A Qualitative Representation of Structural Spatial Knowledge for Robot Navigation with Reinforcement Learning

摘要

In robot navigation tasks, the representation of knowledge of the surrounding world plays an important role, especially in reinforcement learning approaches. This work presents a qualitative representation of space that empowers an agent to learn a goal-directed navigation strategy based on structural knowledge of the world that leads to a generally sensible navigation behavior that can be transferred to completely unknown environments. 1.