Combining intention and emotional state inference in a dynamic neural field architecture for human-robot joint action

We report on our approach towards creating socially intelligent robots, which is heavily inspired by recent experimental findings about the neurocognitive mechanisms underlying action and emotion understanding in humans. Our approach uses neuro-dynamics as a theoretical language to model cognition, emotional states, decision making and action. The control architecture is formalized by a coupled system of dynamic neural fields representing a distributed network of local but connected neural populations. Different pools of neurons encode relevant information in the form of self-sustained activation patterns, which are triggered by input from connected populations and evolve continuously in time. The architecture implements a dynamic and flexible context-dependent mapping from observed hand and facial actions of the human onto adequate complementary behaviors of the robot that take into account the inferred goal and inferred emotional state of the co-actor. The dynamic control architecture was validated in multiple scenarios in which an anthropomorphic robot and a human operator assemble a toy object from its components. The scenarios focus on the robot’s capacity to understand the human’s actions, and emotional states, detect errors and adapt its behavior accordingly by adjusting its decisions and movements during the execution of the task.The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was possible in part by the funding of research grants from the Portuguese Foundation for Science and Technology (grant numbers SFRH/BD/48527/2008, SFRH/BPD/71874/2010, SFRH/BD/81334/2011), and with funding from FP6-IST2 EU-IP Project JAST (project number 003747) and FP7 Marie Curie ITN Neural Engineering Transformative Technologies NETT (project number 289146).