Abstract

Road vehicle accidents are mostly due to human errors, and many such accidents could be avoided by continuously monitoring the driver. Driver monitoring (DM) is a topic of growing interest in the automotive industry, and it will remain relevant for all vehicles that are not fully autonomous, and thus for decades for the average vehicle owner. The present paper focuses on the first step of DM, which consists of characterizing the state of the driver. Since DM will be increasingly linked to driving automation (DA), this paper presents a clear view of the role of DM at each of the six SAE levels of DA. This paper surveys the state of the art of DM, and then synthesizes it, providing a unique, structured, polychotomous view of the many characterization techniques of DM. Informed by the survey, the paper characterizes the driver state along the five main dimensions—called here “(sub)states”—of drowsiness, mental workload, distraction, emotions, and under the influence. The polychotomous view of DM is presented through a pair of interlocked tables that relate these states to their indicators (e.g., the eye-blink rate) and the sensors that can access each of these indicators (e.g., a camera). The tables factor in not only the effects linked directly to the driver, but also those linked to the (driven) vehicle and the (driving) environment. They show, at a glance, to concerned researchers, equipment providers, and vehicle manufacturers (1) most of the options they have to implement various forms of advanced DM systems, and (2) fruitful areas for further research and innovation.

Abstract

In this simulator study, we adopt a human-centered approach to explore whether and how drivers’ cognitive state and driving environment complexity influence reliance on driving automation features. Besides, we examine whether such reliance affects driving performance. Participants operated a vehicle equipped with adaptive cruise control (ACC) in a simulator across six predefined driving scenarios varying in traffic conditions while either performing a cognitively demanding task (i.e., responding to mental calculations) or not. Throughout the experiment, participants had to respect speed limits and were free to activate or deactivate ACC. In complex driving environments, we found that the overall ACC engagement time was lower compared to less complex driving environments. We observed no significant effect of cognitive load on ACC use. Furthermore, while ACC use had no effect on the number of lane changes, it impacted the speed limits compliance and improved lateral control. 

Abstract

Since the invention of the automobile at the end of the 19th century, driving has continually evolved. From rudimentary vehicles consisting of little more than an engine, a seat, and wheels, today's cars have become technological marvels equipped with hundreds of sensors and intelligent algorithms. Consequently, driving has transformed into a complex activity involving multiple interacting entities: the human driver, the vehicle automation, and the driving environment. Despite major technological progress, how to best combine driving automation and driver monitoring systems to dynamically allocate driving tasks for safety and comfort purposes remains a key research challenge. Achieving such adaptive driving automation requires a deep understanding of the interplay between the driver, the vehicle, and the environment. Part I describes the context of this thesis, tracing the evolution of the automobile from mechanical innovation to the integration of driving automation and driver monitoring. It also reviews the state of the art in driver monitoring, with a particular focus on mental workload and distraction. Part II presents human studies conducted in a driving simulator to examine whether drivers' cognitive distraction and the complexity of the driving environment influence reliance on Adaptive Cruise Control (ACC) and whether such reliance affects driving performance. Furthermore, it investigates whether and how physiological and behavioral indicators reflect drivers' cognitive distraction under varying traffic conditions and ACC use. Specifically, three Electrodermal Activity (EDA)-based and three gaze-based indicators were analyzed. Part III introduces engineering approaches for analyzing the driving environment. In particular, it presents a novel Multi-Stream Cellular Test-Time Adaptation (MSC-TTA) setup in which computer vision models adapt on the fly to a dynamic environment divided into cells. To evaluate a method derived from this setup, a new multi-stream, large-scale synthetic semantic segmentation dataset, called DADE, was released. In addition, a probabilistic approach to domain characterization is proposed, where domains are characterized as probability distributions. A method is presented for predicting the likelihood of different weather conditions from images captured by vehicle-mounted cameras. Part IV proposes a closed-loop framework, called DEV, for risk-aware adaptive driving automation that captures the dynamic interplay between the driver, the environment, and the vehicle. The thesis concludes with insights and future perspectives stemming from this research, aimed at fostering safer and more adaptive human–automation cooperation.