Active Learning of Bayesian Probabilistic Movement Primitives

Learning from Demonstration permits non-expert users to easily and intuitively reprogram robots. Among approaches embracing this paradigm, probabilistic movement primitives (ProMPs) are a well-established and widely used method to learn trajectory distributions. However, providing or requesting useful demonstrations is not easy, as quantifying what constitutes a good demonstration in terms of generalization capabilities is not trivial. In this paper, we propose an active learning method for contextual ProMPs for addressing this problem. More specifically, we learn the trajectory distributions using a Bayesian Gaussian mixture model (BGMM) and then leverage the notion of epistemic uncertainties to iteratively choose new context query points for demonstrations. We show that this approach reduces the required number of human demonstrations. We demonstrate the effectiveness of the approach on a pouring task, both in simulation and on a real 7-DoF Franka Emika robot.

Continuous extraction of task constraints in a robot programming by demonstration framework

Sylvain Calinon

Robot Programming by Demonstration (RbD), also referred to as Learning by Imitation, explores user-friendly means of teaching a robot new skills. Recent advances in RbD have identified a number of key-issues for ensuring a generic approach to the transfer of skills across various agents and contexts. This thesis focuses on the two generic questions of what-to-imitate and how-to-imitate, which are respectively concerned with the problem of extracting the essential features of a task and determining a way to reproduce these essential features in different situations. The perspective adopted in this work is that a skill can be described efficiently at a trajectory level and that the robot may infer what are the important characteristics of the skill by observing multiple demonstrations of it, assuming that the important characteristics are invariant across the demonstrations. The proposed approach is based on the use of well-established statistical methods in a RbD application, by using Hidden Markov Model (HMM) as a first approach and then moving on to the joint use of Gaussian Mixture Model (GMM) and Gaussian Mixture Regression (GMR). Even if these methods were applied extensively in various fields of research including human motion analysis and robotics, their use essentially focused on gesture recognition rather than on gesture reproduction. Moreover, the models were usually trained offline using large datasets. Thus, the use and combination of these machine learning techniques in a Learning by Imitation framework is challenging and has not been extensively studied yet. In this thesis, we show that these methods are well suited for incremental and active teaching scenarios where the user only provides a small number of demonstrations, either by wearing a set of motions sensors attached to his/her body, or by helping the robot refine its skill by kinesthetic teaching, that is, by embodying the robot and putting it through the motion. These techniques are then applied for enabling a Fujitsu HOAP-2 and HOAP-3 humanoid robot to extract automatically different constraints by observing several manipulation skills and to reproduce these skills in various situations through Gaussian Mixture Regression (GMR). The contributions of this thesis are threefold: (1) it contributes to RbD by proposing a generic probabilistic framework to deal with recognition, generalization, reproduction and evaluation issues, and more specifically to deal with the automatic extraction of task constraints and with the determination of a controller satisfying several constraints simultaneously to reproduce the skill in a different context; (2) it contributes to Human-Robot Interaction (HRI) by proposing active teaching methods that puts the human teacher "in the loop" of the robot's learning by using an incremental scaffolding process and by using different modalities to produce the demonstrations; (3) it finally contributes to robotics and HRI through various real-world applications of the framework showing learning and reproduction of communicative gestures and manipulation skills. The generality of the proposed framework is also demonstrated through its joint use with other learning approaches in collaborative experiments.

EPFL2007

Sparse Linear Models: Variational Approximate Inference and Bayesian Experimental Design

Matthias Seeger

A wide range of problems such as signal reconstruction, denoising, source separation, feature selection, and graphical model search are addressed today by posterior maximization for linear models with sparsity-favouring prior distributions. The Bayesian posterior contains useful information far beyond its mode, which can be used to drive methods for sampling optimization (active learning), feature relevance ranking, or hyperparameter estimation, if only this representation of uncertainty can be approximated in a tractable manner. In this paper, we review recent results for variational sparse inference, and show that they share underlying computational primitives. We discuss how sampling optimization can be implemented as sequential Bayesian experimental design. While there has been tremendous recent activity to develop sparse estimation, little attendance has been given to sparse approximate inference. In this paper, we argue that many problems in practice, such as compressive sensing for real-world image reconstruction, are served much better by proper uncertainty approximations than by ever more aggressive sparse estimation algorithms. Moreover, since some variational inference methods have been given strong convex optimization characterizations recently, theoretical analysis may become possible, promising new insights into nonlinear experimental design.

2009

Continuous extraction of task constraints in a robot programming by demonstration framework

Sylvain Calinon

EPFL2007