Evolution of Adaptive-Synapse Controllers

This paper is concerned with artificial evolution of neuro-controllers with adaptive synapses for autonomous mobile robots. The method consists of encoding on the genotype a set of local modification rules that synapses obey while the robot freely moves in the environment [2]. The synaptic weights are not encoded on the genotype. In the experiments presented here, a "behavior-based fitness" function gives reproductive advantage to robots that can solve a sequential task. The results show that evolutionary adaptive controllers solve the task much faster and better than evolutionary standard (non-adaptive) controllers, that the method scales up well to large architectures whereas standard controllers do not, and that evolved adaptive controllers are not trivial and cannot be reduced to a fixed-weight network.

The evolution of communication in robot societies

Sara Mitri

Communication is fundamental to life on earth. All social organisms, from bacteria to humans, use communicative signals to coordinate their behaviors with members of their own and other species. Despite its key role in social organization, many questions regarding the evolution of communication are yet to be answered. This is in part due to the difficulty of conducting experimental evolution on social species, and the challenges in experimentally manipulating and measuring signaling and response strategies in communicating organisms. In this thesis, we circumvent these problems by using a system of experimental evolution with groups of foraging robots that could emit and perceive light to communicate. With this system, we have explored how communication can emerge and how different evolutionary conditions can determine the level of reliability of evolving signals. Our experiments revealed that foraging robots initially produced inadvertent cues providing information to other robots about the location of the food. This resulted in increased foraging efficiency, and consequently, in competition near the food, which drove the co-evolution of signaling and response strategies. The reliability of the resulting communication system was found to depend on the level of relatedness between robots in a group and the level at which they were selected. Robots that were highly related or selected at the group level evolved reliable signals. In contrast, when relatedness between robots in a group was low and selection was acting at the level of the individual, robots were selected to suppress the inadvertent cues produced while foraging. However, because of the effect of mutations, these cues were never completely suppressed and some variability in signaling was maintained. Because similar co-evolutionary processes should be common in natural systems, our findings explain why communicative strategies are so variable in many animal species when interests between them conflict. They also predict that relatedness will play an important role in the evolution of signal reliability in natural systems of communication. Additionally, our analyses have led us to devise a quantitative measure of signal reliability, which may be applied to measure reliability in natural systems of communication. The results of this study, together with an extensive review of the literature, illustrate how evolutionary robotic systems can be used to explore issues that cannot easily be studied experimentally with living organisms, and thus contribute to our understanding of biological systems.

EPFL2009

Evolutionary On-Line Self-Organization of Autonomous Robots

Dario Floreano, Joseba Urzelai

We review recent experiments in evolutionary robotics carried out in dynamic environments and across different robotic platforms. We then introduce a new evolutionary approach where robots are evolved for their ability to adapt online. Several experiments show that this new approach is much faster, more powerful, and scalable that the traditional approach.

2000

Evolution of Adaptive Synapses: Robots with Fast Adaptive Behavior in New Environments

Dario Floreano, Joseba Urzelai

This paper is concerned with adaptation capabilities of evolved neural controllers. We propose to evolve mechanisms for parameter self-organization instead of evolving the parameters themselves. The method consists of encoding a set of local adaptation rules that synapses follow while the robot freely moves in the environment. In the experiments presented here, the performance of the robot is measured in environments that are different in significant ways from those used during evolution. The results show that evolutionary adaptive controllers solve the task much faster and better than evolutionary standard fixed-weight controllers, that the method scales up well to large architectures, and that evolutionary adaptive controllers can adapt to environmental changes that involve new sensory characteristics (including transfer from simulation to reality and across different robotic platforms) and new spatial relationships.

2001

The evolution of communication in robot societies

Sara Mitri

EPFL2009