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 …

This article comparatively tests three cooperative co-evolution methods for automated
controller design in simulated robot teams. Collective Neuro-Evolution (CONE) co-evolves …

This paper presents a flexible probabilistic model for the description of aggregation
processes in autonomous collective robotics. Two different experiments are considered: one …

In this paper, we discuss the limitations of current evolutionary robotics models and we
propose a new framework that might solve some of these problems and lead to an open …

Swarm robotics deals with the design, development, and control of multirobot system. The
individual agents of the swarm robotics system are simple, with limited capabilities in order …

Social behaviour and in particular social learning are key mechanisms for the cohesion and
evolu tion of primate societies. Similarly, social skills might be desirable for artificial agents …

The behavior-based approach has been successfully applied to designing robot control
systems. This paper presents our work, based on evolutionary algorithms, to program …

Technology is playing an increasing role in our society. Therefore it becomes important to
educate the general public, and young generations in particular, about the most common …

Tracking of miniature robotic platforms involves major challenges in image recognition and
data association. We present our 3-year effort into developing the platform-independent …

This article introduces Pyro, an open-source Python robotics toolkit for exploring topics in AI
and robotics. We present key abstractions that allow Pyro controllers to run unchanged on a …