Understanding the Interplay Between the Driver, the Vehicle, and the Environment for Adapting Driving Automation

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.