Open access articleCurrently autonomous or self-driving vehicles are at the heart of academia and industry\ud research because of its multi-faceted advantages that includes improved safety, reduced congestion,lower emissions and greater mobility. Software is the key driving factor underpinning autonomy within which planning algorithms that are responsible for mission-critical decision making hold a significant position. While transporting passengers or goods from a given origin to a given destination, motion planning methods incorporate searching for a path to follow, avoiding obstacles and generating the best trajectory that ensures safety, comfort and efficiency. A range of different planning approaches have been proposed in the literature.\ud The purpose of this paper is to review existing approaches and then compare and contrast different methods employed for the motion planning of autonomous on-road driving that consists of (1) finding a path, (2) searching for the safest manoeuvre and (3) determining the most feasible trajectory. Methods developed by researchers in each of these three levels exhibit varying levels of complexity and performance accuracy. This paper presents a critical evaluation of each of these methods, in terms of their advantages/disadvantages, inherent limitations, feasibility, optimality, handling of obstacles and testing operational environments. Based on a critical review of existing methods, research challenges to address current limitations are identified and future research directions are suggested so as to enhance the performance of planning algorithms at all three levels. Some promising areas of future focus have been identified as the use of vehicular communications (V2V and V2I) and the incorporation of transport engineering aspects in order to improve the look-ahead horizon of current sensing\ud technologies that are essential for planning with the aim of reducing the total cost of\ud driverless vehicles. This critical review on planning techniques presented in this paper, along with the associated discussions on their constraints and limitations, seek to assist researchers in accelerating development in the emerging field of autonomous vehicle research

Real-time risk assessment of autonomous driving at tactical and operational levels is extremely challenging since both contextual and circumferential factors should concurrently be considered. Recent methods have started to simultaneously treat the context of the traffic environment along with vehicle dynamics. In particular, interaction-aware motion models that take inter-vehicle dependencies into account by utilizing the Bayesian interference are employed to mutually control multiple factors. However, communications between vehicles are often assumed and the developed models are required many parameters to be tuned. Consequently, they are computationally very demanding. Even in the cases where these desiderata are fulfilled, current approaches cannot cope with a large volume of sequential data from organically changing traffic scenarios, especially in highly complex operational environments such as dense urban areas with heterogeneous road users. To overcome these limitations, this paper develops a new risk assessment methodology that integrates a network-level collision estimate with a vehicle-based risk estimate in real-time under the joint framework of interaction-aware motion models and Dynamic Bayesian Networks (DBN). Following the formulation and explanation of the required functions, machine learning classifiers were utilized for the real-time network-level collision prediction and the results were then incorporated into the integrated DBN model for predicting collision probabilities in real-time. Results indicated an enhancement of the interaction-aware model by up to 10%, when traffic conditions are deemed as collision-prone. Hence, it was concluded that a well-calibrated collision prediction classifier provides a crucial hint for better risk perception by autonomous vehicles.

Highway safety has attracted significant research interest in recent years, especially as innovative technologies such as connected and autonomous vehicles (CAVs) are fast becoming a reality. Identification and prediction of driving intention are fundamental for avoiding collisions as it can provide useful information to drivers and vehicles in their vicinity. However, the state-of-the-art in maneuver prediction requires the utilization of large labeled datasets, which demand a significant amount of processing and might hinder real-time applications. In this paper, an end-to-end machine learning model for predicting lane-change maneuvers from unlabeled data using a limited number of features is developed and presented. The model is built on a novel comprehensive dataset (i.e., highD) obtained from German highways with camera-equipped drones. Density-based clustering is used to identify lane-changing and lane-keeping maneuvers and a support vector machine (SVM) model is then trained to learn the boundaries of the clustered labels and automatically label the new raw data. The labeled data are then input to a long short-term memory (LSTM) model which is used to predict maneuver class. The classification results show that lane changes can efficiently be predicted in real-time, with an average detection time of at least 3 s with a small percentage of false alarms. The utilization of unlabeled data and vehicle characteristics as features increases the prospects of transferability of the approach and its practical application for highway safety.

Current approaches to estimate the probability of a traffic collision occurring in real-time primarily depend on comparing traffic conditions just prior to collisions with normal traffic conditions. Most studies acquire pre-collision traffic conditions by matching the collision time in the national crash database with the time in the traffic database. Since the reported collision time sometimes differs from the actual time, the matching method may result in traffic conditions not representative of pre-collision traffic dynamics. In this paper, this is overcome through the use of highly disaggregated vehicle-based traffic data from a traffic micro-simulation (i.e., VISSIM) and the corresponding traffic conflicts data generated by the surrogate safety assessment model (SSAM). In particular, the idea is to use traffic conflicts as surrogate measures of traffic safety so that traffic collisions data are not needed. Three classifiers (i.e., support vector machines, k-nearest neighbours, and random forests) are then employed to examine the proposed idea. Substantial efforts are devoted to making the traffic simulation as representative of the real-world as possible by employing data from a motorway section in England. Four temporally aggregated traffic datasets (i.e., 30 s, 1 min, 3 min, and 5 min) are examined. The main results demonstrate the viability of using traffic micro-simulation along with the SSAM for real-time conflicts prediction and the superiority of random forests with 5-min temporal aggregation in the classification results. However, attention should be given to the calibration and validation of the simulation software so as to acquire more realistic traffic data, resulting in more effective prediction of conflicts.

Road crashes are one of the critical issues in the transportation sector. Crash studies aim to establish the relationship of crash occurrences with driver, environment and traffic factors. Lack of a large disaggregate driving or accident data constrains the study of driver factors and driving maneuvers. Moreover, the usual outcome of these studies is the crash likelihood without accounting for the impact of a potential crash, thus leading to an incomplete interpretation of crash risk. New and innovative ways of data collection, such as drone videography and floating car data, are a promising candidate for a disaggregated analysis. Our study proposes a method for estimation of rear-end crash risk during a specific traffic state, using separate formulations of likelihood and severity. We quantify rear-end crash risk by weighing the likelihood by the potential severity of a collision, wherein we introduce a severity indicator for the rear-end crash. The methodology is applied to the highD dataset, a large naturalistic traffic dataset collected on German freeways. The proposed methodology allows for the analysis of risk with traffic state and lane-changing maneuver. The findings show that speed-drop is associated with increased crash risk. Also, lane changing is associated with higher rear-end crash risk, as compared to lane-keeping, during the free-flow as well as congestion traffic. The understanding of the evolution of the crash risk, due to the driving maneuvers under different traffic conditions, can be useful for real-time crash prediction and for devising traffic management strategies.