The problem of the validity of simulation is particularly relevant for methodologies that use machine learning techniques to develop control systems for autonomous robots, like, for instance, the Artificial Life approach named Evolutionary Robotics. In fact, despite that it has been demonstrated that training or evolving robots in the real environment is possible, the number of trials needed to test the system discourage the use of physical robots during the training period. By evolving neural controllers for a Khepera robot in computer simulations and then transferring the obtained agents in the real environment we will show that: (a) an accurate model of a particular robot-environment dynamics can be built by sampling the real world through the sensors and the actuators of the robot; (b) the performance gap between the obtained behaviors in simulated and real environment may be significantly reduced by introducing a "conservative" form of noise; (c) if a decrease in per...

This paper discusses the feasibility of applying evolutionary methods to automatically generating controllers for physical mobile robots. We overview the state of the art in the field, describe some of the main approaches, discuss the key challenges, unanswered problems, and some promising directions. 1 Introduction This paper is concerned with the distant goal of automated synthesis of robot controllers. Specifically, we focus on the problems of evolving controllers for physically embodied and embedded systems that deal with all of the noise and uncertainly present in the world. We will also address some systems that evolve both the morphology and the controller of a robot. Within the scope of this paper we define morphology as the physical, embodied characteristics of the robot, such as its mechanics and sensor organization. Given that definition, the only examples of evolving both morphology and control exist in simulation. Evolutionary methods for automated hardware design are an ...

Co-evolution (i.e. the evolution of two or more competing populations with coupled fitness) has several features that may potentially enhance the power of adaptation of artificial evolution. In particular, as discussed by Dawkins and Krebs [3], competing populations may reciprocally drive one another to increasing levels of complexity by producing an evolutionary "arms race". In this paper we will investigate the role of co-evolution in the context of evolutionary robotics. In particular, we will try to understand in what conditions co-evolution can lead to "arms races". Moreover, we will show that in some cases artificial co-evolution has a higher adaptive power than simple evolution. Finally, by analyzing the dynamics of coevolved populations, we will show that in some circumstances well adapted individuals would be better advised to adopt simple but easily modifiable strategies suited for the current competitor strategies rather than incorporate complex and general strategies that m...

s: Jan. 1992 -- Dec. 1994 ffl CTI: Current Technology Index Jan./Feb. 1993 -- Jan./Feb. 1994 ffl DAI: Dissertation Abstracts International: Vol. 53 No. 1 -- Vol. 55 No. 4 (1994) ffl EEA: Electrical & Electronics Abstracts: Jan. 1991 -- Dec. 1994 ffl P: Index to Scientific & Technical Proceedings: Jan. 1986 -- Feb. 1995 (except Nov. 1994) ffl EI A: The Engineering Index Annual: 1987 -- 1992 ffl EI M: The Engineering Index Monthly: Jan. 1993 -- Dec. 1994 The following GA researchers have already kindly supplied their complete autobibliographies and/or proofread references to their papers: Dan Adler, Patrick Argos, Jarmo T. Alander, James E. Baker, Wolfgang Banzhaf, Ralf Bruns, I. L. Bukatova, Thomas Back, Yuval Davidor, Dipankar Dasgupta, Marco Dorigo, Bogdan Filipic, Terence C. Fogarty, David B. Fogel, Toshio Fukuda, Hugo de Garis, Robert C. Glen, David E. Goldberg, Martina Gorges-Schleuter, Jeffrey Horn, Aristides T. Hatjimihail, Mark J. Jakiela, Richard S. Judson, Akihiko Konaga...

... methodology for the automatic design of robotic controllers. EE is an evolutionary robotics (ER) technique that avoids the pitfalls of the simulate-and-transfer method, allows the speed-up of evaluation time by utilizing parallelism, and is particularly suited to future work on multi-agent behaviors. In EE, an evolutionary algorithm is distributed amongst and embodied within a population of physical robots that reproduce with one another while situated in the task environment. We have built a population of eight robots and successfully implemented our first experiments. The controllers evolved by EE compare favorably to hand-designed solutions for a simple task. We detail our methodology, report our initial results, and discuss the application of EE to more advanced and distributed robotics tasks.

