Using probabilistic movement primitives in robotics

Abstract

Movement Primitives are a well-established\ud paradigm for modular movement representation and\ud generation. They provide a data-driven representation\ud of movements and support generalization to novel situations,\ud temporal modulation, sequencing of primitives\ud and controllers for executing the primitive on physical\ud systems. However, while many MP frameworks exhibit\ud some of these properties, there is a need for a uni-\ud fied framework that implements all of them in a principled\ud way. In this paper, we show that this goal can be\ud achieved by using a probabilistic representation. Our\ud approach models trajectory distributions learned from\ud stochastic movements. Probabilistic operations, such as\ud conditioning can be used to achieve generalization to\ud novel situations or to combine and blend movements in\ud a principled way. We derive a stochastic feedback controller\ud that reproduces the encoded variability of the\ud movement and the coupling of the degrees of freedom\ud of the robot. We evaluate and compare our approach\ud on several simulated and real robot scenarios

Learning, Generating and Adapting Wave Gestures for Expressive Human-Robot Interaction

“…We propose here a framework for learning rhythmic movements in joint angle space similar to the one in [2] for stroke-based movements. An overview of the learning method is presented in Algorithm 1.…”

“…When the offsets w 0 of the demonstrations have both negative and positive sign, a normal distribution should be fitted on the random vector X = ln w r , w θ , w 0 ⊤ instead. Similarly to [2] where the conditional probability property is exploited to modulate the trajectory in joint angle space, we modulate the wave gesture in the weight space by conditioning on a subset of the random vector X . Contrary to ProMPs a trajectory distribution can not be defined since y is not a linear transformation of X .…”

Active Learning of Probabilistic Movement Primitives

“…Otherwise, the human user is asked for a new demonstration to reach the new goal position. By utilizing ProMPs in our method instead of DMPs, we are able to achieve greater generalization capabilities [4] while leveraging the probabilistic information already encoded in the policy representation to compute confidence measures. Additionally, we are able to provide a probabilistic measure of the robot's ability to generalize a task in a given region, as opposed to [9] which can only say for a given instance whether or not the robot is confident it can execute the motion.…”

“…We utilize a formulation of ProMPs that closely parallels that of [4]. The ProMP trajectory distribution has the general form…”

Experience Reuse with Probabilistic Movement Primitives

“…Thus, the application of our approach requires a search distribution over the movement trajectories, which, for example, can be realized by parametrized movement representations with a prior distribution over the parameters. Probabilistic Movement Primitive (ProMP) [19] are such kind of representation and we thus use them for each movement trajectory distribution p(τ ) as explained further in Section III-A.…”