Corpus ID: 13083455

Probabilistic Movement Primitives

@inproceedings{Paraschos2013ProbabilisticMP,
  title={Probabilistic Movement Primitives},
  author={A. Paraschos and Christian Daniel and Jan Peters and G. Neumann},
  booktitle={NIPS},
  year={2013}
}
Movement Primitives (MP) are a well-established approach for representing modular and re-usable robot movement generators. [...] Key Method We present a probabilistic formulation of the MP concept that maintains a distribution over trajectories. Our probabilistic approach allows for the derivation of new operations which are essential for implementing all aforementioned properties in one framework.Expand
Using probabilistic movement primitives in robotics
TLDR
A stochastic feedback controller is derived that reproduces the encoded variability of the movement and the coupling of the degrees of freedom of the robot by using a probabilistic representation. Expand
Learning Via-Point Movement Primitives with Inter- and Extrapolation Capabilities
TLDR
A new simple but efficient formulation of MPs is proposed, the Via-points Movement Primitive (VMP), that can adapt to arbitrary via-points using a simple structured model that is based on the previous approaches but outperforms those in terms of extrapolation abilities. Expand
Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation
TLDR
A generic probabilistic framework for adapting ProMPs is proposed and is formulated as a constrained optimisation problem where the Kullback-Leibler divergence between the adapted distribution and the distribution of the original primitive is minimised and the probability mass associated with undesired trajectories is constrain to be low. Expand
Extracting low-dimensional control variables for movement primitives
TLDR
This paper uses hierarchical Bayesian models (HBMs) to estimate a low dimensional latent variable model for probabilistic movement primitives (ProMPs), which is a recent movement primitive representation and extends the HBM by a mixture model, such that it can model different movement types in the same dataset. Expand
Model-free Probabilistic Movement Primitives for physical interaction
TLDR
The model-free ProMPs are introduced, that are learning jointly the movement and the necessary actions from a few demonstrations, and derive a variable stiffness controller analytically. Expand
Combination of Movement Primitives for Robotics Kombination von Movement Primitives in der Robotik
Probabilistic Movement Primitives (ProMPs) are a promising approach to represent movements. ProMPs can capture the variance of the movements and can be trained by immitation learning. Additionally,Expand
Using probabilistic movement primitives for striking movements
TLDR
A method to adapt a probability distribution of hitting movements learned in joint space to have a desired end effector position, velocity and orientation and a method to find the initial time and duration of the movement primitive in order to intercept a moving object like the table tennis ball. Expand
Adaptation and Robust Learning of Probabilistic Movement Primitives
TLDR
This article makes use of prior distributions over the parameters of a probabilistic movement primitive to make robust estimates of the parameters with few training instances, and introduces general purpose operators to adapt movement primitives in joint and task space. Expand
Demonstration-free contextualized probabilistic movement primitives, further enhanced with obstacle avoidance
  • Adrià Colomé, C. Torras
  • Computer Science
  • 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2017
TLDR
A contextual representation of ProMPs is proposed that allows for an easy adaptation to changing situations through context variables, by reparametrizing motion with them and a simple yet effective quadratic optimization-based obstacle avoidance method is proposed. Expand
Probabilistic movement primitives under unknown system dynamics
TLDR
This work presents a reformulation of the ProMPs that allows accurate reproduction of the skill without modeling the system dynamics and derives a variable-stiffness controller in closed form that reproduces the trajectory distribution and the interaction forces present in the demonstrations. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 27 REFERENCES
A probabilistic approach to robot trajectory generation
TLDR
A probabilistic movement primitive approach that overcomes the limitations of existing approaches that allows performing new operations - a product of distributions for the co-activation of MPs conditioning for generalizing the MP to different desired targets. Expand
Learned graphical models for probabilistic planning provide a new class of movement primitives
TLDR
This work proposes an alternative MP representation based on probabilistic inference in learned graphical models with new and interesting properties that complies with salient features of biological movement control, integrating the power of stochastic optimal control (SOC) methods within a MP. Expand
Learning Movement Primitives
TLDR
A novel reinforcement learning technique based on natural stochastic policy gradients allows a general approach of improving DMPs by trial and error learning with respect to almost arbitrary optimization criteria, and demonstrates the different ingredients of the DMP approach in various examples. Expand
Task-Specific Generalization of Discrete and Periodic Dynamic Movement Primitives
TLDR
3-D vision on humanoid robots with complex oculomotor systems is often difficult due to the modeling uncertainties, but it is shown that these uncertainties can be accounted for by the proposed approach. Expand
Policy Search for Motor Primitives in Robotics
TLDR
This paper extends previous work on policy learning from the immediate reward case to episodic reinforcement learning, resulting in a general, common framework also connected to policy gradient methods and yielding a novel algorithm for policy learning that is particularly well-suited for dynamic motor primitives. Expand
Modelling motion primitives and their timing in biologically executed movements
TLDR
This work shows how the coupling of the low level primitive model, and the higher level timing model during inference can produce good reconstructions of handwriting, with shared primitives for all characters modelled. Expand
Learning Attractor Landscapes for Learning Motor Primitives
TLDR
By nonlinearly transforming the canonical attractor dynamics using techniques from nonparametric regression, almost arbitrary new nonlinear policies can be generated without losing the stability properties of the canonical system. Expand
Learning Collaborative Impedance-Based Robot Behaviors
TLDR
The results show that the model can be used to modify the robot impedance along task execution to facilitate the collaboration, by triggering stiff and compliant behaviors in an on-line manner to adapt to the user's actions. Expand
Robot trajectory optimization using approximate inference
TLDR
This work considers a probabilistic model for which the maximum likelihood (ML) trajectory coincides with the optimal trajectory and which reproduces the classical SOC solution and utilizes approximate inference methods that efficiently generalize to non-LQG systems. Expand
Robot motor skill coordination with EM-based Reinforcement Learning
TLDR
An approach allowing a robot to acquire new motor skills by learning the couplings across motor control variables through Expectation-Maximization based Reinforcement Learning is presented. Expand
...
1
2
3
...