A Neural Schema Architecture for Autonomous Robots

Abstract

As autonomous robots become more complex in their behavior, more sophisticated software
\narchitectures are required to support the ever more sophisticated robotics software. These
\nsoftware architectures must support complex behaviors involving adaptation and learning,
\nimplemented, in particular, by neural networks. We present in this paper a neural based schema
\n[2] software architecture for the development and execution of autonomous robots in both
\nsimulated and real worlds. This architecture has been developed in the context of adaptive
\nrobotic agents, ecological robots [6], cooperating and competing with each other in adapting to
\ntheir environment. The architecture is the result of integrating a number of development and
\nexecution systems: NSL, a neural simulation language; ASL, an abstract schema language; and
\nMissionLab, a schema-based mission-oriented simulation and robot system. This work
\ncontributes to modeling in Brain Theory (BT) and Cognitive Psychology, with applications in
\nDistributed Artificial Intelligence (DAI), Autonomous Agents and Robotics.