Industry 4.0 is taking human-robot collaboration at the center of the production environment. Collaborative robots enhance productivity and flexibility while reducing human's fatigue and the risk of injuries, exploiting advanced control methodologies. However, there is a lack of real-time model-based controllers accounting for the complex human-robot interaction dynamics. With this aim, this paper proposes a Model-Based Reinforcement Learning (MBRL) variable impedance controller to assist human operators in collaborative tasks. More in details, an ensemble of Artificial Neural Networks (ANNs) is used to learn a human-robot interaction dynamic model, capturing uncertainties. Such a learned model is kept updated during collaborative tasks execution. In addition, the learned model is used by a Model Predictive Controller (MPC) with Cross-Entropy Method (CEM). The aim of the MPC+CEM is to online optimize the stiffness and damping impedance control parameters minimizing the human effort (i.e, minimizing the human-robot interaction forces). The proposed approach has been validated through an experimental procedure. A lifting task has been considered as the reference validation application (weight of the manipulated part: 10 kg unknown to the robot controller). A KUKA LBR iiwa 14 R820 has been used as a test platform. Qualitative performance (i.e, questionnaire on perceived collaboration) have been evaluated. Achieved results have been compared with previous developed offline model-free optimized controllers and with the robot manual guidance controller. The proposed MBRL variable impedance controller shows improved humanrobot collaboration. The proposed controller is capable to actively assist the human in the target task, compensating for the unknown part weight. The human-robot interaction dynamic model has been trained with a few initial experiments (30 initial experiments). In addition, the possibility to keep the learning of the human-robot interaction dynamics active allows accounting for the adaptation of human motor system.

The control shifting between a human driver and a semi-autonomous vehicle is one of the most critical scenarios in the road-map of autonomous vehicle development. This paper proposes a methodology to study driver's behaviour in semi-autonomous driving with physiological-sensors-integrated driving simulators. A virtual scenario simulating take-over tasks has been implemented. The behavioural profile of the driver has been defined analysing key metrics collected by the simulator namely lateral position, steering wheel angle, throttle time, brake time, speed, and the take-over time. In addition, heart rate and skin conductance changes have been considered as physiological indicators to assess cognitive workload and reactivity. The methodology has been applied in an experimental study which results are crucial for taking insights on users’ behaviour. Results show that individual different driving styles and performance are able to be distinguished by calculating and elaborating the data collected by the system. This research provides potential directions for establishing a method to characterize a driver's behaviour in a semi-autonomous vehicle.