Abstract Autonomous agents are becoming increasingly ubiquitous and are playing an increasing role in wide range of safety-critical systems, such as driverless cars, exploration robots and unmanned aerial vehicles. These agents operate in highly dynamic and heterogeneous environments, resulting in complex behaviour and interactions. Therefore, the need arises to model and understand more complex and nuanced agent interactions than have previously been studied. In this paper, we propose a novel agent-based modelling approach to investigating norm emergence, in which such interactions can be investigated. To this end, while there may be an ideal set of optimally compatible actions there are also combinations that have positive rewards and are also compatible. Our approach provides a step towards identifying the conditions under which globally compatible norms are likely to emerge in the context of complex rewards. Our model is illustrated using the motivating example of self-driving cars, and we present the scenario of an autonomous vehicle performing a left-turn at a T-intersection.

Recent advances in smart connected vehicles and Intelligent Transportation Systems (ITS) are based upon the capture and processing of large amounts of sensor data. Modern vehicles contain many internal sensors to monitor a wide range of mechanical and electrical systems and the move to semi-autonomous vehicles adds outward looking sensors such as cameras, lidar, and radar. ITS is starting to connect existing sensors such as road cameras, traffic density sensors, traffic speed sensors, emergency vehicle, and public transport transponders. This disparate range of data is then processed to produce a fused situation awareness of the road network and used to provide real-time management, with much of the decision making automated. Road networks have quiet periods followed by peak traffic periods and cloud computing can provide a good solution for dealing with peaks by providing offloading of processing and scaling-up as required, but in some situations latency to traditional cloud data centres is too high or bandwidth is too constrained. Cloud computing at the edge of the network, close to the vehicle and ITS sensor, can provide a solution for latency and bandwidth constraints but the high mobility of vehicles and heterogeneity of infrastructure still needs to be addressed. This paper surveys the literature for cloud computing use with ITS and connected vehicles and provides taxonomies for that plus their use cases. We finish by identifying where further research is needed in order to enable vehicles and ITS to use edge cloud computing in a fully managed and automated way. We surveyed 496 papers covering a seven-year timespan with the first paper appearing in 2013 and ending at the conclusion of 2019.

This paper proposes a discrete time distributed state feedback controller design strategy for a homogenous vehicle platoon system with undirected network topology which is resilient to both external disturbances and random consecutive network packet drop. The system incorporates a distributed state feedback controller design by satisfying bounded$H_{\infty }$norm using Lyapunov-Krasovskii based linear matrix inequality (LMI) approach that ensures internal stability and performance. The effect of packet drops on internal stability in terms of stability margin are studied for a homogenous vehicle platoon system with undirected network topology and external disturbance. The variation of stability margin, representing absolute value of least stable close-loop pole, is also studied for two common undirected network topologies for vehicle platooning, i.e., bidirectional predecessor following (BPF) and bidirectional predecessor leader following (BPLF) topologies by varying platoon members, packet drop rates with number of contiguous packets dropped. Results demonstrate that the control strategy best satisfies the requirement of maintaining a desired inter-vehicular distance with constant spacing policy and leader trajectory using two network topologies: BPF and BPLF. We show how these topologies are robust in terms of ensuring internal stability and performance to maintain cooperative motion of vehicle platoon system with different number of followers, random multiple consecutive packet drops and external disturbance.

This paper presents the design of a robust distributed state-feedback controller in the discrete-time domain for homogeneous vehicle platoons with undirected topologies, whose dynamics are subjected to external disturbances and under random single packet drop scenario. A linear matrix inequality (LMI) approach is used for devising the control gains such that a bounded$H_{\infty }$norm is guaranteed. Furthermore, a lower bound of the robustness measure, denoted as$\gamma $gain, is derived analytically for two platoon communication topologies, i.e., the bidirectional predecessor following (BPF) and the bidirectional predecessor leader following (BPLF). It is shown that the$\gamma $gain is highly affected by the communication topology and drastically reduces when the information of the leader is sent to all followers. Finally, numerical results demonstrate the ability of the proposed methodology to impose the platoon control objective for the BPF and BPLF topology under random single packet drop.

