SciTePress - Affiliation Profile

Research.Publish.Connect.

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

Name:
Country:
Subject:

Advanced Search Affiliations Search

If you're looking for an exact phrase use quotation marks on text fields.

Proceedings

Proceedings Search

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

Papers

Papers Search

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

Authors

Authors Search

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

Advanced Search

Affiliation

Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA), Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Università della Svizzera Italiana (USI), 6962 Lugano, Switzerland

Context (please use complete words only)

Field

Sort by

2 Papers

RoboMorph: In-Context Meta-Learning for Robot Dynamics Modeling

Topics: Machine Learning in Control Applications; System Identification; Modeling, Simulation and Architecture; System Modeling

Authors: Manuel Bazzi ¹ , Asad Shahid ² , Christopher Agia ³ , John Alora ³ , Marco Forgione ² , Dario Piga ² , Francesco Braghin ¹ , Marco Pavone ³ and Loris Roveda ^{2

;

3}

Affiliations: ¹ Department of Mechanical Engineering, Politecnico di Milano, Italy , ² Istituto Dalle Molle di Studi Sull’Intelligenza Artificiale (IDSIA USI-SUPSI), Scuola Universitaria Professionale della Svizzera Italiana, DTI , Italy , ³ Stanford University, U.S.A.

Digital Object Identifier: 10.5220/0012945500003822

Proceedings of ICINCO 2024, ISBN: 978-989-758-717-7

Quick Abstract

The landscape of Deep Learning has experienced a major shift with the pervasive adoption of Transformer-based architectures, particularly in Natural Language Processing (NLP). Novel avenues for physical applications, such as solving Partial Differential Equations and Image Vision, have been explored. However, in challenging domains like robotics, where high non-linearity poses significant challenges, Transformer-based applications are scarce. While Transformers have been used to provide robots with knowledge about high-level tasks, few efforts have been made to perform system identification. This paper proposes a novel methodology to learn a meta-dynamical model of a high-dimensional physical system, such as the Franka robotic arm, using a Transformer-based architecture without prior knowledge of the system’s physical parameters. The objective is to predict quantities of interest (end-effector pose and joint positions) given the torque signals for each joint. This prediction can be useful as a component for Deep Model Predictive Control frameworks in robotics. The meta-model establishes the correlation between torques and positions and predicts the output for the complete trajectory. This work provides empirical evidence of the efficacy of the in-context learning paradigm, suggesting future improvements in learning the dynamics of robotic systems without explicit knowledge of physical parameters. Code, videos, and supplementary materials can be found at project website.

Experimental Validation of an Actor-Critic Model Predictive Force Controller for Robot-Environment Interaction Tasks

Topics: Machine Learning in Control Applications; Robot Design, Development and Control; Neural Networks Based Control Systems

Authors: Alessandro Pozzi ¹ , Luca Puricelli ¹ , Vincenzo Petrone ² , Enrico Ferrentino ² , Pasquale Chiacchio ² , Francesco Braghin ¹ and Loris Roveda ³

Affiliations: ¹ Department of Mechanical Engineering, Politecnico di Milano, 20133 Milano, Italy , ² Department of Computer Engineering, Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, 84084 Fisciano, Italy , ³ Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA), Scuola Universitaria Professionale della Svizzera Italiana (SUPSI), Università della Svizzera Italiana (USI), 6962 Lugano, Switzerland

Digital Object Identifier: 10.5220/0012160700003543

Proceedings of ICINCO 2023, ISBN: 978-989-758-670-5

Quick Abstract

In industrial settings, robots are typically employed to accurately track a reference force to exert on the surrounding environment to complete interaction tasks. Interaction controllers are typically used to achieve this goal. Still, they either require manual tuning, which demands a significant amount of time, or exact modeling of the environment the robot will interact with, thus possibly failing during the actual application. A significant advancement in this area would be a high-performance force controller that does not need operator calibration and is quick to be deployed in any scenario. With this aim, this paper proposes an Actor-Critic Model Predictive Force Controller (ACMPFC), which outputs the optimal setpoint to follow in order to guarantee force tracking, computed by continuously trained neural networks. This strategy is an extension of a reinforcement learning-based one, born in the context of human-robot collaboration, suitably adapted to robot-environment interaction. We validate the ACMPFC in a real-case scenario featuring a Franka Emika Panda robot. Compared with a base force controller and a learning-based approach, the proposed controller yields a reduction of the force tracking MSE, attaining fast convergence: with respect to the base force controller, ACMPFC reduces the MSE by a factor of 4.35.