RHIZOME ARCHITECTURE: An Adaptive Neurobehavioral Control Architecture for Cognitive Mobile Robots—Application in a Vision-Based Indoor Robot Navigation Context

In this paper, a control architecture called Robotic Hybrid Indoor-Zone Operational ModulE (RHIZOME) is proposed as a new control paradigm capable of easy adaptation to different scenarios where a robot is able to interact with its environment and other cognitive agents while coping with possible unexpected situations. It creates a synergy of different state-of-the-art control paradigms by merging them into a neural structure, which follows a perception-action mechanism that constantly evolves because of the dynamic interaction of the robot with its environment. The RHIZOME architecture was tested on the NAO robot humanoid in an indoor vision-based navigation context. The proposed architecture was conceived, built and implemented through three different scenarios under which, three interdependent architectures emerged, each responding to different scenario constraints (deterministic and stochastic). Thanks to the generic composition, it is possible to develop it further with respect to robustness and completeness by simply adding new modules without modifying the already in-built components. Hence, it can be extended to perform other cognitive tasks. Experimental results obtained from its physical implementation show the feasibility, genericity and adaptability of the architecture.