Robust Virtual Sensing of the Vehicle Sideslip Angle through the Cross-Combination of Multiple Filters Using a Decision Tree Algorithm.

This paper presents a state-of-the-art estimation technique by cross-combining a number n of filters for high-precision, reliable and robust vehicle sideslip angle state estimation, over a full range of vehicle operations irrespective of the driving mission and disruptions that may occur in the system. A machine-learning algorithm based on decision trees connects several filters together to switch between them according to the driving context, ensuring the best possible state estimate for relatively small and large sideslip angle values. In conjunction with the above-mentioned aspects, a seamless transition between different vehicle models is attained by observing the key parameters characterizing the lateral motion of the vehicle. The tests conducted using a prototype vehicle on a snow-covered track confirm the effectiveness and reliability of the proposed approach.

In the Wild HRI Scenario: Influence of Regulatory Focus Theory.

Research related to regulatory focus theory has shown that the way in which a message is conveyed can increase the effectiveness of the message. While different research fields have used this theory, in human-robot interaction (HRI), no real attention has been given to this theory. In this paper, we investigate it in an in the wild scenario. More specifically, we are interested in how individuals react when a robot suddenly appears at their office doors. Will they interact with it or will they ignore it? We report the results from our experimental study in which the robot approaches 42 individuals. Twenty-nine of them interacted with the robot, while the others either ignored it or avoided any interaction with it. The robot displayed two types of behavior (i.e., promotion or prevention). Our results show that individuals that interacted with a robot that matched their regulatory focus type interacted with it significantly longer than individuals that did not experience regulatory fit. Other qualitative results are also reported, together with some reactions from the participants.

Socially assistive robotics for stroke and mild TBI rehabilitation.

This paper describes an interdisciplinary research project aimed at developing and evaluating effective and user-friendly non-contact robot-assisted therapy, aimed at in-home use. The approach stems from the emerging field of social cognitive neuroscience that seeks to understand phenomena in terms of interactions between the social, cognitive, and neural levels of analysis. This technology-assisted therapy is designed to be safe and affordable, and relies on novel human-robot interaction methods for accelerated recovery of upper-extremity function after lesion-induced hemiparesis. The work is based on the combined expertise in the science and technology of non-contact socially assistive robotics and the clinical science of neurorehabilitation and motor learning, brought together to study how to best enhance recovery after stroke and mild traumatic brain injury. Our approach is original and promising in that it combines several ingredients that individually have been shown to be important for learning and long-term efficacy in motor neurorehabilitation: (1) intensity of task specific training and (2) engagement and self-management of goal-directed actions. These principles motivate and guide the strategies used to develop novel user activity sensing and provide the rationale for development of socially assistive robotics therapy for monitoring and coaching users toward personalized and optimal rehabilitation programs.