Probabilistic Learning of Torque Controllers from Kinematic and Force Constraints

Abstract

When learning skills from demonstrations, one is often required to think in advance about the appropriate task representation (usually in either operational or configuration space). We here propose a probabilistic approach for simultaneously learning and synthesizing torque control commands which take into account task space, joint space and force constraints. We treat the problem by considering different torque controllers acting on the robot, whose relevance is learned probabilistically from demonstrations. This information is used to combine the controllers by exploiting the properties of Gaussian distributions, generating new torque commands that satisfy the important features of the task. We validate the approach in two experimental scenarios using 7-DoF torquecontrolled manipulators, with tasks that require the consideration of different controllers to be properly executed.

Non-parametric Imitation Learning of Robot Motor Skills

“…Since our approach employs the kernel treatment instead of the explicit basis functions, it enables the convenient extension to the learning of complex and high-dimensional trajectories. In the future, we plan to apply our approach to the concurrent imitation learning in Cartesian space and joint space [33], [34].…”

Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives

“…where Γ p are weight matrices that regulate the contribution of each individual controller. Examples of Γ p found in the literature include scalar terms that maximize external rewards [20] and precision matrices, either computed from covariance [6], [19] or uncertainty [7]. Equation (12) has an analytical solution given byû =Σ u P p=1 Γ p u p , wherê…”

“…In recent work [6], [7], we discussed a fundamental difference between the type of variance encapsulated by the predictions of classical probabilistic techniques, particularly Gaussian mixture regression (GMR) and Gaussian process regression (GPR) [8]. We showed that the variance predicted by these two techniques has distinct, complementary interpretations.…”

“…The uncertainty is further leveraged by the robot to know when different controllers, responsible for the execution of separate, elementary sub-tasks, should be activated. In particular we: 1) demonstrate that KMP predicts full covariance matrices and uncertainty (Sections III and IV-A) 2) exploit a linear quadratic regulator (LQR) formulation that yields control gains which are a function of both covariance and uncertainty (Section IV-B) 3) dovetail 1), 2) with the concept of fusion of controllers [6] which allows for demonstrating one complex task as separate sub-tasks, whose activation depends on individual uncertainty levels (Section IV-C) Experimentally, we expand on a previously published robot-assisted painting scenario and validate the approach using a KUKA LWR where different types of controllers are used for individual sub-tasks (Section V). We provide a discussion of the approach and the obtained results in Section VI and concluding remarks and possible extensions in Section VII.…”

An Uncertainty-Aware Minimal Intervention Control Strategy Learned from Demonstrations

“…In [10], Umlauft et al discuss the differences between variance being interpreted as uncertainty and variability. The topic is also covered in [11], where the different notions are exploited in scenarios that require the combination of different controllers, and in [12], in the context of robot dynamics with multiple additive noise sources. The first contribution of the present work is the exploitation of the notion of variance as uncertainty to regulate impedance gains and render the robot compliant when uncertain about its actions.…”