We introduce Embodied Evolution (EE) as a new methodology for evolutionary robotics (ER). EE uses a population of physical robots that autonomously reproduce with one another while situated in their task environment. This constitutes a fully distributed evolutionary algorithm embodied in physical robots. Several issues identified by researchers in the evolutionary robotics community as problematic for the development of ER are alleviated by the use of a large number of robots being evaluated in parallel. Particularly, EE avoids the pitfalls of the simulate-and-transfer method and allows the speed-up of evaluation time by utilizing parallelism. The more novel features of EE are that the evolutionary algorithm is entirely decentralized, which makes it inherently scalable to large numbers of robots, and that it uses many robots in a shared task environment, which makes it an interesting platform for future work in collective robotics and Artificial Life. We have built a population of eight robots and successfully implemented the first example of Embodied Evolution by designing a fully decentralized, asynchronous evolutionary algorithm. Controllers evolved by EE outperform a hand-designed controller in a simple application. We introduce our approach and its motivations, detail our implementation and initial results, and discuss the advantages and limitations of EE. © 2002 Elsevier Science B.V. All rights reserved.

In this paper I claim that one of the main characteristics that makes the Evolutionary Robotics approach suitable for the study of adaptive behavior in natural and artificial agents is the possibility to rely largely on a self-organization process. Indeed by using Artificial Evolution the role of the designer may be limited to the specification of a fitness function which measures the ability of a given robot to perform a desired task. From an engineering point of view the main advantage of relying on self-organization is the fact that the designer does not need to divide the desired behavior into simple basic behaviors to be implemented into separate layers (or modules) of the robot control system. By selecting individuals for their ability to perform the desired behavior as a whole, simple basic behaviors can emerge from the interaction between several processes in the control system and from the interaction between the robot and the environment. From the point of view of ...

We propose that the ability to extract regularities from time series through prediction learning can be enhanced if we use a hierarchical architecture in which higher layers are trained to predict the internal state of lower layers when such states change significantly. This hierarchical organization has two functions: (a) it forces the system to progressively re-code sensory information so as to enhance useful regularities and filter out useless information; (b) it progressively reduces the length of the sequences which should be predicted going from lower to higher layers. This, in turn, allows higher levels to extract higher level regularities which are hidden at the sensory level. By training an architecture of this type to predict the next sensory state of a robot navigating in a environment divided into two rooms we show how the first level prediction layer extracts low level regularities such as `walls', `corners', and `corridors' while the second level prediction laye...

We will discuss in which conditions we can expect the emergence of agents able to integrate sensory-motor information over time and later use this information to modulate their behavior accordingly. In doing so we will illustrate the problems that these agents should be able to solve and the processes that might lead to a transition from simple agents that only rely on sensory information or on their internal dynamic to agents that are also able to integrate information over time. The analysis of evolved individuals revealed that: (1) individuals able to integrate information over time rely on mixed strategy in which basic sensory-motor mechanisms are complemented and enhanced with additional internal mechanisms; (2) evolved individuals tend to rely on partial, action-oriented, and action-mediated representations of the external environment. 1

It is well known that individual learning can speed up artificial evolution enormously. However both supervised learning and reinforcement learning require specific learning goals which usually are not available or difficult to find. We introduce a new principle -- homeokinesis -- which is completely unspecific and yet induces specific, seemingly goal--oriented behaviors of an agent in a complex external world. The principle is based on the assumption that the agent is equipped with an adaptive model of its behavior. A learning signal for both the model and the controller is derived from the misfit between the real behavior of the agent in the world and that predicted by the model. If the structural complexity of the model is chosen adequately, this misfit is minimized if the agent exhibits a smooth controlled behavior. The principle is explicated by two examples. We moreover discuss how functional modularization emerges in a natural way in a structured system from a mechanism of competition for the best internal representation.