Search results

Feature selection is crucial for machine learning to recognize lane-change (LC) maneuver as there exist a large number of feature candidates. Blindly using feature could take up large storage and excessive computation time, while insufficient feature selection would cause poor performance. Selecting high contributive features to classify LC and lane-keep behavior is effective for maneuver recognition. This paper aims to propose a feature selection method from a statistical view based on an analysis from naturalistic driving data.

In total, 1,375 LC cases are analyzed. To comprehensively select features, the authors extract the feature candidates from both time and frequency domains with various LC scenarios segmented by an occupancy schedule grid. Then the effect size (Cohen’s d) and p-value of every feature are computed to assess their contribution for each scenario.

It has been found that the common lateral features, e.g. yaw rate, lateral acceleration and time-to-lane crossing, are not strong features for recognition of LC maneuver as empirical knowledge. Finally, cross-validation tests are conducted to evaluate model performance using metrics of receiver operating characteristic. Experimental results show that the selected features can achieve better recognition performance than using all the features without purification.

In this paper, the authors investigate the contributions of each feature from the perspective of statistics based on big naturalistic driving data. The aim is to comprehensively figure out different types of features in LC maneuvers and select the most contributive features over various LC scenarios.

This study aims to develop an automatic lane-change mechanism on highways for self-driving articulated trucks to improve traffic safety.

The authors proposed a novel safety lane-change path planning and tracking control method for articulated vehicles. A double-Gaussian distribution was introduced to deduce the lane-change trajectories of tractor and trailer coupling characteristics of intelligent vehicles and roads. With different steering and braking maneuvers, minimum safe distances were modeled and calculated. Considering safety and ergonomics, the authors invested multilevel self-driving modes that serve as the basis of decision-making for vehicle lane-change. Furthermore, a combined controller was designed by feedback linearization and single-point preview optimization to ensure the path tracking and robust stability. Specialized hardware in the loop simulation platform was built to verify the effectiveness of the designed method.

The numerical simulation results demonstrated the path-planning model feasibility and controller-combined decision mechanism effectiveness to self-driving trucks. The proposed trajectory model could provide safety lane-change path planning, and the designed controller could ensure good tracking and robust stability for the closed-loop nonlinear system.

This is a fundamental research of intelligent local path planning and automatic control for articulated vehicles. There are two main contributions: the first is a more quantifiable trajectory model for self-driving articulated vehicles, which provides the opportunity to adapt vehicle and scene changes. The second involves designing a feedback linearization controller, combined with a multi-objective decision-making mode, to improve the comprehensive performance of intelligent vehicles. This study provides a valuable reference to develop advanced driving assistant system and intelligent control systems for self-driving articulated vehicles.

The purpose of this paper is to investigate problems in performing stable lane changes and to find a solution to reduce energy consumption of autonomous electric vehicles.

An optimization algorithm, model predictive control (MPC) and Karush–Kuhn–Tucker (KKT) conditions are adopted to resolve the problems of obtaining optimal lane time, tracking dynamic reference and energy-efficient allocation. In this paper, the dynamic constraints of vehicles during lane change are first established based on the longitudinal and lateral force coupling characteristics and the nominal reference trajectory. Then, by optimizing the lane change time, the yaw rate and lateral acceleration that connect with the lane change time are limed. Furthermore, to assure the dynamic properties of autonomous vehicles, the real system inputs under the restraints are obtained by using the MPC method. Based on the gained inputs and the efficient map of brushless direct-current in-wheel motors (BLDC IWMs), the nonlinear cost function which combines vehicle dynamic and energy consumption is given and the KKT-based method is adopted.

The effectiveness of the proposed control system is verified by numerical simulations. Consequently, the proposed control system can successfully achieve stable trajectory planning, which means that the yaw rate and longitudinal and lateral acceleration of vehicle are within stability boundaries, which accomplishes accurate tracking control and decreases obvious energy consumption.

This paper proposes a solution to simultaneously satisfy stable lane change maneuvering and reduction of energy consumption for autonomous electric vehicles. Different from previous path planning researches in which only the geometric constraints are involved, this paper considers vehicle dynamics, and stability boundaries are established in path planning to ensure the feasibility of the generated reference path.

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.

This study aims to investigate the safety effects of work zone advisory systems. The traditional system includes a dynamic message sign (DMS), whereas the advanced system includes an in-vehicle work zone warning application under the connected vehicle (CV) environment.

A comparative analysis was conducted based on the microsimulation experiments.

The results indicate that the CV-based warning system outperforms the DMS. From this study, the optimal distances of placing a DMS varies according to different traffic conditions. Nevertheless, negative influence of excessive distance DMS placed from the work zone would be more obvious when there is heavier traffic volume. Thus, it is recommended that the optimal distance DMS placed from the work zone should be shortened if there is a traffic congestion. It was also revealed that higher market penetration rate of CVs will lead to safer network under good traffic conditions.

