1,720,970 research outputs found
Derivative-free online learning of inverse dynamics models
No full textThis paper discusses online algorithms for inverse dynamics modeling in robotics. Several model classes, including rigid body dynamics models, data-driven models and semiparametric models (which are combination of the previous two classes), are placed in a common framework. While model classes used in the literature typically exploit joint velocities and accelerations, which needs to be approximated resorting to numerical differentiation schemes, in this paper, a new 'derivative-free' (DF) framework is proposed, which does not require this preprocessing step. An extensive experimental study with real data from the right arm of the iCub robot is presented, comparing different model classes and estimation procedures, showing that the proposed DF methods outperform existing methodologies
Online semi-parametric learning for inverse dynamics modeling
No full textThis paper presents a semi-parametric algorithm for online learning of a robot inverse dynamics model. It combines the strength of the parametric and non-parametric modeling. The former exploits the rigid body dynamics equation, while the latter exploits a suitable kernel function. We provide an extensive comparison with other methods from the literature using real data from the iCub humanoid robot. In doing so we also compare two different techniques, namely cross validation and marginal likelihood optimization, for estimating the hyperparameters of the kernel function
DECAF: A Discrete-Event based Collaborative Human-Robot Framework for Furniture Assembly
No full textThis paper proposes a task planning framework for collaborative Human-Robot scenarios, specifically focused on assembling complex systems such as furniture. The human is characterized as an uncontrollable agent, implying for example that the agent is not bound by a pre-established sequence of actions and instead acts according to its own preferences. Meanwhile, the task planner computes reactively the optimal actions for the collaborative robot to efficiently complete the entire assembly task in the least time possible.We formalize the problem as a Discrete Event Markov Decision Problem (DE-MDP), a comprehensive framework that incorporates a variety of asynchronous behaviors, human change of mind, and failure recovery as stochastic events. Although the problem could theoretically be addressed by constructing a graph of all possible actions, such an approach would be constrained by computational limitations. The proposed formulation offers an alternative solution utilizing Reinforcement Learning to derive an optimal policy for the robot. Experiments were conducted both in simulation and on a real system with human subjects assembling a chair in collaboration with a 7-DoF manipulator
MODEL-BASED ASSESSMENT OF EXERCISE EFFECT ON INSULIN-INDEPENDENT AND INSULIN-DEPENDENT GLUCOSE UTILIZATION IN HEALTHY SUBJECTS
No full textExercise effect on insulin-dependent and insulin-independent glucose utilization in healthy individuals and individuals with type 1 diabetes: A modeling study
No full textExercise effects (EE) on whole body glucose rate of disappearance (Rd) occur through insulin-independent (IIRd) and insulin-dependent (IDRd) mechanisms. Quantifying these processes in vivo would allow a better understanding of the physiology of glucose regulation. This is of particular importance in individuals with type 1 diabetes (T1D) since such a knowledge may help to improve glucose management. However, such a model is still lacking. Here, we analyzed data from six T1D and six nondiabetic (ND) subjects undergoing a labeled glucose clamp study during, before, and after a 60-min exercise session at 65% VO2max on three randomized visits: euglycemia-low insulin, euglycemia-high insulin, and hyperglycemia-low insulin. We tested a set of models, all sharing a single-compartment description of glucose kinetics, but differing in how exercise is assumed to modulate glucose disposal. Model selection was based on parsimony criteria. The best model assumed an exercise-induced immediate effect on IIRd and a delayed effect on IDRd. It predicted that exercise increases IIRd, compared with rest, by 66%–82% and 67%–97% in T1D and ND, respectively, not significantly different between the two groups. Conversely, the exercise effect on IDRd ranged between 81% and 155% in T1D and it was significantly higher than ND, which ranged between 10% and 40%. The exaggerated effect observed in IDRd can explain the higher hypoglycemia risk related to individuals with T1D. This novel exercise model could help in informing safe and effective glucose management during and after exercise in individuals with T1D
Kernel Methods and Gaussian Processes for System Identification and Control: A Road Map on Regularized Kernel-Based Learning for Control
No full textThe commonly adopted route to control a dynamic system and make it follow the desired behavior consists of two steps. First, a model of the system is learned from input-output data, a task known as system identification in the engineering literature. Here, an important point is not only to derive a nominal model of the plant but also confidence bounds around it. The information coming from the first step is then exploited to design a controller that should guarantee a certain performance also under the uncertainty affecting the model. This classical way to control dynamic systems has recently been the subject of new intense research, thanks to an interesting cross-fertilization with the field of machine learning. New system identification and control techniques have been developed with links to function estimation and mathematical foundations in reproducing kernel Hilbert spaces (RKHSs) and Gaussian processes (GPs). This has become known as the Gaussian regression (kernel-based) approach to system identification and control. It is the purpose of this article to give an overview of this development (see 'Summary')
Effects of glucagon concentrations on splanchnic and leg glucagon uptake in healthy humans.
No full textLagrangian Inspired Polynomial Estimator for black-box learning and control of underactuated systems
Full text linkThe Lagrangian Inspired Polynomial (LIP) estimator Giacomuzzo et al. (2023) is a black-box estimator based on Gaussian Process Regression, recently presented for the inverse dynamics identification of Lagrangian systems. It relies on a novel multi-output kernel that embeds the structure of the Euler-Lagrange equation. In this work, we extend its analysis to the class of underactuated robots. First, we show that, despite being a black-box model, the LIP allows estimating kinetic and potential energies, as well as the inertial, Coriolis, and gravity components directly from the overall torque measures. Then we exploit these properties to derive a two-stage energy-based controller for the swing-up and stabilization of balancing robots. Experimental results on a simulated Pendubot confirm the feasibility of the proposed approach
Exercise effect on endogenous glucose production in type 1 diabetes: a modeling analysis.
No full text- …
