A salient feature of human motor skill learning is the ability to exploit similarities across related tasks. In biological motor control, it has been hypothesized that muscle synergies, coherent activations of groups of muscles, allow for exploiting shared knowledge. Recent studies have shown that a rich set of complex motor skills can be generated by a combination of a small number of muscle synergies. In robotics, dynamic movement primitives are commonly used for motor skill learning. This machine learning approach implements a stable attractor system that facilitates learning and it can be used in high-dimensional continuous spaces. However, it does not allow for reusing shared knowledge, i.e. for each task an individual set of parameters has to be learned. We propose a novel movement primitive representation that employs parametrized basis functions, which combines the benefits of muscle synergies and dynamic movement primitives. For each task a superposition of synergies modulates a stable attractor system. This approach leads to a compact representation of multiple motor skills and at the same time enables efficient learning in high-dimensional continuous systems. The movement representation supports discrete and rhythmic movements and in particular includes the dynamic movement primitive approach as a special case. We demonstrate the feasibility of the movement representation in three multi-task learning simulated scenarios. First, the characteristics of the proposed representation are illustrated in a point-mass task. Second, in complex humanoid walking experiments, multiple walking patterns with different step heights are learned robustly and efficiently. Finally, in a multi-directional reaching task simulated with a musculoskeletal model of the human arm, we show how the proposed movement primitives can be used to learn appropriate muscle excitation patterns and to generalize effectively to new reaching skills.
Provides a musculoskeletal arm model with eleven muscles and an easy to use Matlab interface to run forward dynamics simulations.
In this project we study a salient feature of human motor skill learning that is the ability to exploit similarities across related tasks. We test this concept in forward dynamics simulations of multiple reaching movements of a musculoskeletal arm model with eleven muscles. The eleven muscle activation patterns are generated by a combination of parametrized muscle synergies, where these synergies encode a shared prior among multiple reaching directions.
A musculoskeletal arm model with eleven muscles and a Matlab interface are provided to run forward dynamic simulations of reaching tasks. The Matlab interface (mex-file) takes muscle excitation patterns as input and returns 3D marker coordinates (the marker is placed on the radial stylion). The mex-file can be easily changed to receive other quantities in a forward dynamic simulation.See all Downloads