The state-of-the-art decision and planning approaches for autonomous vehicles have moved away from manually designed systems, instead focusing on the utilisation of large-scale datasets of expert demonstration via Imitation Learning (IL). In this paper, we present a comprehensive review of IL approaches, primarily for the paradigm of end-to-end based systems in autonomous vehicles. We classify the literature into three distinct categories: 1) Behavioural Cloning (BC), 2) Direct Policy Learning (DPL) and 3) Inverse Reinforcement Learning (IRL). For each of these categories, the current state-of-the-art literature is comprehensively reviewed and summarised, with future directions of research identified to facilitate the development of imitation learning based systems for end-to-end autonomous vehicles. Due to the data-intensive nature of deep learning techniques, currently available datasets and simulators for end-to-end autonomous driving are also reviewed.

Behaviour prediction function of an autonomous vehicle predicts the future states of the nearby vehicles based on the current and past observations of the surrounding environment. This helps enhance their awareness of the imminent hazards. However, conventional behavior prediction solutions are applicable in simple driving scenarios that require short prediction horizons. Most recently, deep learning-based approaches have become popular due to their promising performance in more complex environments compared to the conventional approaches. Motivated by this increased popularity, we provide a comprehensive review of the state-of-the-art of deep learning-based approaches for vehicle behavior prediction in this article. We firstly give an overview of the generic problem of vehicle behavior prediction and discuss its challenges, followed by classification and review of the most recent deep learning-based solutions based on three criteria: input representation, output type, and prediction method. The article also discusses the performance of several well-known solutions, identifies the research gaps in the literature and outlines potential new research directions.

Haptic feedback can improve safety and driving behaviour. While vibration has been widely studied, other haptic modalities have been neglected. To address this, we present two studies investigating the use of uni- and bimodal vibrotactile and thermal cues on the steering wheel. First, notifications with three levels of urgency were subjectively rated and then identified during simulated driving. Bimodal feedback showed an increased identification time over unimodal vibrotactile cues. Thermal feedback was consistently rated less urgent, showing its suitability for less time critical notifications, where vibration would be unnecessarily attention-grabbing. The second study investigated more complex thermal and bimodal haptic notifications comprised of two different types of information (Nature and Importance of incoming message). Results showed that both modalities could be identified with high recognition rates of up to 92% for both and up to 99% for a single type, opening up a novel design space for haptic in-car feedback.

Quantifying and encoding occupants' preferences as an objective function for the tactical decision making of autonomous vehicles is a challenging task. This paper presents a low-complexity approach for lane-change initiation and planning to facilitate highly automated driving on freeways. Conditions under which human drivers find different manoeuvres desirable are learned from naturalistic driving data, eliminating the need for an engineered objective function and incorporation of expert knowledge in form of rules. Motion planning is formulated as a finite-horizon optimisation problem with safety constraints. It is shown that the decision model can replicate human drivers' discretionary lane-change decisions with up to 92% accuracy. Further proof of concept simulation of an overtaking manoeuvre is shown, whereby the actions of the simulated vehicle are logged while the dynamic environment evolves as per ground truth data recordings.

High reliability is one of the key requirements for the future fully connected autonomous vehicles. This paper proposes a novel highly reliable multiple access technique for Vehicle-to-Everything (V2X) networks. The proposed technique uses Index Modulation (IM) in conjunction with Non-Orthogonal Multiple Access (NOMA), which significantly improves the performance of detection at the receiver side. It also benefits from superimposed IM with repetition coding and power allocation factor in V2X networks. We investigate mapping rules for IM-aided NOMA for multiple vehicles. Performance evaluation in this paper shows that both diversity order and power gain can be improved if the proposed scheme is deployed, resulting in a lower probability of index and symbol errors in presence of sparsely activated sub-carriers compared to Orthogonal Multiple Access (OMA) or NOMA.

