Abstract. This paper deals with online onboard behavior optimization for a autonomous mobile robot in the scope of the European FP7 Symbrion Project. The work presented here extends the (1+1)-onlinealgorithm introduced in [4]. The (1+1)online algorithm has a limitation regarding the ability to perform global search whenever a local optimum is reached. Our new implementation of the algorithm, termed (1+1)-restart-online algorithm, addresses this issue and has been successfully experimented using a Cortex M3 microcontroller connected to a realistic robot simulator as well as within an autonomous robot based on an Atmel ATmega128 microcontroller. Results from the experiments show that the new algorithm is able to escape local optima and to perform behavior optimization in a complete autonomous fashion. As a consequence, it is able to converge faster and provides a richer set of relevant controllers compared to the previous implementation. Let’s imagine an autonomous mobile robot tailored for exploration. This robot could be dropped in a wide variety of unknown environments, from a dense tropical forest

Abstract—To test adaptation hypotheses about the evolution of animals, we need information about the behavior of phenotypically-variable individuals in a specific environment. To model behavior of ancient fish-like vertebrates, we previously combined evolutionary robotics and software simulations to create autonomous biomimetic swimmers in a simple aquatic environment competing and foraging for a single source of food. This system allowed us to test the hypothesis that selection for improved forage navigation drove the evolution of stiffer tails. In this paper, we extend our framework to evaluate more complex environments and hypotheses. Specifically, we test the hypothesis that predatorprey dynamics and the need for effective foraging strategies, operating simultaneously, were key selection pressures driving the evolution of morphological and sensory traits in early, fishlike

Abstract. This paper reports on a feasibility study into the evolution of robot controllers during the actual operation of robots (on-line), using only the computational resources within the robots themselves (on-board). We identify the main challenges that these restrictions imply and propose mechanisms to handle them. The resulting algorithm is evaluated in a hybrid system, using the actual robots ’ processors interfaced with a simulator that represents the environment. The results show that the proposed algorithm is indeed feasible and the particular problems we encountered during this study give hints for further research. 1

Abstract—In this paper we discuss the notion of situated evolution. Our treatment includes positioning situated evolution on the map of evolutionary processes in terms of time- and space-embeddedness, and the identification of decentralization as an orthogonal property. We proceed with a selected overview of related literature in the categories of our interest. This overview enables us to distill further detailes that distinguish the encountered methods. As it turns out the essential differences can be captured through the mechanics of selection and fertilization. These insights are aggregated into a new model called the Situated Evolution Method, which is then used to provide a fine-grained map of exisiting work. I. BACKGROUND AND OBJECTIVES The background of this paper is a research project1 concerned with a group of robots that operate in a challenging environment and permanently adapt their controllers in order to increase their task performance. Evolution is chosen as the principal method of adaptation, hence evolutionary computing (EC) is expected to supply the technical machinery to enable successful adaptation on-the-fly. This choice draws our attention to evolutionary algorithms, expecting much existing work that can be used to drive the evolutionary mechanics in a group of evolving robots. Looking around in EC soon reveals that there is a large variety of evolutionary algorithms, such as Evolutionary

This paper is concerned with a fixed-size population of autonomous agents facing unknown, possibly changing, environments. The motivation is to design an embodied evolutionary algorithm that can cope with the implicit fitness function hidden in the environment so as to provide adaptation in the long run at the level of the population. The proposed algorithm, termed mEDEA, is shown to be both efficient in unknown environments and robust to abrupt and unpredicted changes in the environment. The emergence of consensus towards specific behavioural strategies is examined, with a particular focus on algorithmic stability. Finally, a real world implementation of the algorithm is decribed with a population of 20 real-world e-puck robots.