The automotive industry has suffered a massive technological evolution over the past decades. Despite the increasing mechanical performance and futuristic design, nowadays there's new demands on the automotive world: autonomous driving, electrified vehicles (hybrid, plug-in, battery electric, and fuel cell), safety, digitalization and infotainment [1], [2].

These new demands are revolutionizing the car's cockpit, through the integration of advanced infotainment systems and new capabilities such as monitoring the driver's context and supporting driver's tasks by providing the right information at the right time through different human-machine modalities. These features aim to increase the driver's experience by maintaining an optimal workload, and keeping the driver focused on the driving task, whenever required by the automation level [3], [4]. In order to continuously access the driver's workload, as well as his readiness when he needs to regain control of the vehicle, it's necessary to firstly monitor the driver's context [4]-[6]. Therefore, this background leads to the emergence of a new challenge: design and development of a real-time automotive system that monitors the driver's activities, fatigue and distraction, and its integration on an automotive HMI system architecture for the new intelligent cockpit of the future.

In this context, this MSc thesis aims to design and develop a system that solves the problem aforementioned, following the Bosch InnovCar P689 project's requirements. Since the activities allowed to be performed by a driver in an automotive cockpit depends on the vehicle's automation level, it's crucial to define which driving-related and non-related activities must be recognized by the automotive HMI system. Regarding the technology stack, it should fully support the envisioned system while optimizing common quality attributes, such as performance, reliability, flexibility and modularity. Hence, it's imperative to choose the most suitable hardware for monitoring the driver's context while solving the tread-off between cost, features and performance. By its side, the software must be modular and flexible, without sacrificing the system's performance. Lastly, the conclusions of the project implementation should provide a clear idea about the integration of the proposed system in an automotive HMI that accesses the driver's context in real-time.

[1] Continental, "Trends in the Automotive Industry." [Online]. Available:
http://www.continental-corporation.com/www/portal_com_en/technologies/technologies/trends-automobil-industry.html. [Accessed: 08-Nov-2016].

[2] A. Vits, "Automotive HMI: Current status and future challenges," pp. 1-7, 2008.

[3] SAE International, "Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Driving Systems," p. 12, 2016.

[4] L. Lorenz, P. Kerschbaum, and J. Schumann, "Designing take over scenarios for automated driving : How does augmented reality support the driver to get back into the loop?," Proc. Hum. Factors Ergon. Soc. 58th Annu. Meet. - 2014, vol. 1, pp. 1681-1685, 2014.

[5] T. Louw, G. Kountouriotis, O. Carsten, and N. Merat, "Driver Inattention During Vehicle Automation: How Does Driver Engagement Affect Resumption Of Control?," 4th Int. Conf. Driv. Distraction Ina., no. November, pp. 1-13, 2015.

[6] C. Braunagel, E. Kasneci, W. Stolzmann, and W. Rosenstiel, "Driver-Activity Recognition in the Context of Conditionally Autonomous Driving," IEEE Conf. Intell. Transp. Syst. Proceedings, ITSC, vol. 2015-Octob, pp. 1652-1657, 2015.