Automated vehicles are increasingly getting main-streamed and this has pushed development of systems for autonomous manoeuvring (e.g., lane-change, merge, and overtake) to the forefront. A novel framework for situational awareness and trajectory planning to perform autonomous overtaking in high-speed structured environments (e.g., highway and motorway) is presented in this paper. A combination of a potential field like function and reachability sets of a vehicle are used to identify safe zones on a road that the vehicle can navigate towards. These safe zones are provided to a tube-based robust model predictive controller as reference to generate feasible trajectories for combined lateral and longitudinal motion of a vehicle. The strengths of the proposed framework are: 1) it is free from non-convex collision avoidance constraints; 2) it ensures feasibility of trajectory even if decelerating or accelerating while performing lateral motion; and 3) it is real-time implementable. The ability of the proposed framework to plan feasible trajectories for high-speed overtaking is validated in a high-fidelity IPG CarMaker and Simulink co-simulation environment.

The visual demand of finger-touch based interactions with touch screens has been increasingly modelled using Fitts' Law. With respect to driving, these models facilitate the prediction of mean glance duration and total glance time with an index of difficulty based on target size and location. Strong relationships between measures have been found in the controlled conditions of driving simulators. The present study aimed to validate such models in naturalistic conditions. Nineteen experienced drivers carried out a range of touchscreen button-press tasks in an instrumented car on a UK motorway. In contrast with previous simulator-based work, our on-road data produced much weaker relationships between the index of difficulty and glance times. The model improved by focusing on tasks that required one glance only. Limitations of Fitts' Law in the more complex and dynamic real-world driving environment are discussed, as are the potential drawbacks of driving simulators for conducting visual demand research.

Haptic feedback is used in cars to reduce visual inattention. While tactile feedback like vibration can be influenced by the car's movement, thermal and cutaneous push feedback should be independent of such interference. This paper presents two driving simulator studies investigating novel tactile feedback on the steering wheel for navigation. First, devices on one side of the steering wheel were warmed, indicating the turning direction, while those on the other side were cooled. This thermal feedback was compared to audio. The thermal navigation lead to 94.2% correct recognitions of warnings 200m before the turn and to 91.7% correct turns. Speech had perfect recognition for both. In the second experiment, only the destination side was indicated thermally, and this design was compared to cutaneous push feedback. The simplified thermal feedback design did not increase recognition, but cutaneous push feedback had high recognition rates (100% for 200 m warnings, 98% for turns).

3D object classification can be realised by rendering views of the same object from different angles and aggregating all the views to build a classifier. Although this approach has been previously proposed for general objects classification, most existing works did not consider visual impairments. In contrast, this paper considers the problem of 3D object classification for driving applications under impairments (e.g. occlusion and sensor noise) by generating an application-specific dataset. We present a cooperative object classification method where multiple images of the same object seen from different perspectives (agents) are exploited to generate more accurate classification. We consider model generalisation capability and its resilience to impairments. We introduce an occlusion model with higher resemblance to real-world occlusion and use a simplified sensor noise model. The experimental results show that the cooperative model, relying on multiple views, significantly outperforms single-view methods and is effective in mitigating the effects of occlusion and sensor noise.

Understanding how best to present information inside a semi-automated vehicle is a prevalent challenge in HMI design. There is an understanding that a driver's trust and previous driving experience can affect the information they require inside a semi-automated vehicle. However, to date little is known about how these predispositions specifically affect the types of information that should be presented and importantly, how this changes with increased exposure to an automated system. In this paper, seventeen participants experienced twenty-six minutes of an automated driving simulation once every day for a week. The information to display was carefully chosen in accordance with the Skills, Rules, Knowledge model. The information was synchronized to the driving simulation and presented on a tablet in the driving simulator. Eye tracking was used to measure the information looked at. The results showed that trust increased significantly with increased exposure, but this had no correlation to any specific piece of information viewed. Drivers who were more prone to making lapses or errors (as measured by the Driver Behavior Questionnaire) tended towards using information that was less cognitively demanding. Finally, a driver's propensity to making lapses was found to be a potential early predictor of trust, but this became less accurate with increased exposure to the semi-automated vehicle.

