Deep Probabilistic Movement Primitives with a Bayesian Aggregator

Movement primitives are trainable parametric models that reproduce robotic movements starting from a limited set of demonstrations. Previous works proposed simple linear models that exhibited high sample efficiency and generalization power by allowing temporal modulation of move-ments (reproducing movements faster or slower), blending (merging two movements into one), via-point conditioning (constraining a movement to meet some particular via-points) and context conditioning (generation of movements based on an observed variable, e. g. , position of an object). Previous works have proposed neural network-based motor primitive models, having demonstrated their capacity to perform tasks with some forms of input conditioning or time-modulation representations. However, there has not been a single unified deep movement primitive's model proposed that is capable of all previous operations, limiting neural movement primitive's potential applications. This paper proposes a deep movement primitive architecture that encodes all the operations above and uses a Bayesian context aggregator that allows a more sound context conditioning and blending. Our results demonstrate our approach can scale to reproduce complex motions on a larger variety of input choices compared to baselines while maintaining operations of linear movement primitives provide.

Authors

• Michael Przystupa
• Faezeh Haghverd
• Martin Jägersand
• Samuele Tosatto

Keywords

• Limiting
• Merging
• Modulation
• Gaussian distribution
• Probabilistic logic
• Bayes methods
• Parametric statistics
• Movement Primitives
• Probabilistic Movement Primitives
• Deep Models
• Contextual Conditioning
• Object Position
• Temporal Modulation
• Movement Generation
• Primitive Model
• Neural Network
• Deep Neural Network
• Latent Variables
• Probabilistic Model
• Variety Of Contexts
• Motor Skills
• Kullback-Leibler
• Latent Space
• Linear Mode
• Latent Representation
• Variational Autoencoder
• Objects In The Scene
• Rhythmic Movements
• Latent Distribution
• Inverse Reinforcement Learning
• Simulated Task
• Real Robot
• Variational Inference
• Evidence Lower Bound
• Mean Aggregation
• Input Combinations
• Robot Configuration