Elio Tuci

Evolutionary Robotics: A New Scientific Tool for Studying Cognition

We survey developments in artificial neural networks, in behavior-based robotics, and in evolutionary algorithms that set the stage for evolutionary robotics (ER) in the 1990s. We examine the motivations for using ER as a scientific tool for studying minimal models of cognition, with the advantage of being capable of generating integrated sensorimotor systems with minimal (or controllable) prejudices. These systems must act as a whole in close coupling with their environments, which is an essential aspect of real cognition that is often either bypassed or modeled poorly in other disciplines. We demonstrate with three example studies: homeostasis under visual inversion, the origins of learning, and the ontogenetic acquisition of entrainment.

Integration of Action and Language Knowledge: A Roadmap for Developmental Robotics

This position paper proposes that the study of embodied cognitive agents, such as humanoid robots, can advance our understanding of the cognitive development of complex sensorimotor, linguistic, and social learning skills. This in turn will benefit the design of cognitive robots capable of learning to handle and manipulate objects and tools autonomously, to cooperate and communicate with other robots and humans, and to adapt their abilities to changing internal, environmental, and social conditions. Four key areas of research challenges are discussed, specifically for the issues related to the understanding of: 1) how agents learn and represent compositional actions; 2) how agents learn and represent compositional lexica; 3) the dynamics of social interaction and learning; and 4) how compositional action and language representations are integrated to bootstrap the cognitive system. The review of specific issues and progress in these areas is then translated into a practical roadmap based on a series of milestones. These milestones provide a possible set of cognitive robotics goals and test scenarios, thus acting as a research roadmap for future work on cognitive developmental robotics.

Evolving self-assembly in autonomous homogeneous robots: Experiments with two physical robots

This research work illustrates an approach to the design of controllers for self-assembling robots in which the self-assembly is initiated and regulated by perceptual cues that are brought forth by the physical robots through their dynamical interactions. More specifically, we present a homogeneous control system that can achieve assembly between two modules (two fully autonomous robots) of a mobile self-reconfigurable system without a priori introduced behavioral or morphological heterogeneities. The controllers are dynamic neural networks evolved in simulation that directly control all the actuators of the two robots. The neurocontrollers cause the dynamic specialization of the robots by allocating roles between them based solely on their interaction. We show that the best evolved controller proves to be successful when tested on a real hardware platform, the swarm-bot. The performance achieved is similar to the one achieved by existing modular or behavior-based approaches, also due to the effect of an emergent recovery mechanism that was neither explicitly rewarded by the fitness function, nor observed during the evolutionary simulation. Our results suggest that direct access to the orientations or intentions of the other agents is not a necessary condition for robot coordination: Our robots coordinate without direct or explicit communication, contrary to what is assumed by most research works in collective robotics. This work also contributes to strengthening the evidence that evolutionary robotics is a design methodology that can tackle real-world tasks demanding fine sensory-motor coordination.

Object transport by modular robots that self-assemble

We present a first attempt to accomplish a simple object manipulation task using the self-reconfigurable robotic system swarm-bot. The number of modular entities involved, their global shape or size and their internal structure are not pre-determined, but result from a self-organized process in which the modules autonomously grasp each other and/or an object. The modules are autonomous in perception, control, action, and power. We present quantitative results, obtained with six physical modules, that confirm the utility of self-assembling robots in a concrete task

Swarm Cognition: an Interdisciplinary Approach to the study of Self-organising Biological Collectives

Basic elements of cognition have been identified in the behaviour displayed by animal collectives, ranging from honeybee swarms to human societies. For example, an insect swarm is often considered a “super-organism” that appears to exhibit cognitive behaviour as a result of the interactions among the individual insects and between the insects and the environment. Progress in disciplines such as neurosciences, cognitive psychology, social ethology and swarm intelligence has allowed researchers to recognise and model the distributed basis of cognition and to draw parallels between the behaviour of social insects and brain dynamics. In this paper, we discuss the theoretical premises and the biological basis of Swarm Cognition, a novel approach to the study of cognition as a distributed self-organising phenomenon, and we point to novel fascinating directions for future work.

