Learning to Sense Robustly and Act Effectively

The hypothesis of this research is that a successful cyber-physical system will need to be a learning agent, learning the properties of its sensors, effectors, and environment from its own experience, and adapting over time. Inspired by human developmental learning, we believe that foundational concepts such as Space, Object, Action, etc., are essential for such a learning agent to abstract and control the complexity of its world. To bridge the gap between continuous interaction with the physical environment, and discrete symbolic descriptions that support effective planning, the agent will need multiple representations for these foundational domains, linked by abstraction relations