In this paper we address the problem of synthesizing mobile robots able to solve problems in which they cannot merely react to sensory input, but have to maintain an internal state as well. More precisely we will show how autonomous robots synthesized through an evolutionary process can solve problems that necessarily require an ability to integrate sensory-motor information over time. By presenting the result of a set of experiments in which evolving robots are asked to navigate and self-localize in the environment, we will show that successful results can be achieved by providing evolving individuals with neural controllers with neurons that (a) vary their activity at different rates to detect regularities at different time scales in the sensory-motor flow, and (b) use thresholded activation functions to detect events extending over time.

In this paper we present the results of an experiment in which a collection of simulated robots that are evolved for the ability to solve a collective navigation problem develop a communication system that allows them to better cooperate. The analysis of the obtained results indicates how evolving robots develop a non-trivial communication system and exploit different communication modalities. Results also indicate how the possibility to co-adapt the robots ’ individual and social/communicative behaviour plays a key role in the development of progressively more complex and effective individuals. 1.

Choosing one option from a sequence of possibilities seen one at a time is a common problem facing agents whenever resources, such as mates or habitats, are distributed in time or space. Optimal algorithms have been developed for solving a form of this sequential search task known as the Dowry Problem ( nding the highest dowry in a sequence of 100 values); here we explore whether continuous time recurrent neural networks (CTRNNs) can be evolved to perform adaptively in Dowry Problem scenarios, as an example of minimally cognitive behavior [Beer, 1996]. We show that even 4-neuron CTRNNs can successfully solve this sequential search problem, and we oer some initial analysis of how they can achieve this feat.

Abstract. In this paper we describe how a population of simulated robots evolved for the ability to solve a collective navigation problem develop individual and social/communication skills. In particular, we analyze the evolutionary origins of motor and signaling behaviors. Obtained results indicate that signals and the meaning of the signals produced by evolved robots are grounded not only on the robots sensory-motor system but also on robots ’ behavioral capabilities previously acquired. Moreover, the analysis of the co-evolution of robots individual and communicative abilities indicate how innovation in the former might create the adaptive basis for further innovations in the latter and vice versa. 1

In this paper we describe the implications from a general theory of category formation of a set of experiments in which embodied artificial agents are evolved for the ability to accomplish simple tasks. In particular we will focus on how categories might emerge from the dynamical interaction between an agent and its environment and on the relation between categories and behavior. Finally, we will introduce and discuss the notion of action-mediated categories, that is the notion of internal states that provide indirect and implicit information about the external environment and/or the agent/environment relation by exploiting the effects resulting from a stereotypic way of interacting with the environment. 1.

Abstract not found

Abstract not found

Abstract. Communication is a point of central importance in swarms of robots. This paper describes a set of simulations in which artificial evolution is used as a means to engineer robot neuro-controllers capable of guiding groups of robots in a categorisation task by producing appropriate actions. Communicative behaviour emerges, notwithstanding the absence of explicit selective pressure (coded into the fitness function) to favour signalling over non-signalling groups. Post-evaluation analyses illustrate the adaptive function of the evolved signals and show that they are tightly linked to the behavioural repertoire of the agents. Finally, our approach for developing controllers is validated by successfully porting one evolved controller on real robots. 1

Abstract not found

Abstract. This work investigates the conditions in which a population of embodied agents evolved for the ability to display coordinated/cooperative skills can develop an ability to communicate, whether and to what extent the evolved communication system can complexifies during the course of the evolutionary process, and how the characteristics of such communication system varies evolutionarily. The analysis of the obtained results indicates that evolving robots develop a capacity to access/generate information which has a communicative value, an ability to produce different signals encoding useful regularities, and an ability to react appropriately to explicit and implicit signals. The analysis of the obtained results allows us to formulate detailed hypothesis on the evolution of communication for what concern aspects such us: (i) how communication can emerge from a population of initially noncommunicating agents, (ii) how communication systems can complexifies, (iii) how signals/meanings can originate and how they can be grounded in agents sensory-motor states. 1