Grounding adaptive language games in robotic agents.

1 Introduction 2 Adaptive Language Games (1) VUB AI Laboratory, Pleinlaan 2, 1050 Brussels, steels@arti.vub.ac.be, paul@arti.vub.ac.be (2) SONY Computer Science Laboratory 6 Rue Amyot, Paris The paper addresses the question how a group of physically embodied robotic agents may originate meaning and language through adaptive language games. The main principles underlying the approach are sketched as well as the steps needed to implement these principles on physical agents. Some experimental results based on this implementation are presented. In the past five years, a large number of robotic agents, i.e. physical systems capable of sensori-motor control, have been built in order to investigate a bottom-up approach to artificial intelligence (see the overview in 7). Important results have been achieved, particularly by using behavior-oriented architectures 12 and learning methods based on neural networks 5 or genetic algorithms 2. Nevertheless, it is still largely an...