and experimental verification are considered considering the diversity of GPS data sampling frequency, the experimental data used are still a single source.

Based on the GPS trajectory data of the Ministry of Transport, the experimental results show that the accuracy of the priority-based weight-based algorithm is higher. The accuracy of this algorithm is over 98.1 per cent, which is better than other similar algorithms.

Motivated by a problem in the context of DiDi Travel, the biggest taxi hailing platform in China, the purpose of this paper is to propose a novel facility location problem, specifically, the single source capacitated facility location problem with regional demand and time constraints, to help improve overall transportation efficiency and cost.

This study develops a mathematical programming model, considering regional demand and time constraints. A novel two-stage neighborhood search heuristic algorithm is proposed and applied to solve instances based on data sets published by DiDi Travel.

The results of this study show that the model is adequate since new characteristics of demand can be deduced from large vehicle trajectory data sets. The proposed algorithm is effective and efficient on small and medium as well as large instances. The research also solves and presents a real instance in the urban area of Chengdu, China, with up to 30 facilities and demand deduced from 16m taxi trajectory data records covering around 16,000 drivers.

This study examines an offline and single-period case of the problem. It does not consider multi-period or online cases with uncertainties, where decision makers need to dynamically remove out-of-service stations and add other stations to the selected group.

Prior studies have been quite limited. They have not yet considered demand in the form of vehicle trajectory data in facility location problems. This study takes into account new characteristics of demand, regional and time constrained, and proposes a new variant and its solution approach.

Precise vehicle localization is a basic and critical technique for various intelligent transportation system (ITS) applications. It also needs to adapt to the complex road environments in real-time. The global positioning system and the strap-down inertial navigation system are two common techniques in the field of vehicle localization. However, the localization accuracy, reliability and real-time performance of these two techniques can not satisfy the requirement of some critical ITS applications such as collision avoiding, vision enhancement and automatic parking. Aiming at the problems above, this paper aims to propose a precise vehicle ego-localization method based on image matching.

This study included three steps, Step 1, extraction of feature points. After getting the image, the local features in the pavement images were extracted using an improved speeded up robust features algorithm. Step 2, eliminate mismatch points. Using a random sample consensus algorithm to eliminate mismatched points of road image and make match point pairs more robust. Step 3, matching of feature points and trajectory generation.

Through the matching and validation of the extracted local feature points, the relative translation and rotation offsets between two consecutive pavement images were calculated, eventually, the trajectory of the vehicle was generated.

The experimental results show that the studied algorithm has an accuracy at decimeter-level and it fully meets the demand of the lane-level positioning in some critical ITS applications.

The purpose of this paper is to characterize distracted driving by quantifying the response time and response intensity to an emergency stop using the driver’s physiological states.

Field tests with 17 participants were conducted in the connected and automated vehicle test field. All participants were required to prioritize their primary driving tasks while a secondary nondriving task was asked to be executed. Demographic data, vehicle trajectory data and various physiological data were recorded through a biosignalsplux signal data acquisition toolkit, such as electrocardiograph for heart rate, electromyography for muscle strength, electrodermal activity for skin conductance and force-sensing resistor for braking pressure.

This study quantified the psychophysiological responses of the driver who returns to the primary driving task from the secondary nondriving task when an emergency occurs. The results provided a prototype analysis of the time required for making a decision in the context of advanced driver assistance systems or for rebuilding the situational awareness in future automated vehicles when a driver’s take-over maneuver is needed.

The hypothesis is that the secondary task will result in a higher mental workload and a prolonged reaction time. Therefore, the driver states in distracted driving are significantly different than in regular driving, the physiological signal improves measuring the brake response time and distraction levels and brake intensity can be expressed as functions of driver demographics. To the best of the authors’ knowledge, this is the first study using psychophysiological measures to quantify a driver’s response to an emergency stop during distracted driving.

Time headway (THW) is an essential parameter in traffic safety and is used as a typical control variable by many vehicle control algorithms, especially in safety-critical ADAS and automated driving systems. However, due to the randomness of human drivers, THW cannot be accurately represented, affecting scholars’ more profound research.

In this work, two data sets are used as the experimental data to calculate the goodness-of-fit of 18 commonly used distribution models of THW to select the best distribution model. Subsequently, the characteristic parameters of traffic flow are extracted from the data set, and three variables with higher importance are extracted using the random forest model. Combining the best distribution model parameters of the data set, this study obtained a distribution model with adaptive parameters, and its performance and applicability are verified.

In this work, two data sets are used as the experimental data to calculate the goodness-of-fit of 18 commonly used distribution models of THW to select the best distribution model. Subsequently, the characteristic parameters of traffic flow are extracted from the data set, and three variables with higher importance are extracted using the random forest model. Combining the best distribution model parameters of the data set, this study obtained a distribution model with adaptive parameters, and its performance and applicability are verified.

The results show that the proposed model has a 62.7% performance improvement over the distribution model with fixed parameters. Moreover, the parameter function of the distribution model can be regarded as a quantitative analysis of the degree of influence of the traffic flow state on THW.

