The importance of automating pavement maintenance tasks for highway systems has garnered interest from both industry and academia. Despite significant research efforts and promising demonstrations being devoted to reaching a level of semi-automation featuring digital sensing and inspection, site maintenance work still requires manual processes using special vehicles and equipment, reflecting a clear gap to transition to fully autonomous maintenance. This paper reviews the current progress in pavement maintenance automation in terms of inspection and repair operations, followed by a discussion of three key technical challenges related to robotic sensing, control, and actuation. To address these challenges, we propose a conceptual solution we term Autonomous Maintenance Plant (AMP), mainly consisting of five modules for sensing, actuation, control, power supply, and mobility. This AMP concept is part of the “Digital Roads” project’s cyber-physical platform where a road digital twin (DT) is created based on its physical counterpart to enable real-time condition monitoring, sensory data processing, maintenance decision making, and repair operation execution. In this platform, the AMP conducts high-resolution survey and autonomous repair operations enabled (instructed) by the road DT. This process is unmanned and completely autonomous with an expectation to create a fully robotized highway pavement maintenance system.

Policymakers have attempted to preemptively address the concern of ethical issues with the regulation of automated vehicles. Unfortunately, both policymakers and designers of these technologies struggle to articulate ethical issues and their resolution. We propose a framework that engineers and designers of automated technologies can apply that allows them to identify and resolve ethical tensions within the design task. We demonstrate the practicability of the framework to the engineering design process through a human-subject study where engineers applied the framework in a workshop.

The latest advances in the design of vehicles with the adaptive level of automation pose new challenges in the vehicle-driver interaction. Safety requirements underline the need to explore optimal cockpit architectures with regard to driver cognitive and perceptual workload, eyes-off-the-road time and situation awareness. We propose to integrate existing task analysis approaches into system architecture evaluation for the early-stage design optimization. We built the discrete-event simulation tool and applied it within the multi-sensory (sight, sound, touch) cockpit design industrial project.

Advanced Driver-Assistance Systems were created to address the driver's failures. All these ADAS are a part of the evolution of the vehicles towards whole automation. To complete its launch in the automotive market, autonomous vehicles have to pass safety tests to acquire the consumers’ trust. To receive the approval of the public, the self-driving car has to take into account the human feeling. The risk perceived by the driver is one of the new emotional form to integrate at the validation plan. The purpose of this study is to examine the perception of the risk of a self-driving car's driver.

Collision avoidance for robots and vehicles in unpredictable environments is a challenging task. Various control strategies have been developed for the agent (i.e., robots or vehicles) to sense the environment, assess the situation, and select the optimal actions to avoid collision and accomplish its mission. In our research on autonomous ships, we take a machine learning approach to collision avoidance. The lack of available ship steering data of human ship masters has made it necessary to acquire collision avoidance knowledge through reinforcement learning (RL). Given that the learned neural network tends to be a black box, it is desirable that a method is available which can be used to design an agent's behavior so that the desired knowledge can be captured. Furthermore, RL with complex tasks can be either time consuming or unfeasible. A multi-stage learning method is needed in which agents can learn from simple tasks and then transfer their learned knowledge to closely related but more complex tasks. In this paper, we explore the ways of designing agent behaviors through tuning reward functions and devise a transfer RL method for multi-stage knowledge acquisition. The computer simulation-based agent training results have shown that it is important to understand the roles of each component in a reward function and the various design parameters in transfer RL. The settings of these parameters are all dependent on the complexity of the tasks and the similarities between them.

Autonomous vehicles with an ability to trace chemical plumes can be instrumental in tasks such as detection of unexploded ordnance, search for undersea wreckage and environmental monitoring. As a consequence, use of autonomous vehicles to perform chemical plume tracing has received an increasing interest from the research community in recent years. Owing to the diversity of applications and ambient fluid environment of the plumes, there are numerous plume tracing strategies and approaches. This paper reviews two main approaches and a number of strategies that have been successfully implemented to track air or water borne plumes in order to locate odour sources using autonomous vehicles. The first strategy considered is the biomimetic approach that offers excellent models for the development of robotic systems. Strategies inspired by lobsters and bacterium are the main focus in this study. The second scheme considers parallelization of the search procedure by employing a multi-robot approach. This approach has the advantage of utilising a group of smaller and simpler communicating robots which are capable of performing a collaborative search of the plume.

One of the most fundamental problems in the development of an intelligent highway system or an autonomous mobile robot system for factory use is to find the necessary input control variables for smooth and safe movement of the vehicle, or robot, between any two configurations. In this paper it is demonstrated that this problem can be converted into one of finding a fitting function which satisfies the boundary conditions. Three curves, a quintic polynomial, a cubic polynomial and a triangular function are developed to perform the parallel transfer manoeuvre which forms the basis of several important manoeuvres such as reverse parking, moving off, negotiating a stationary obstacle, overtaking a moving vehicle, and changing lane. A detailed discussion of the effect of the vehicle's steering angle limit on the feasibility of these manoeuvres is presented. Simulation results using three typical vehicles, a long commercial vehicle, an ordinary car, and a small laboratory robot, travelling along three curves are also presented and discussed. Based on the comparative study, some suggestions for further work are made. Compared with other methods, this approach is simple and provides excellent simulation of human driver techniques. The paper concludes with a focused discussion about the integration of these techniques with satellite based GPS systems for automated vehicle guidance on highways.