Because this study used only microsimulation, the results do not reflect the real-world drivers’ reactions to DMS and CV warning messages. A series of driving simulator experiments need to be conducted to capture the real driving behaviors so as to investigate the unresolved-related issues. Human machine interface needs be used to simulate the process of in-vehicle warning information delivery. The validation of the simulation model was not conducted because of the data limitation.

It suggests for the optimal DMS placement for improving the overall efficiency and safety under the CV environment.

A traffic network evaluation method considering both efficiency and safety is proposed by applying traffic simulation.

This study aims to propose an enhanced eco-driving strategy based on reinforcement learning (RL) to alleviate the mileage anxiety of electric vehicles (EVs) in the connected environment.

In this paper, an enhanced eco-driving control strategy based on an advanced RL algorithm in hybrid action space (EEDC-HRL) is proposed for connected EVs. The EEDC-HRL simultaneously controls longitudinal velocity and lateral lane-changing maneuvers to achieve more potential eco-driving. Moreover, this study redesigns an all-purpose and efficient-training reward function with the aim to achieve energy-saving on the premise of ensuring other driving performance.

To illustrate the performance for the EEDC-HRL, the controlled EV was trained and tested in various traffic flow states. The experimental results demonstrate that the proposed technique can effectively improve energy efficiency, without sacrificing travel efficiency, comfort, safety and lane-changing performance in different traffic flow states.

In light of the aforementioned discussion, the contributions of this paper are two-fold. An enhanced eco-driving strategy based an advanced RL algorithm in hybrid action space (EEDC-HRL) is proposed to jointly optimize longitudinal velocity and lateral lane-changing for connected EVs. A full-scale reward function consisting of multiple sub-rewards with a safety control constraint is redesigned to achieve eco-driving while ensuring other driving performance.

The paper considers the application of neural networks to model driver decisions to change lane on a dual carriageway road. The lane changing process is treated as consisting of two decisions, namely motivation and opportunity. Separate backpropagation neural networks are applied to represent each of the two decisions. The trained motivation and opportunity neural network models are linked to produce a layered network which represents the complete lane changing process. Separate models are developed to represent the nearside to offside lane changing decision, and the offside to nearside lane changing decision. This paper describes the development of the model of the nearside to offside lane changing decision.

For model development, data were collected from several subject vehicle drivers. The results are presented and the implications considered. Selected data were applied to train the neural networks and then an independent subset of data were used to assess performance. When the complete nearside lane changing neural network model was presented with the unseen test examples, 93.3% of the examples were correctly predicted as a lane change or no lane change. These results are shown to be a considerable improvement on those obtained previously.

Freeway work zones have been traffic bottlenecks that lead to a series of problems, including long travel time, high-speed variation, driver’s dissatisfaction and traffic congestion. This research aims to develop a collaborative component of connected and automated vehicles (CAVs) to alleviate negative effects caused by work zones.

The proposed cooperative component is incorporated in a cellular automata model to examine how and to what scale CAVs can help in improving traffic operations.

Simulation results show that, with the proposed component and penetration of CAVs, the average performances (travel time, safety and emission) can all be improved and the stochasticity of performances will be minimized too.

To the best of the authors’ knowledge, this is the first research that develops a cooperative mechanism of CAVs to improve work zone performance.

The purpose of this paper is to reflect on what it means to be an academic in contemporary times and particularly how the value associated with being a researcher has changed in currency over time.

Based on Cavarerro's work about stories of the narrated self, in which revealing self narratives are viewed as a vehicle for uncovering (self) identities, this paper reveals the pitfalls associated with trying to change focus and direction and attempts to reinvent oneself in times that are characterized by a return to the essentially conservative conventions of educational research. Neo‐liberal, market driven, utilitarian models of education dominate the contemporary research landscape. What constitutes evidence is under debate. How evidence is obtained and analysed is subject to traditional definitions which may not have direct relevance to contemporary phenomena in post‐modern times. Those in positions of power reduce performance to minutiae and constantly want prescriptive teaching to produce observable outcomes. Yet, is this possible in environs that are formed by individuals in a multiplicity of contexts, cultures and locations? What does this mean for research which focuses not only on the lived experiences in classroom but the recognition that no two classrooms are the same and the quest for the identification of a “good teacher” is like that of the holy grail?

This paper reveals the pitfalls associated with trying to change focus and direction in academic research. The author has reinterpreted the driving procedure – look in the mirror, indicate and then (if it is clear) move – in her career to being reflective and reflexive about where she has come from, signaling that she wants to change or shift her position and then attempting to make the move. This process of change is continuing and not always continuous.

The article reflects a personal story that is intended to resonate with audiences experiencing similar contexts in contemporary academic life.