Davide Marocco

The emergence of communication in evolutionary robots.

Evolutionary robotics is a biologically inspired approach to robotics that is advantageous to studying the evolution of communication. A new model for the emergence of communication is developed and tested through various simulation experiments. In the first simulation, the emergence of simple signalling behaviour is studied. This is used to investigate the inter-relationships between communication abilities, namely linguistic production and comprehension, and other behavioural skills. The model supports the hypothesis that the ability to form categories from direct interaction with an environment constitutes the grounds for subsequent evolution of communication and language. In the second simulation, evolutionary robots are used to study the emergence of simple syntactic categories, e.g. action names (verbs). Comparisons between the two simulations indicate that the signalling lexicon emerged in the first simulation follows the evolutionary pattern of nouns, as observed in related models on the evolution of syntactic categories. Results also support the language-origin hypothesis on the fact that nouns precede verbs in both phylogenesis and ontogenesis. Further extensions of this new evolutionary robotic model for testing hypotheses on language origins are also discussed.

2012 Special Issue: The grounding of higher order concepts in action and language: A cognitive robotics model

In this paper we present a neuro-robotic model that uses artificial neural networks for investigating the relations between the development of symbol manipulation capabilities and of sensorimotor knowledge in the humanoid robot iCub. We describe a cognitive robotics model in which the linguistic input provided by the experimenter guides the autonomous organization of the robots knowledge. In this model, sequences of linguistic inputs lead to the development of higher-order concepts grounded on basic concepts and actions. In particular, we show that higher-order symbolic representations can be indirectly grounded in action primitives directly grounded in sensorimotor experiences. The use of recurrent neural network also permits the learning of higher-order concepts based on temporal sequences of action primitives. Hence, the meaning of a higher-order concept is obtained through the combination of basic sensorimotor knowledge. We argue that such a hierarchical organization of concepts can be a possible account for the acquisition of abstract words in cognitive robots.

2013 Special Issue: Autonomous learning in humanoid robotics through mental imagery

In this paper we focus on modeling autonomous learning to improve performance of a humanoid robot through a modular artificial neural networks architecture. A model of a neural controller is presented, which allows a humanoid robot iCub to autonomously improve its sensorimotor skills. This is achieved by endowing the neural controller with a secondary neural system that, by exploiting the sensorimotor skills already acquired by the robot, is able to generate additional imaginary examples that can be used by the controller itself to improve the performance through a simulated mental training. Results and analysis presented in the paper provide evidence of the viability of the approach proposed and help to clarify the rational behind the chosen model and its implementation.

Towards the grounding of abstract words: A Neural Network model for cognitive robots

In this paper, a model based on Artificial Neural Networks (ANNs) extends the symbol grounding mechanism to abstract words for cognitive robots. The aim of this work is to obtain a semantic representation of abstract concepts through the grounding in sensorimotor experiences for a humanoid robotic platform. Simulation experiments have been developed on a software environment for the iCub robot. Words that express general actions with a sensorimotor component are first taught to the simulated robot. During the training stage the robot first learns to perform a set of basic action primitives through the mechanism of direct grounding. Subsequently, the grounding of action primitives, acquired via direct sensorimotor experience, is transferred to higher-order words via linguistic descriptions. The idea is that by combining words grounded in sensorimotor experience the simulated robot can acquire more abstract concepts. The experiments aim to teach the robot the meaning of abstract words by making it experience sensorimotor actions. The iCub humanoid robot will be used for testing experiments on a real robotic architecture.

Special issue on artificial mental imagery in cognitive systems and robotics

The present special issue of Adaptive Behavior is focused on exploiting the concept of mental imagery and mental simulation as a fundamental cognitive capability, as applied to artificial cognitive systems and robotics. The special issue is motivated by the fact that the processes behind the human ability to create mental images have recently become an object of renewed interest in cognitive science and, in particular, their applications in the field of artificial cognitive systems. With the aim of providing a panorama of the current research activity on the topic, this special issue presents seven selected contributions considered to be representative of the state of the art in the field. In the section that follows, we give a short introduction on recent work on mental imagery in general, and in the field of artificial cognitive systems in particular, in order to help the reader to contextualize the topic. Subsequently, we summarize the new findings that this special issue presents. Mental imagery has long been the subject of research and debate in philosophy, psychology, cognitive science, and more recently, neuroscience (Kosslyn, 1996), but only quite recently a growing amount of evidence from empirical studies has begun to demonstrate the relationship between bodily experiences and mental processes that actively involve body representations. This is also due to the fact that, in the past, philosophical and scientific investigations of the topic primarily focused upon visual mental imagery. Contemporary imagery research has now broadly extended its scope to include every experience that resembles the experience of perceiving from any sensorial modality. The underlying neurocognitive mechanisms involved in mental imagery, however, and the subsequent physical performance, are still far from being fully understood. Understanding the processes behind the human ability to create mental images of events and experiences, remains a critical issue. Recent research, both in experimental as well as practical contexts, suggests that imagined and executed movement planning relies on internal models for action (Hesslow, 2012). These representations are frequently associated with the notion of internal (forward) models and are hypothesized to be an integral part of action planning (Wolpert, 1997; Skoura, Vinter, & Papaxanthis, 2009). Furthermore, Steenbergen, van Nimwegen, and Crajé (2007) suggest that motor imagery may be a necessary prerequisite for motor planning. Jeannerod (2001) studied the role of motor imagery in action planning and proposed the so-called equivalence hypothesis, suggesting that motor simulation and motor control processes are functionally equivalent (Munzert, Lorey, & Zentgraf, 2009; Ramsey, Cumming, Eastough, & Edwards, 2010). Advances in information and communication technologies have made new tools available to scientists interested in artificial cognitive systems and in designing robotic platforms equipped with sophisticated motors and sensors in order to replicate animal or human sensorimotor input/output streams, e.g. the iCub humanoid robot (Metta, Natale, Nori, Sandini, Vernon, Fadiga, et al., 2010). These platforms, despite the tremendous potential applications, still face several challenges in developing complex behaviors (Asada et al., 2009). To this end, increased research efforts are needed to understand the role of mental imagery and its mechanisms in human cognition and how it can be used to enhance motor control in autonomous robots. From a technological point of view, the impact in the field of robotics could be significant. It could lead to the derivation of engineering principles for the development of autonomous systems that are capable of