Symbol Grounding and Beyond

A Hybrid Model for Learning Word-Meaning Mappings.- Cooperation, Conceptual Spaces and the Evolution of Semantics.- Cross-Situational Learning: A Mathematical Approach.- Dialog Strategy Acquisition and Its Evaluation for Efficient Learning of Word Meanings by Agents.- Evolving Distributed Representations for Language with Self-Organizing Maps.- How Do Children Develop Syntactic Representations from What They Hear?.- How Grammar Emerges to Dampen Combinatorial Search in Parsing.- Implementation of Biases Observed in Childrens Language Development into Agents.- Lexicon Convergence in a Population With and Without Metacommunication.- Operational Aspects of the Evolved Signalling Behaviour in a Group of Cooperating and Communicating Robots.- Propositional Logic Syntax Acquisition.- Robots That Learn Language: Developmental Approach to Human-Machine Conversations.- Simulating Meaning Negotiation Using Observational Language Games.- Symbol Grounding Through Cumulative Learning.- The Human Speechome Project.- Unify and Merge in Fluid Construction Grammar.- Utility for Communicability by Profit and Cost of Agreement.

The Facilitatory Role of Linguistic Instructions on Developing Manipulation Skills

In this paper, we show how a simulated humanoid robot controlled by an artificial neural network can acquire the ability to manipulate spherical objects located over a table by reaching, grasping, and lifting them. The robot controller is developed through an adaptive process in which the free parameters encode the control rules that regulate the fine-grained interaction between the agent and the environment, and the variations of these free parameters are retained or discarded on the basis of their effects at the level of the behavior exhibited by the agent. The robot develops the sensory-motor coordination required to carry out the task in two different conditions; that is, with or without receiving as input a linguistic instruction that specifies the type of behavior to be exhibited during the current phase. The obtained results shown that the linguistic instructions facilitate the development of the required behavioral skills.

Explaining social learning of food preferences without aversions: an evolutionary simulation model of Norway rats

Norway rats (Rattus norvegicus) transmit preferences for novel foods socially by smelling each others breath. However, rats fail to learn aversions, acquiring a preference even if the rat whose breath they smell has been poisoned. Rats can distinguish between sick and healthy conspecifics and social learning of both preferences and aversions is present in other species – it is unclear why rats cannot learn aversions socially. We constructed an evolutionary simulation in which a population of rats foraged from a central location, exploiting food sites that could contain edible or toxic foodstuffs. We examined the relationship between toxin lethality and selection for individual versus social learning and discrimination between sick and healthy conspecifics in order to allow learning of both preferences and aversions. At low lethality levels individual learning was selected for and at intermediate levels we found social learning of both preferences and aversions. Finally, given high lethality levels the simulated rats would employ social learning but failed to learn aversions, matching the behaviour of real rats. We argue that Norway rats do not learn aversions socially because their environment may contain only highly lethal toxins which make interaction with a sick conspecific an extremely rare event.

Active Categorical Perception of Object Shapes in a Simulated Anthropomorphic Robotic Arm

Active perception refers to a theoretical approach to the study of perception grounded on the idea that perceiving is a way of acting, rather than a process whereby the brain constructs an internal representation of the world. The operational principles of active perception can be effectively tested by building robot-based models in which the relationship between perceptual categories and the body-environment interactions can be experimentally manipulated. In this paper, we study the mechanisms of tactile perception in a task in which a neuro-controlled anthropomorphic robotic arm, equipped with coarse-grained tactile sensors, is required to perceptually categorize spherical and ellipsoid objects. We show that best individuals, synthesized by artificial evolution techniques, develop a close to optimal ability to discriminate the shape of the objects as well as an ability to generalize their skill in new circumstances. The results show that the agents solve the categorization task in an effective and robust way by self-selecting the required information through action and by integrating experienced sensory-motor states over time.

Self-Organizing and Scalable Shape Formation for a Swarm of Pico Satellites

We present a scalable and distributed control strategy for swarms of satellites to autonomously form an hexagonal lattice in space around a predefined meeting point. The control strategy is modeled as an artificial potential field. Such potential field is split in two main terms: a local potential is used to form locally hexagonal lattices based on the well known Lennard-Jones potential, and a global potential used to join the lattices into a single one. The control strategy uses only simple local information about few neighbouring satellites and assumes that each satellite can estimate its position with respect to the meeting point. Experiments show the results of the method with up to 500 satellites. The proposed method is general and can be adapted to build different kinds of lattices and shapes.