843 research outputs found
A Black-Box Physics-Informed Estimator Based on Gaussian Process Regression for Robot Inverse Dynamics Identification
No full textLearning the inverse dynamics of robots directly from data, adopting a black-box approach, is interesting for several real-world scenarios where limited knowledge about the system is available. In this article, we propose a black-box model based on Gaussian process (GP) regression for the identification of the inverse dynamics of robotic manipulators. The proposed model relies on a novel multidimensional kernel, called Lagrangian Inspired Polynomial (LIP) kernel. The LIP kernel is based on two main ideas. First, instead of directly modeling the inverse dynamics components, we model as GPs the kinetic and potential energy of the system. The GP prior on the inverse dynamics components is derived from those on the energies by applying the properties of GPs under linear operators. Second, as regards the energy prior definition, we prove a polynomial structure of the kinetic and potential energy, and we derive a polynomial kernel that encodes this property. As a consequence, the proposed model allows also to estimate the kinetic and potential energy without requiring any label on these quantities. Results on simulation and on two real robotic manipulators, namely a 7 DOF Franka Emika Panda, and a 6 DOF MELFA RV4FL, show that the proposed model outperforms state-of-the-art black-box estimators based both on Gaussian processes and neural networks in terms of accuracy, generality, and data efficiency. The experiments on the MELFA robot also demonstrate that our approach achieves performance comparable to fine-tuned model-based estimators, despite requiring less prior information. The code of the proposed model is publicly available
Accelerating Model-Based Reinforcement Learning using Non-Linear Trajectory Optimization
No full textThis paper addresses the slow policy optimization convergence of Monte Carlo Probabilistic Inference for Learning Control (MC-PILCO), a state-of-the-art model-based reinforcement learning (MBRL) algorithm, by integrating it with iterative Linear Quadratic Regulator (iLQR), a fast trajectory optimization method suitable for nonlinear systems. The proposed method, Exploration-Boosted MC-PILCO (EB-MC-PILCO), leverages iLQR to generate informative, exploratory trajectories and initialize the policy, significantly reducing the number of required optimization steps. Experiments on the cart-pole task demonstrate that EB-MC-PILCO accelerates convergence compared to standard MC-PILCO, achieving up to 45.9% reduction in execution time when both methods solve the task in four trials. EB-MC-PILCO also maintains a 100% success rate across trials while solving the task faster, even in cases where MC-PILCO converges in fewer iterations
Adaptive Robust Controller for handling Unknown Uncertainty of Robotic Manipulators
No full textThe ability to achieve precise and smooth trajectory tracking is crucial for ensuring the successful execution of various tasks involving robotic manipulators. State-of-the-art techniques require accurate mathematical models of the robot dynamics, and robustness to model uncertainties is achieved by relying on precise bounds on the model mismatch. In this paper, we propose a novel adaptive robust feedback linearization scheme able to compensate for model uncertainties without any a-priori knowledge on them, and we provide a theoretical proof of convergence under mild assumptions. We evaluate the method on a simulated RR robot. First, we consider a nominal model with known model mismatch, which allows us to compare our strategy with state-of-the-art uncertainty-aware methods. Second, we implement the proposed control law in combination with a learned model, for which uncertainty bounds are not available. Results show that our method leads to performance comparable to uncertainty-aware methods while requiring less prior knowledge
Motor-level Nonlinear Model Predictive Control for a Tilting Quadrotor
No full textThis work presents a novel motor-level Nonlinear Model Predictive Control trajectory tracking controller for an over-actuated quadrotor with tilting propellers. The proposed controller directly provides the motor-level commands for both the tilting and the spinning of the propellers. Moreover, it optimally solves the control allocation problem arising from the system’s over-actuation taking into account the physical constraints of the platform. Leveraging a look-ahead strategy combined with the knowledge of the actuation limits, the proposed solution fully exploits the vehicle capabilities and accurately tracks the desired reference. Simulation results show that the solution proposed outperforms a state-of-the-art controller based on Feedback Linearization, in terms of both trajectory tracking and robustness to unmodeled dynamics
Embedding the Physics in Black-box Inverse Dynamics Identification: a Comparison Between Gaussian Processes and Neural Networks
No full textIn recent years, black-box estimators for robot inverse dynamics have drawn the attention of the robotics community. This paper compares two recent black-box approaches that try to improve generalization and data efficiency by embedding the physical laws governing the system dynamics in two different ways. The so-called Deep Lagrangian Networks (DeLaNs) impose the structure of the Lagrangian equations but do not constrain the basis functions used to model the dynamics. Instead, the Gaussian process model based on the recently introduced Geometrically Inspired Polynomial (GIP) kernel constrains the basis functions of the regression problem to a physically inspired finite-dimensional space but does not force structural properties to be guaranteed. We carried out extensive experiments both on simulated and real manipulators with increasing degrees of freedom (DOF). Our results show that: (i) the accuracy of the DeLaNs model deteriorates much more rapidly than the one of the GIP kernel mod..
