Robot navigation framework based on reinforcement learning for intelligent space

Navigation in an unknown environment is still a hard problem, because mobile robots need topological maps in order to operate in the environment. Building a map of the environment while also using it for learning is of prime importance for mobile robots but until recently, it has only been confined to small-scale environments. This paper describes a mobile robot navigation framework integrated into the intelligent space environment. in the intelligent space, several distributed intelligent network devices communicate and share their information about the environment. In this environment mobile robots can be tracked with ultrasonic positioning system and the topological map can be build using laser range finders.