Mental practice and verbal instructions execution: a cognitive robotics study Alessandro G. Di Nuovo Davide Marocco, Angelo Cangelosi, Plymouth, University Drake Circus, Plymouth PL4 8AA, UK Vivian M. De La Cruz, Università degli Studi di Messina, via Concezione n. 6, 98122, Messina, Italy Santo Di Nuovo, Università degli Studi di Catania, Via Biblioteca 4, 95124, Catania, Italy Abstract—Understanding the tight relationship that exists between mental imagery and motor activities (i.e. how images in the mind can influence movements and motor skills) has become a topic of interest and is of particular importance in domains in which improving those skills is crucial for obtaining better performance, such as in sports and rehabilitation. In this paper, using an embodied cognition approach and a cognitive robotics platform, we introduce initial results of an ongoing study that explores the impact linguistic stimuli could have in processes of mental imagery practice and subsequent motor execution and performance. Results are presented to show that the robot used, is able to “imagine” or “mentally” recall and accurately execute movements learned in previous training phases, strictly on the basis of the verbal commands issued. Further tests show that data obtained with “imagination” could be used to simulate “mental training” processes such as those that have been employed with human subjects in sports training, in order to enhance precision in the performance of new tasks, through the association of different verbal commands. Keywords- motor imagery, embodied cognition, cognitive robotics, mental training, recurrent neural network. I. INTRODUCTION The processes behind the human ability to create mental images of events and experiences have recently become an object of renewed interest in cognitive science (e.g. [1]). Brain-imaging studies have shown that the same brain areas that are activated when seeing are also activated when recalling images [2]. It has also been shown that primary motor cortex is activated during the production of motor images as well as during the production of active movement [3,4]. Evidence also exists that suggests that language comprehension processes, also involve the activation of specific motor regions of the brain depending on the linguistic constructs heard by subjects. During the reading of verbs related to concrete action, for example, it has been found that the recruitment of the effector-specific regions in primary motor or pre-motor cortex is similar to the activation found in those areas when moving the effector that is most involved in those actions [5]. The first type of evidence, would be partly in line with what has been the controversial yet historically dominant interpretation given by philosophers and psychologists alike to the term “mental images”, that is, that they are a type of “inner pictures” in the mind. The second type, suggests that despite this general tendency to attribute mental images to being quasi-visual phenomena, it would be more appropriate to consider them as quasi-perceptual experience in any sensory mode or combination of sensory modes that is experienced in the absence of the actual stimuli. We consider mental imagery to be a multimodal mental simulation that activates the same, or very similar sensorial modalities, that are activated when we interact with the environment in real time. This could explain why both brain hemispheres and several functional areas (i.e., perceptual, linguistic, and motor) are involved in parallel when a mental image is produced and/or processed [6, 7]. A number of recent studies have shown that the capacity to mentally simulate actions, as well as their end results, plays an extremely important part in our ability to plan and execute actions as well as understand those of others. Mental simulation is often mediated by language. Language is instrumental in the vicarious experiencing of the events characteristic of mental simulation. It describes real or imagined events, guides our attention and orchestrates the retrieval of experiential traces of people, places, objects, actions, and events [8]. Even at the level of the single word, linguistic constructs have been linked to the sensorimotor memory traces that form the basis of mental simulation. In sports, beneficial effects of mental training for performance enhancement in athletes are well established and a number of studies in the literature have explored and reviewed them as well as presented new training principles, e.g [9,10]. For example in [11], a cognitive behavioral training program was implemented to improve the free-throw performance of college basketball players, finding improvements of over 50%. Furthermore, the trial in [12], where mental imagery was used to enhance the training phase of hockey athletes to score a goal, have shown that imagery practice helped in obtaining better performance. Despite these results, and the ample evidence that suggests that mental imagery, and in particular motor imagery, contributes to the enhancement of motor performance, the topic is still a relatively new subject of research, for example ([13]) investigated the effect of mental practice to improve game plans or strategies of play in a trial with 10 female basketball players. Results of the trail support the assumption that motor imagery may lead to better motor performance in open skills when compared to the no-practice condition.