Mobility, node density, and the demand for large volumes of data exchange have aggravated competition for limited resources in the wireless communications environment. This paper proposes a novel MAC scheme called segmentation MAC (SMAC), which can be used in large-scale vehicle-to-everything (V2X) communication networks. SMAC functions to support the dynamical allocation of radio channels. It is compatible with the asynchronous multi-channel MAC sub-layer extension of the IEEE 802.11p standard. A key innovate feature of SMAC is that the segmentation of the network and channel allocations are dynamically adjusted according to the density of vehicles. We also propose a novel efficient forwarding mechanism to ensure inter-segment connectivity. To evaluate the performance of inter-segment connectivity, a rigorous analytical model is proposed to measure the multi-hop dissemination latency. The proposal is evaluated in network simulator NS2 as well as the standard IEEE 1609.4 and two asynchronous multi-channel MAC benchmarks. Both analytical and simulation results demonstrate better effectiveness of the proposed scheme compared with the existing similar schemes in the literature.

An autonomous vehicle (AV) requires an accurate perception of its surrounding environment to operate reliably. The perception system of an AV, which normally employs machine learning (e.g., deep learning), transforms sensory data into semantic information that enables autonomous driving. Object detection is a fundamental function of this perception system, which has been tackled by several works, most of them using 2D detection methods. However, the 2D methods do not provide depth information, which is required for driving tasks, such as path planning, collision avoidance, and so on. Alternatively, the 3D object detection methods introduce a third dimension that reveals more detailed object's size and location information. Nonetheless, the detection accuracy of such methods needs to be improved. To the best of our knowledge, this is the first survey on 3D object detection methods used for autonomous driving applications. This paper presents an overview of 3D object detection methods and prevalently used sensors and datasets in AVs. It then discusses and categorizes the recent works based on sensors modalities into monocular, point cloud-based, and fusion methods. We then summarize the results of the surveyed works and identify the research gaps and future research directions.

With increasing automation, occupants of fully autonomous vehicles are likely to be completely disengaged from the driving task. However, even with no driving involved, there are still activities that will require interfaces between the vehicle and passengers. This study evaluated different configurations of screens providing operational-related information to occupants for tracking the progress of journeys. Surveys and interviews were used to measure trust, usability, workload and experience after users were driven by an autonomous low speed pod. Results showed that participants want to monitor the state of the vehicle and see details about the ride, including a map of the route and related information. There was a preference for this information to be displayed via an onboard touchscreen device combined with an overhead letterbox display versus a smartphone-based interface. This paper provides recommendations for the design of devices with the potential to improve the user interaction with future autonomous vehicles.

Haptic feedback has been widely studied for in-car interactions. However, most of this research has used vibrotactile cues. This paper presents two studies that examine novel thermal feedback for navigation during simulated driving for a lane change task. In the first, we compare the distraction and time differences of audio and thermal feedback. The results show that the presentation of thermal stimuli does not increase lane deviation, but the time needed to complete a lane change increased by 1.82 seconds. In the second study, the influence of variable changes of thermal stimuli on the lane change task performance was tested. We found that the same stimulus design for warm and cold temperatures does not always elicit the same results. Furthermore, variable alterations can have different effects on specified tasks. This suggests that the design of thermal stimuli is highly dependent on what task result should be maximized.