An individual’s driving style significantly affects overall traffic safety. However, driving style is difficult to identify due to temporal and spatial differences and scene heterogeneity of driving behavior data. As such, the study of real-time driving-style identification methods is of great significance for formulating personalized driving strategies, improving traffic safety and reducing fuel consumption. This study aims to establish a driving style recognition framework based on longitudinal driving operation conditions (DOCs) using a machine learning model and natural driving data collected by a vehicle equipped with an advanced driving assistance system (ADAS).

Specifically, a driving style recognition framework based on longitudinal DOCs was established. To train the model, a real-world driving experiment was conducted. First, the driving styles of 44 drivers were preliminarily identified through natural driving data and video data; drivers were categorized through a subjective evaluation as conservative, moderate or aggressive. Then, based on the ADAS driving data, a criterion for extracting longitudinal DOCs was developed. Third, taking the ADAS data from 47 Kms of the two test expressways as the research object, six DOCs were calibrated and the characteristic data sets of the different DOCs were extracted and constructed. Finally, four machine learning classification (MLC) models were used to classify and predict driving style based on the natural driving data.

The results showed that six longitudinal DOCs were calibrated according to the proposed calibration criterion. Cautious drivers undertook the largest proportion of the free cruise condition (FCC), while aggressive drivers primarily undertook the FCC, following steady condition and relative approximation condition. Compared with cautious and moderate drivers, aggressive drivers adopted a smaller time headway (THW) and distance headway (DHW). THW, time-to-collision (TTC) and DHW showed highly significant differences in driving style identification, while longitudinal acceleration (LA) showed no significant difference in driving style identification. Speed and TTC showed no significant difference between moderate and aggressive drivers. In consideration of the cross-validation results and model prediction results, the overall hierarchical prediction performance ranking of the four studied machine learning models under the current sample data set was extreme gradient boosting > multi-layer perceptron > logistic regression > support vector machine.

The contribution of this research is to propose a criterion and solution for using longitudinal driving behavior data to label longitudinal DOCs and rapidly identify driving styles based on those DOCs and MLC models. This study provides a reference for real-time online driving style identification in vehicles equipped with onboard data acquisition equipment, such as ADAS.

Purpose – This chapter provides details of research that attempts to relate traffic operational conditions on uninterrupted flow facilities (e.g., freeways and expressways) with real-time crash likelihood. Unlike incident detection, the purpose of this line of work is to proactively assess crash likelihood and potentially reduce the likelihood through proactive traffic management techniques, including variable speed limit and ramp metering among others.

Methodology – The chapter distinguishes between the traditional aggregate crash frequency-based approach to safety evaluation and the approach needed for real-time crash risk estimation. Key references from the literature are summarised in terms of the reported effect of different traffic characteristics that can be derived in near real-time, including average speed, temporal variation in speed, volume and lane-occupancy, on crash occurrence.

Findings – Traffic and weather parameters are among the real-time crash-contributing factors. Among the most significant traffic parameters is speed particularly in the form of coefficient of variation of speed.

Research implications – In the traffic safety field, traditional data sources are infrastructure-based traffic detection systems. In the future, if automatic traffic detection systems could provide reliable data at the vehicle level, new variables such as headway could be introduced. Transferability of real-time crash prediction models is also of interest. Also, the potential effects of different management strategies to reduce real-time crash risk could be evaluated in a simulation environment.

Practical implications – This line of research has been at the forefront of bringing data mining and other machine-learning techniques into the traffic management arena. We expect these analysis techniques to play a more important role in real-time traffic management, not just for safety evaluation but also for congestion pricing and alternate routing.

The expected benefits of newly developed transportation infrastructures are the saving of travel time and further promoted transport economics. There is a need for a methodology of travel time estimation with acceptable robustness and practicability. Macroscopic fundamental diagram (MFD) represents the overall traffic performance at a network level by linking average flow, speed and density. MFD can be used to estimate network state and to describe various traffic management strategies. This study aims to describe the effect of new infrastructure development on the network performance using the MFD framework.

The scenarios of Islamabad Road network before and after the infrastructure construction were simulated, in which the floating car data set (FCD) for multiple modes was extracted. MFD has been formed for the whole region and partitioned region, which was divided on the basis of infrastructural changes. Moreover, this study has been extended to calculate travel time for multiple modes using the MFD results and the Bureau of Public Roads (BPR) function at a neighborhood level.

MFD results for the whole network showed that the speed of traffic improves after the construction of new infrastructure. The travel time estimates using MFD results were dependent on the speed estimates, whereas the estimates obtained using the BPR function were found to be dependent on the traffic volume variation during different intervals of the day. By using the FCD for multiple modes, travel time estimates for multiple modes were obtained. The BPR function method was found valid for estimating travel time of traffic stream only.

This paper innovatively investigates the change in network performance for pre-construction and post-construction scenarios using the MFD framework. In practice, the approach presented can be used by transportation agencies to evaluate the effect of different traffic management strategies and infrastructural changes.