The challenges for automating vehicles in situations other than lane keeping and interdistance regulation require that systems be upgraded to have the necessary skills to control the vehicle in complex cases such as crossroads or roundabouts. But how to make sure that the developments do not last for years and that the driver accepts the delegation of its activity and its security to a machine? The ANR CoCoVeA project (2013-2017) laid the foundations for a cooperative system for the automated vehicle (level 2). Based on its results in shared driving, the CoCoVeIA project aims to integrate this self-learning capability into the system, giving it the ability to analyze and understand the driver's actions during the shared and manual driving phases to achieve two essential objectives: - The system, learning about simple situations from the actions performed by the driver, will adapt its behavior to the preferences of the driver and thus improve acceptability and confidence. - The system, learning about complex situations (at the tactical level), will extend its skills and thus become, over time, able to help the driver in more varied situations. The approach we propose is to allow the system to learn to perform as well as possible well-defined maneuvers, previously modeled in a deterministic way (for the respect of traffic rules and safety) in a context of shared driving (to improve efficiency and acceptability). Suppose that a maneuver achievable by the system is modeled (an insertion, a highway exit, the crossing of a roundabout, ...). Given the great diversity of driving situations (infrastructure and traffic), the system will probably need the intervention of the driver, in shared mode, to manage some of these situations (for decision making or sharp trajectory control). During these phases of shared or manual driving, learning techniques will make it possible to identify the driver's actions and the causal links with regard to the specific characteristics of the situation (location, speed of other vehicles, driver actions, etc.). Parameters for control laws and trajectory planning will be tuned as a consequence of the observed driving behaviour in connection with the precise situation. This parameter setting would be very difficult to integrate directly during the design of the system without such an observation phase. Furthermore, it will lead to a progressive evolution of the system's skills as it is used, skills that can also be integrated or even shared in future generations of systems or between communicating vehicles. To this end, the present project will propose solutions for increasing the skills of driving controllers via the "progressive learning" properties of the automations, learning made possible through the implementation of a continuous control sharing of the vehicle. The objectives are multiple: 1. Promote the development of automatisms by human behaviors "mimic", while ensuring that these behaviors are compatible with safety; 2. Allow drivers to build their confidence in the vehicle through their driving experience; 3. To have a better customization of the automated systems’ operation according to the wishes of each driver; 4. Design automated driving systems that integrate smoothly into the traffic.

The accumulation within the cars cockpit of assistance systems interacting with the driver via various modalities (visual, manual, tactile, sound, haptic…) jointly with the increase in the complexity of these systems (going from information to automatic driving) raises new problems of cooperation between the driver and the vehicle. Ensuring good safety conditions supposes to focus particularly on the compatibility of the whole of these systems with the vehicle guiding task, especially in terms of “comprehension of what the system does”, of “conscience of the activated modes” and of “capacity of attention and treatment” (situation awareness, workload) which they are likely to require. This is especially true during the transition phases (manual towards automatic and conversely). These problems were particularly highlighted within the ANR-ABV project (2009-2013) in which the majority of the partners of this consortium were involved. This project of automatic driving, partly at the origin of the CoCoVeA project, showed the need for integrating at the early stages of the system design the interactions with the driver dealing with task sharing, and degree of freedom, authority, level of automation, priorisation of information and management of the various systems. This approach supposes to be able to know the state of the driver at every moment, the current driving situation, the limits of operation of the various assistance systems and starting from these data, to make a decision concerning the activation or not of one or the other system and the modulation of its degree of action. The consortium brings competences necessary to the realization of this multidisciplinary project. PSA Peugeot Citroen, as a car manufacturer, is an expert as regards problems of integration and evaluation of embedded systems. Continental Automotive and Valeo have an important knowledge in design and development of these systems. LAMIH is an expert as regards human-machine cooperation and has an important experience in the prototyping and evaluation of driver assistance systems in simulator. SPIROPS is specialized in artificial intelligence and decision-making processes. IFSTTAR and INRIA are recognized for their work on driver assistance systems, particularly in automatic driving. UNICAEN-COMETE and AKKA have a large experience in the analysis of the state and the behavior of the driver through studies carried out in particular on the assessment of vigilance. AKKA has also an important experience in the ergonomic study of the aircraft cockpits (human factors certification) and in particular in the management of emergency situations. This competence will make it possible to widen the field of research and to capitalize on the two fields: aeronautics and car. In addition, the partners have state-of-the-art experimental platforms which will be made available for the project, in particular the dynamic simulator of LAMIH as well as the laboratory vehicles of IFSTTAR and AKKA-INRIA. Using these complementary competences and means, the consortium proposes: • To develop a cooperative architecture between driver and assistance system for automatic driving (vehicle control sharing through haptics). • To develop a prototype for the control and coordination of the systems embedded in the cockpit. • To integrate these systems on several demonstrators in both driving simulator and real vehicles. • To validate through an experiment the developed systems. • To produce recommendations for the manufacturers and equipment suppliers.