A Neural Network model for spatial mental imagery investigation: A study with the humanoid robot platform iCub

Understanding the process behind the human ability of creating mental images of events and experiences is a still crucial issue for psychologists. Mental imagery may be considered a multimodal biological simulation that activates the same, or very similar, sensorial and motor modalities that are activated when we interact with the environment in real time. Neuro-psychological studies show that neural mechanisms underlying real-time visual perception and mental visualization are the same when a task is mentally recalled. Nevertheless, the neural mechanisms involved in the active elaboration of mental images might be different from those involved in passive elaborations. The enhancement of this active and creative imagery is the aim of most psychological and educational processes, although, more empirical effort is needed in order to understand the mechanisms and the role of active mental imagery in human cognition. In this work we present some results of on ongoing investigation about mental imagery using cognitive robotics. Here we focus on the capability to estimate, from proprioceptive and visual information, the position into a soccer field when the robot acquires the goal. Results of simulation with the iCub platform are given to show that the computational model is able to efficiently estimate the robots position. The final objective of our work is to replicate with a cognitive robotics model the mental imagery when it is used during the training phase of athletes that are allowed to imaginary practice to score a goal.

Making sense of words: a robotic model for language abstraction

Building robots capable of acting independently in unstructured environments is still a challenging task for roboticists. The capability to comprehend and produce language in a ‘human-like’ manner represents a powerful tool for the autonomous interaction of robots with human beings, for better understanding situations and exchanging information during the execution of tasks that require cooperation. In this work, we present a robotic model for grounding abstract action words (i.e. USE, MAKE) through the hierarchical organization of terms directly linked to perceptual and motor skills of a humanoid robot. Experimental results have shown that the robot, in response to linguistic commands, is capable of performing the appropriate behaviors on objects. Results obtained in case of inconsistency between the perceptual and linguistic inputs have shown that the robot executes the actions elicited by the seen object.

Morphological Coevolution for Fluid Dynamical-Related Risk Mitigation

In the lava flow mitigation context, the determination of areas exposed to volcanic risk is crucial for diminishing consequences in terms of human causalities and damages of material properties. In order to mitigate the destructive effects of lava flows along volcanic slopes, the building and positioning of artificial barriers is fundamental for controlling and slowing down the lava flow advance. In this article, an evolutionary computation-based decision support system for defining and optimizing volcanic hazard mitigation interventions is proposed. In particular, the SCIARA-fv2 Cellular Automata numerical model has been applied for simulating lava flows at Mt. Etna (Italy) volcano and Parallel Genetic Algorithms (PGA) adopted for optimizing protective measures construction by morphological evolution. The PGA application regarded the optimization of the position, orientation, and extension of earth barriers built to protect Rifugio Sapienza, a touristic facility located near the summit of the volcano. A preliminary release of the algorithm, called single barrier (SBA) approach, was initially considered. Subsequently, a second GA strategy, called Evolutionary Greedy Strategy (EGS), was implemented by introducing multibarrier protection measures in order to improve the efficiency of the final solution. Finally, a Coevolutionary Cooperative Strategy (CCS), has been introduced where all barriers are encoded in the genotype and, because all the constituents parts of the solution interact with the GA environment, a mechanism of cooperation between individuals has been favored. The study has produced extremely positive results and represents, to our knowledge, the first application of morphological evolution for lava flow mitigation.

Lava Flow Modeling by the Sciara-Fv3 Parallel Numerical Code

This paper presents the release fv3 of the Complex Cellular Automata model Sciara for simulating lava flows. It is based on a Bingham-like rheology and both flow velocity and the physical time corresponding to a computational step have been made explicit. The model has been preliminary tested with satisfying results by considering the 2006 lava event at Mt Etna (Italy). A HTML5 based Web application with a WebGL 3D interactive visualization system has also been developed as user interface for Sciara-fv3. Eventually, the numerical code has been parallelised by the CUDA GPGPU paradigm, allowing for a considerable reduction of the execution time, despite the numerical code complexity.

Emergence of Leadership in a Group of Autonomous Robots.

In this paper we examine the factors contributing to the emergence of leadership in a group, and we explore the relationship between the role of the leader and the behavioural capabilities of other individuals. We use a simulation technique where a group of foraging robots must coordinate to choose between two identical food zones in order to forage collectively. Behavioural and quantitative analysis indicate that a form of leadership emerges, and that groups with a leader are more effective than groups without. Moreover, we show that the most skilled individuals in a group tend to be the ones that assume a leadership role, supporting biological findings. Further analysis reveals the emergence of different “styles” of leadership (active and passive).