We propose the use of probabilistic context-free grammars to sequence a series of primitives to generate complex robot policies from a given library of ...

In this work, we exploit the physical nature of robot movement primitives to restrict and efficiently search the grammar space. The grammar is learned applying ...

Abstract—Movement Primitives are a well studied and widely applied concept in modern robotics. Composing prim- itives out of an existing library, however, ...

Inducing Probabilistic Context-Free Grammars for the Sequencing of Robot Movement Primitives. R. Lioutikov , G. Maeda , F.F. Veiga , K. Kersting , J. Peters.

May 21, 2018 · In this work, we exploit the physical nature of robot movement primitives to restrict and efficiently search the grammar space. The grammar is ...

The physical nature of robot movement primitives is exploited to restrict and efficiently search the grammar space, and the grammar is learned with Markov ...

Structured task plans typically encode the patterns and constraints in the sub-tasks or primitives and take the robot from an initial state to the goal state. .

However, the induction of context-free grammars has proven to be a complicated and yet unsolved challenge. We exploit the physical nature of robot movement ...

grammar is induced that sequences primitives in order to pick up a stone and ... probabilistic context-free grammars for primitive sequencing, our work ...

Nov 17, 2019 · We propose the use of probabilistic context-free grammars to sequence a series of primitives to generate complex robot policies from a given library of ...