Fine morphology of the myrmecophilous larva of Paussus kannegieteri (Coleoptera: Carabidae: Paussinae: Paussini). Corresponding author
No full textFIGURES 13–18. Paussus kannegieteri third instar larva: 13, thorax, left lateral view; 14, thorax, dorsal view; 15, mesothoracic spiracle; 16, metathoracic spiracle-like structure; 17, mesothoracic leg, anterolateral view; 18, apex of metathoracic leg with lanceolate setae, posterolateral view. CO = coxa, ls = lanceolate setae, m = membrane, ME = mesonotum, MT = metanotum, pe = peritreme, PR = pronotum, un = claw. Scale bars: Figs. 13–14 = 500 µm; Fig. 15 = 10 µm; Fig. 16 = 20 µm; Fig. 17 = 200 µm; Fig. 18 = 50 µm.Published as part of Giulio, Andrea Di, 2008, Fine morphology of the myrmecophilous larva of Paussus kannegieteri (Coleoptera: Carabidae: Paussinae: Paussini), pp. 37-50 in Zootaxa 1741 on page 44, DOI: 10.5281/zenodo.18152
Forward Dynamics Estimation from Data-Driven Inverse Dynamics Learning ??
No full textIn this paper, we propose to estimate the forward dynamics equations of mechanical systems by learning a model of the inverse dynamics and estimating individual dynamics components from it. We revisit the classical formulation of rigid body dynamics in order to extrapolate the physical dynamical components, such as inertial and gravitational components, from an inverse dynamics model. After estimating the dynamical components, the forward dynamics can be computed in closed form as a function of the learned inverse dynamics. We tested the proposed method with several machine learning models based on Gaussian Process Regression and compared them with the standard approach of learning the forward dynamics directly. Results on two simulated robotic manipulators, a PANDA Franka Emika and a UR10, show the effectiveness of the proposed method in learning the forward dynamics, both in terms of accuracy as well as in opening the possibility of using more structured models
GIULIO TARRA TRADUTTORE DAL FRANCESE
No full textCon Il Libro pel bambino, Don Giulio Tarra risultò il vincitore di due concorsi indetti dal Congresso Pedagogico Italiano nel 1861: quello per un libro di lettura destinato ai bambini sordomuti e l’altro per un libro destinato alle scuole rurali. Fra le opere del Tarra pubblicate da Paolo Carrara è menzionato il volumetto “Lezioni in famiglia, versione da M. Carraud”. Questo contributo intende offrire alcuni elementi d’informazione su Zulma Carraud, autrice delle Historiettes véritables pour les enfants de quatre à huit ans, titolo originale della raccolta di racconti tradotta da Don Giulio. Il libro era uscito a Parigi nel 1864 per i tipi di Hachette. In precedenza lo stesso editore aveva accolto le prime opere di Zulma nelle collane destinate alla scuola primaria. A pochi anni di distanza l’uno dall’altra, la Carraud nella Francia del II Impero e il Tarra nell’Italia postunitaria, entrambi hanno contribuito con i loro “libri di lettura” allo sviluppo dell’editoria per la scuola e per l’infanzia.
Giulio Tarra translator from French
With the volume entitled Il Libro pel bambino, Don Giulio Tarra won two literary competitions held in 1861 by the Congresso Pedagogico Italiano: the first was dedicated to books for deaf-mute chidren, the second to books for rural schools. Among Tarra’s works published by Paolo Carrara we find “Lezioni in famiglia, versione da M. Carraud”. This article provides some information about Zulma Carraud, the author of the collection of novels entitled: Historiettes véritables pour les enfants de quatre à huit ans published by Hachette in 1864 and translated into Italian by Don Giulio. Previously the same publisher had collected Zulma’s first works in a series to be used in primary schools. Carraud, during the Second Empire period in France, and Tarra, in post-Unity Italy, both contributed to the development of the publishing industry for schools and children with their educational and entertaining books
Barocco italiano; Giovan Battista Basile
No full textSi tratta di due capitoli del volume Letteratura curato da Giulio Ferroni, in cui si definiscono le coordinate del Barocco in una chiave originale e si rivede l'opera del Basile, considerando non soltanto il Cunto de li Cunti, ma anche le opere volgari.These are two chapters of the volume titled Letteratura, ed. by Giulio Ferroni; the first is dedicated to a reassessment of the concept of Baroque in a new perspective; the second is a little monograph about the author of Lo Cunto de li Cunti, considering also his literary production in italian language
- …
