Analysis of Evolved Agents Performing Referential Communication

2009

In this paper a experiment is presented in which two simulated robots evolved a form of communication to allow one of the robots to complete the task of finding a light placed in the world. The robots are constrained so that one has inputs about the world, seeing robot, ...

Proceedings. 2004 NASA/DoD Conference on Evolvable Hardware, 2004., 2004

Sensor evolution in nature aims at improving the acquisition of information from the environment and is intimately related with selection pressure towards adaptivity and robustness. Recent work in the area aims at studying the perception-action loop in a formalized informationtheoretic manner. This paves the way towards a principled and general understanding of the mechanisms guiding the evolution of sensors in nature and provides insights into the design of mechanisms of artificial sensor evolution.

Lecture Notes in Computer Science, 2007

Artificial agents controlled by dynamic recurrent node networks with fixed weights are evolved to search for food and associate it with one of two different temperatures depending on experience. The task requires either instrumental or classical conditioned responses to be learned. The paper extends previous work in this area by requiring that a situated agent be capable of re-learning during its lifetime. We analyse the best-evolved agent's behaviour and explain in some depth how it arises from the dynamics of the coupled agent-environment system.

2006

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 allow 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.

2003

The paper surveys some of the mechanisms that have been demonstrated to be relevant for evolving communication systems in software simulations or robotic experiments. In each case, precursors or parallels with work in the study of artificial life and adaptive behaviour are discussed.

ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference, 2023

Referential communication is a complex form of social interaction that communicates a spatially or temporally distant referent. Previous modeling practices have studied how artificial agents manage to communicate locations that directly determine foraging behaviors. In our study, we introduce conceptual referential communication. In this mode of referential communication, communicated information can lead to behaviors that change flexibly to suit the environment. Instead of giving specific behavioral instructions, this mode only communicates a label of the desired referent, the location of which is unknown to both the sender and receiver. This requires the signal receiver to adjust its foraging behavior based on its own exploration of the environment. We evolve artificial dynamical agents that can communicate 2 and 3 different labels and successfully forage the target label in changing environments. We found that a typical strategy to communicate and differentiate labels in our experiments is by varying the numbers and lengths of contacts between the agents. We also identify several ways in which the receiver develops inter-neurons that differentiate and store information both from communication and the environment.

1993

This paper shows how a mixture of qualitative and quantitative analysis can be used to understand a particular brand of arbitrarily recurrent continuous dynamical neural network used to generate robust behaviours in autonomous mobile robots. These networks have been evolved in an open-ended way using an extended form of genetic algorithm. After brie y covering the background to our research, properties of special frequently occurring subnetworks are analysed mathematically. Networks evolved to control simple robots with low resolution sensing are then analysed using a combination of knowledge of these mathematical properties and careful interpretation of time plots of sensor, neuron and motor activities.

Information-theoretic techniques have received much recent attention as tools for the analysis of embodied agents. However, while techniques for quantifying static information structure are well-established, the application of information theory to the analysis of temporal behavior is still in its infancy. Here we formulate a novel information-theoretic approach for analyzing the dynamics of information flow in embodied systems. To demonstrate our approach, we apply it to analyze a previously evolved model of relational categorization. The results of this analysis demonstrate the unique strengths of our approach for exploring the detailed structure of information dynamics, and point towards a natural synergy between temporally-extended information theory and dynamical systems theory.

2007

In order to solve a collective task, a team of mobile autonomous robots needs to communicate with each other and with the environment. The creation of suitable control programs for these robots through evolutionary search requires knowledge about the prerequisites and environmental factors which drive the evolutionary process toward the development of effective communication. Since a lot of key features about the nature of the task, the capacities of the robots and the evolutionary forces are relatively unknown, it is not trivial which characteristics of a task stimulate a group of robots to develop a functional communication system. To gain insight in these questions a model is proposed which embodies some of the (presumably) key aspects that influence the development of communication. From this model a series of experimental setups is derived which is tested in a simulator (EvoRobot). Results show that it is hard to isolate different task dimensions because the presence of one aspect influences the usefulness of communication in relation to the other aspects. Nevertheless, it can be concluded that the most influential aspect that boosts the use of communication is the possibility for robots to have access to information which is useful for other robots. Next to this, the aim of this thesis is to investigate the characteristics of evolved communication systems and the level of complexity that can be achieved. Thus, various aspects of complexity on both the task setup and the resulting communication system are discussed and based on this a more complex task is developed. This results in a rich communication system which includes selective attention, different functional roles and integration of multiple communication channels. In order to strengthen findings in simulation, evolved behaviors are then transferred onto e-Puck robots.

2004