What Your Body and Your Living Room Tell My Agent

This paper proposes a class of software agent architectures capable of playing some of beneficial roles embodiment accomplishes in living beings. These are component based architectures including sensors, actuators, emotion eliciting mechanisms and action control mechanisms. These architectures through their yellow pages and log services, which maintain updated information about the agent body and its dynamics, provide the means for the soft-visual appearance required for non-verbal communication and for learning through imitation. Component based architectures fulfil the requirement of efficient execution of agent functions in parallel and the possibility of using simplifying sensory-motor coordination. All components of architectures of the proposed class share the same goal of preserving the plans for the adaptive and situated construction of the agent. This feature plays the role of the body as an inner source of motives, enables the agent to have feelings and emotions, and allows the agent to centrifugally construct itself, avoiding non-grounding meta-control processes. Finally the proposed class of architectures integrate several learning mechanisms necessary for learning through imitation, for learning through direct manipulation of objects, for learning correlations among and computational complexity of the several aspects of the task and the environment, which allows the agent to replace slow with fast computations. 1