From adaptive software bahaviour to adaptive robotic bahaviour

Maintenance accounts for a major cost of software development. The design of software systems from the very beginning phase to achieve adaptive behaviour should, therefore, be recognised of its importance in practice. Adaptive Agent Model (AAM) is aimed towards this end via using Agent-oriented Model-Driven Architecture. Models are derived from requirements and reconfigured continuously by domain experts to reflect changing business needs. Agents interpret these models, at runtime, to choose alternative partners in collaboration or reusable components in computation, in an adaptive manner. Adopting an event-driven architecture at runtime, AAM has its agents and knowledge-based control readily applicable to robots and their on-board control extension. The paper describes work towards this goal and ultimately, this will demonstrate the feasibility of AAM in software adaptivity via the robot platform, and also help to achieve robot adaptivity through corresponding AAM support.