Learning Sensory-Motor Associations from Demonstration
This addresses the problem of enabling robots to adapt robustly from minimal demonstrations, though it appears incremental in applying reactive programming to sensory-motor learning.
The paper tackles the problem of generating reactive robot behavior from human demonstration by using the Playful programming language to represent learned behavior as sensor-motor associations, resulting in useful behaviors learned from a single demonstration covering a limited task space.
We propose a method which generates reactive robot behavior learned from human demonstration. In order to do so, we use the Playful programming language which is based on the reactive programming paradigm. This allows us to represent the learned behavior as a set of associations between sensor and motor primitives in a human readable script. Distinguishing between sensor and motor primitives introduces a supplementary level of granularity and more importantly enforces feedback, increasing adaptability and robustness. As the experimental section shows, useful behaviors may be learned from a single demonstration covering a very limited portion of the task space.