This paper presents formative research to inform the design of intelligent automotive user interfaces. It describes an evaluation of dialogue-based interfaces, mediating the driver to take back control from the autonomous mode of a car. Four concepts designed to increase driver Situation Awareness were evaluated in a driving simulator. They used dialogue-based interaction, where driving-related information was either asked from or repeated by the driver, with the alternative of a countdown-based interface with no additional information. An inclusive set of participants, with a wide age spectrum, tested the interfaces. The shorter and simpler interaction of the countdown timer was most accepted. The interface seeking answers to driving-related questions came next, and the interface requiring repetition of driving-related information, even when augmented by visual and tactile cues, was least accepted. Design guidelines on utilizing dialogue as a means of keeping the driver in the loop during a takeover were thus derived.

Autonomous driving presents an exciting new development in vehicle technology. It poses a new challenge in driver-automation collaboration particularly during handover transitions between human and machine. In order to deal with this problem, this paper proposes a novel control framework for the haptic take-over system. The high-level framework of the haptic take-over control system, which takes driver cognitive workload, neuromuscular dynamics and optimal trajectory planning into consideration, is developed. Under the proposed framework, the determination approach of the optimal input sequence is introduced. The model of the allowed driver take-over authority, which is associated with driver's cognitive workload, as well as muscle readiness during take- over, is investigated and developed. The haptic feedback torque controller is then designed so as to minimize the deviation between the allowed control authority and driver's current degree of participation. A handover process, along with the proposed take-over control method, is also simulated. The simulation results validate the feasibility and effectiveness of the proposed approach.

The rise of intelligent vehicle systems will lead to more human-machine interactions and so there is a need to create a bridge between the system and the actions and behaviours of the people inside the vehicle. In this paper, we propose a dual camera setup to monitor the actions and behaviour of vehicle passengers and a deep learning architecture which can utilise video data to classify a range of actions. The method incorporates two different views as input to a 3D convolutional network and uses transfer learning from other action recognition data. The performance of this method is evaluated using an in-vehicle dataset, which contains video recordings of people performing a range of common in-vehicle actions. We show that the combination of transfer learning and using dual viewpoints in a 3D action recognition network offers an increase in classification accuracy of action classes with distinct poses, e.g. mobile phone use and sleeping, whilst it does not apply as well for classifying those actions with small movements, such as talking and eating.

For an autonomous vehicle to operate safely and effectively, an accurate and robust localization system is essential. While there are a variety of vehicle localization techniques in literature, there is a lack of effort in comparing these techniques and identifying their potentials and limitations for autonomous vehicle applications. Hence, this paper evaluates the state-of-the-art vehicle localization techniques and investigates their applicability on autonomous vehicles. The analysis starts with discussing the techniques which merely use the information obtained from on-board vehicle sensors. It is shown that although some techniques can achieve the accuracy required for autonomous driving but suffer from the high cost of the sensors and also sensor performance limitations in different driving scenarios (e.g., cornering and intersections) and different environmental conditions (e.g., darkness and snow). This paper continues the analysis with considering the techniques which benefit from off-board information obtained from V2X communication channels, in addition to vehicle sensory information. The analysis shows that augmenting off-board information to sensory information has potential to design low-cost localization systems with high accuracy and robustness, however, their performance depends on penetration rate of nearby connected vehicles or infrastructure and the quality of network service.

In order to develop an advanced haptic take-over system for highly automated vehicles, research into the driver's neuromuscular dynamics is needed. In this paper a dynamic model of drivers' neuromuscular interaction with a steering wheel is firstly established. The transfer function and the natural frequency of the systems are analysed. In order to identify the key parameters of the driver-steering-wheel coupled system and investigate the system properties under different situations, experiments with drive-in-the-loop are carried out. For each test subject, two steering tasks, namely the passive and active steering tasks, are instructed to be completed. Furthermore, during the experiments, subjects manipulated the steering wheel with two distinct postures and three different hand positions. Based on the test results, key parameters of the transfer function and system properties are identified and investigated. The data and characteristics of the driver neuromuscular system are discussed and compared with respect to different steering tasks, hand positions and driver postures. These test results identified system properties that provide a good foundation for the development of a haptic take-over control system for automated vehicles.