Ponències/Comunicacions de congressos
Enviaments recents
-
Heteroscedastic Gaussian processes and random features: scalable motion primitives with guarantees
(Proceedings of Machine Learning Research (PMLR), 2023)
Text en actes de congrés
Accés obertHeteroscedastic Gaussian processes (HGPs) are kernel-based, non-parametric models that can be used to infer nonlinear functions with time-varying noise. In robotics, they can be employed for learning from demonstration as ... -
Morse cell decomposition and parametrization of surfaces from point clouds
(Publicacions de la Universitat Jaume I, 2022)
Text en actes de congrés
Accés obertAn algorithm for the reconstruction of a surface from a point sample is presented. It proceeds directly from the point-cloud to obtain a cellular decomposition of the surface derived from a Morse function. No intermediate ... -
A comparison between model-based and data-driven leak localization methods
(2023)
Text en actes de congrés
Accés obertWater networks are crucial infrastructures for the sustainability of modern cities, and hence their proper operation is of great importance. This includes the fast detection, localization and repair of leaks, which may ... -
Quadratic dynamic matrix control for fast cloth manipulation
(Institute of Electrical and Electronics Engineers (IEEE), 2023)
Text en actes de congrés
Accés obertRobotic cloth manipulation is an increasingly relevant area of research, challenging classic control algorithms due to the deformable nature of cloth. While it is possible to apply linear model predictive control to make ... -
Teaching a robot where doors and drawers are and how to handle them
(2023)
Text en actes de congrés
Accés obertWe address the problem of teaching a service robot to detect doors and drawers in indoor environments. We propose a robust and accurate method in which a human demonstrates to the robot how to open doors and drawers that ... -
Gestión de energía, mediante control predictivo, de un vehículo de pila de combustible
(2023)
Text en actes de congrés
Accés obertEn este trabajo se propone el uso del Control Predictivo (MPC) para resolver el problema de la gestión de energía en un vehículo híbrido en un entorno industrial. En concreto, se propone un controlador para un sistema ... -
Reconstruction of sampled surfaces with boundary via Morse theory
(European Association for Computer Graphics (Eurographics), 2023)
Text en actes de congrés
Accés obertWe study the perception problem for garments (e.g. a pair of pants) using tools from computational topology: the identification of their geometry and position from point-cloud samples, as obtained e.g. with 3D scanners. ... -
Event-IMU fusion strategies for faster-than-IMU estimation throughput
(2023)
Comunicació de congrés
Accés obertThis study presents new methods for integrating event data and IMU readings to achieve ultra-fast camera pose estimates. The conventional predict-with-IMU-correct-with-vision approach is no longer optimal because events ... -
Robust wind turbine blade segmentation from RGB images in the wild
(Institute of Electrical and Electronics Engineers (IEEE), 2023)
Text en actes de congrés
Accés obertWith the relentless growth of the wind industry, there is an imperious need to design automatic data-driven solutions for wind turbine maintenance. As structural health monitoring mainly relies on visual inspections, the ... -
Human acceptance in the Human-Robot Interaction scenario for last-mile goods delivery
(2023)
Text en actes de congrés
Accés obertThe introduction of robotic technology in an existing scenario must be analyzed from the point of view of all the human roles involved in that scenario. In the case of dealing with urban public space, the analysis must ... -
On discrete symmetries of robotics systems: A group-theoretic and data-driven analysis
(RSS Foundation, 2023)
Text en actes de congrés
Accés restringit per política de l'editorialWe present a comprehensive study on discrete morphological symmetries of dynamical systems, which are commonly observed in biological and artificial locomoting systems, such as legged, swimming, and flying animals/robots/virtual ... -
Leveraging triplet loss for unsupervised action segmentation
(Institute of Electrical and Electronics Engineers (IEEE), 2023)
Text en actes de congrés
Accés obertIn this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, without requiring any training data. Our method ...