Deep Learning for Koopman-based Dynamic Movement Primitives
This addresses the challenge of efficient robot learning from demonstration for tasks like manipulation and locomotion, though it appears incremental as it builds on existing theories.
The paper tackles the problem of teaching robots complex motions from few demonstrations by combining Koopman Operators and Dynamic Movement Primitives, achieving results comparable to Extended Dynamic Mode Decomposition on the LASA Handwriting dataset with training on only small fractions of the letters.
The challenge of teaching robots to perform dexterous manipulation, dynamic locomotion, or whole--body manipulation from a small number of demonstrations is an important research field that has attracted interest from across the robotics community. In this work, we propose a novel approach by joining the theories of Koopman Operators and Dynamic Movement Primitives to Learning from Demonstration. Our approach, named \gls{admd}, projects nonlinear dynamical systems into linear latent spaces such that a solution reproduces the desired complex motion. Use of an autoencoder in our approach enables generalizability and scalability, while the constraint to a linear system attains interpretability. Our results are comparable to the Extended Dynamic Mode Decomposition on the LASA Handwriting dataset but with training on only a small fractions of the letters.