Abstract
Dynamical movement primitives (DMPs) are one of the most popular representations for goal-directed motion primitives in robotics. They are also often used as the policy representation for policy improvement in robotics, a particular form of reinforcement learning. dmpbbo provides five software modules for the representation and optimization of dynamical movement primitives.
Highlights
Nakanishi, Pastor, Hoffmann, & Schaal (2013)) are one of the most popular representations for goal-directed motion primitives in robotics. They are often used as the policy representation for policy improvement in robotics, a particular form of reinforcement learning. dmpbbo provides five software modules for the representation and optimization of dynamical movement primitives
Dynamicalsystems/, various dynamical systems representing for instance exponential decay or spring-damper systems
Several more advanced features implemented in dmpbbo are:
Summary
1 ENSTA-ParisTech (at the time of this work) 2 Department of Advanced Robotics, Istituto Italiano di Tecnologia (IIT) J. Ijspeert, Nakanishi, & Schaal, 2002, A. Ijspeert, Nakanishi, Pastor, Hoffmann, & Schaal (2013)) are one of the most popular representations for goal-directed motion primitives in robotics. They are often used as the policy representation for policy improvement in robotics, a particular form of reinforcement learning.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have