Evaluating Sensorimotor Abstraction on Curricula for Learning Mobile Manipulation Skills

Developmental mechanisms in newborn animals shepherd the infant through interactions with the world that form the foundation for hierarchical skills. An important part of this guidance resides in mechanisms of growth and maturation, wherein patterns of sensory and motor recruitment constrain learning complexity while building foundational expertise and transferable control knowledge. The resulting control policies represent a sensorimotor state abstraction that can be leveraged when developing new behaviors. This paper uses a computational model of developmental learning with parameters for controlling the recruitment of sensory and motor resources, and evaluates how this influences sample efficiency and fitness for a specific mobile manipulation task. We find that a developmental curriculum driven by sensorimotor abstraction drastically improves (by up to an order of magnitude) learning performance and sample efficiency over non-developmental approaches. Additionally, we find that the developmental policies/state abstractions offer significant robustness properties, enabling skill transfer to novel domains without additional training.