Evolving Communication in Embodied Agents: Assessment and Open Challenges

  title={Evolving Communication in Embodied Agents: Assessment and Open Challenges},
  author={Stefano Nolfi and Marco Mirolli},
  booktitle={Evolution of Communication and Language in Embodied Agents},
In this chapter we summarize the progresses that have recently been made in the study of the emergence of communication in artificial embodied agents along different dimensions, including the understanding of the adaptive roles of communication, the expressive power and organization complexity of signalling systems, the stability, robustness, and evolvability of communication, and the knowledge gain obtained with such models. Finally, we briefly discuss what we think are the most important open… 
Emergence of communication and language in evolving robots
This chapter illustrates how communication systems originate and evolve in a population of robots that adapt to a given task/environment and analysis of these synthetic experiments can help understand.
Robots, communication, and language: An overview of the Lingodroid project
An overview of the Lingodroid project, in which real and simulated robots play language games to ground concepts for effective communication about their world, is presented.
A signal-centric perspective on the evolution of symbolic communication
This work uses a simple synthetic model composed of sender and receiver agents controlled by Continuous-Time Recurrent Neural Networks, which is optimized by means of neuro-evolution to characterize signal decoding as either regression or classification, with limited and unlimited signal amplitude.
On The Evolutionary Origin of Symbolic Communication
An unbroken evolutionary pathway from a population of initially noncommunicating robots to the spontaneous emergence of symbolic communication is demonstrated, suggesting that the ability for symbolic communication could have emerged spontaneously under natural selection, without requiring cognitive pre adaptations or preexisting iconic communication schemes as previously conjectured.
ITALK - Integration and Transfer of Action and Language Knowledge in Robots
Whether a robot can be treated similar to an infant in an interaction is raised and the results confirm previous findings concerning the differences between ACI, AAI, and ARI and constitute an important empirical basis for making use of ostensive stimuli as social signals for tutoring behavior in social robotics.
Diversity, competition, extinction: the ecophysics of language change
The similarities between observed and predicted patterns indicate that an ecological theory of language is emerging, supporting (on a quantitative basis) its ecological nature, although key differences are also present.
change Diversity , competition , extinction : the ecophysics of language
References http://rsif.royalsocietypublishing.org/content/7/53/1647.full.html#ref-list-1 This article cites 82 articles, 11 of which can be accessed free Rapid response


Emergence of communication in embodied agents evolved for the ability to solve a collective navigation problem
How evolving robots develop a non-trivial communication system and exploit different communication modalities and the possibility of co-adapting the robots’ individual and social/communicative behaviour plays a key role in the development of progressively more complex and effective individuals is indicated.
Origins of Communication in Evolving Robots
Analysis of the evolutionary origins of motor and signaling behaviors indicates that signals and the meaning of the signals produced by evolved robots are grounded not only on the robots sensory-motor system but also on robots' behavioral capabilities previously acquired.
Social learning and cultural evolution in embodied and situated agents
Results demonstrate that social learning provides an adaptive advantage when individuals are allowed to learn socially from experienced individuals and individually and indicate how the iteration of a social and individual learning through out generations lead to a cumulative cultural evolutionary process.
Cumulative Cultural Evolution: Can We Ever Learn More?
This simulation integrates the iterated learning model with the Talking Heads experiment in which a population of agents evolves a language to communicate geometrical coloured objects by playing guessing games and transmitting the language from one generation to the next.
Evolution of Signaling in a Multi-Robot System: Categorization and Communication
This article describes a set of experiments in which artificial evolution is used as a means to engineer robot neuro-controllers capable of guiding groups of robots in a categorization task by producing appropriate actions.
Transition from imperatives to declara-tives in artificial communicating systems
A new simulation is introduced to bridge the gap between the two models of embodied interaction and symbolic communication, and the typology of sentences is explained from a communicative point of view, which challenges the traditional views of formalizing grammar.
From Solitary to Collective Behaviours: Decision Making and Cooperation
Artificial evolution is used to synthesise neural controllers that let a homogeneous group of robots decide when to switch from solitary to collective actions based on the information gathered through time and shows that the simultaneous presence of robots trying to decide whether to engage in a collective action or not can lead to cooperation in the decision making process itself.
Evolution of Acoustic Communication Between Two Cooperating Robots
The results of this work are a "proof-of-concept": they demonstrate that evolution can exploit a very simple sound communication system, to design the mechanisms that allow the robots cooperate by employing acoustic interactions.
Self-organisation and communication in groups of simulated and physical robots
This work presents an experimental study of self-organising behaviours for a group of robots, which exploit communication to coordinate their activities, suggesting that artificial evolution can produce behaviours that are more adaptive than those obtained with conventional design methodologies.