A Legendre-Gauss Pseudospectral Collocation Method for Trajectory Optimization in Second Order Systems

Autor: Siro Moreno-Martin, Lluis Ros, Enric Celaya

Trabajo presentado en el International Conference on Intelligent Robots and Systems (IROS), celebrado en Kyoto (Japón), del 23 al 27 de octubre de 2022
Pseudospectral collocation methods have proven to be powerful tools to solve optimal control

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::abdd369a83c3e2aac461ee9c6af0f635
http://arxiv.org/abs/2302.09036

Online Reinforcement Learning Using a Probability Density Estimation

Autor: Enric Celaya, Alejandro Agostini

Publikováno v: Digital.CSIC. Repositorio Institucional del CSIC
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

Letter: Communicated by Masa-aki Sato.
Function approximation in online, incremental, reinforcement learning needs to deal with two fundamental problems: biased sampling and nonstationarity. In this kind of task, biased sampling occurs because s

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f29ca4c7d8b4d8052641857e1ef763d
https://doi.org/10.1162/neco_a_00906

Reactive free-gait generation to follow arbitrary trajectories with a hexapod robot

Autor: Enric Celaya, Josep M. Porta

Publikováno v: Digital.CSIC. Repositorio Institucional del CSIC
instname

We present a reactive controller that is able to displace a legged robot along an arbitrary trajectory with a high degree of accuracy. We designed the different modules of our controller so that they can deal with arbitrary leg configurations. In thi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ec931b92e07f0e5e7fbaf854676783f
https://doi.org/10.1016/j.robot.2004.04.001

Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments

Autor: Josep M. Porta, Enric Celaya

Publikováno v: Digital.CSIC. Repositorio Institucional del CSIC
instname
Scopus-Elsevier
Journal of Artificial Intelligence Research, 23, 79-122. Morgan Kaufmann Publishers, Inc.

In this paper, we confront the problem of applying reinforcement learning to agents that perceive the environment through many sensors and that can perform parallel actions using many actuators as is the case in complex autonomous robots. We argue th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::295df42e8bb42bc3008b7fe29f5811bf
http://arxiv.org/abs/1107.0048

A relational positioning methodology for robot task specification and execution

Autor: A. Rodriguez, Enric Celaya, L. Basaez

Publikováno v: Digital.CSIC. Repositorio Institucional del CSIC
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
Universitat Jaume I

12 pages, 11 figures.
This paper presents a relational positioning methodology that allows to restrict totally or partially the movements of an object by specifying its allowed positions in terms of a set of intuitive geometric constraints. In o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d19d093de470c94410579c8052713167
http://hdl.handle.net/10261/12109