A5017391315- Tactile and Sensory Interactions
- Advanced Sensor and Energy Harvesting Materials
- Interactive and Immersive Displays
- Robot Manipulation and Learning
- Modular Robots and Swarm Intelligence
- Romani and Gypsy Studies
- Geography and Environmental Studies
- Soil Geostatistics and Mapping
- Mosquito-borne diseases and control
- Agricultural and Food Sciences
- Advanced Fiber Optic Sensors
- 3D Shape Modeling and Analysis
- Speech and Audio Processing
- Geological Modeling and Analysis
- 3D Modeling in Geospatial Applications
- Muscle activation and electromyography studies
- Geochemistry and Geologic Mapping
- Advanced Memory and Neural Computing
- Industrial Vision Systems and Defect Detection
- Remote Sensing and LiDAR Applications
- Structural Health Monitoring Techniques
- Infrastructure Maintenance and Monitoring
University of Liverpool
2022
Universidade Federal de Santa Maria
2020
Universidade Federal do Rio Grande do Sul
2020
Recently simulation methods have been developed for optical tactile sensors to enable the Sim2Real learning, i.e., first training models in before deploying them on a real robot. However, some artefacts objects are unpredictable, such as imperfections caused by fabrication processes, or scratches natural wear and tear, thus cannot be represented simulation, resulting significant gap between simulated images. To address this gap, we propose novel texture generation network map images into...
This paper introduces RoTipBot, a novel robotic system for handling thin, flexible objects. Different from previous works that are limited to singulating them using suction cups or soft grippers, RoTipBot can grasp and count multiple layers simultaneously, emulating human in various environments. Specifically, we develop vision-based tactile sensor named RoTip rotate sense contact information around its tip. Equipped with two sensors, feeds of objects into the centre between fingers,...
Identificação e mapeamento de unidades homogêneas do bioma Pampa utilizando
Recently, several morphologies, each with its advantages, have been proposed for the \textit{GelSight} high-resolution tactile sensors. However, existing simulation methods are limited to flat-surface sensors, which prevents their usage newer sensors of non-flat morphologies in Sim2Real experiments. In this paper, we extend a previously GelSight method developed and propose novel curved particular, address light rays travelling through membrane form geodesic paths. The is validated by...
End-to-end self-supervised models have been proposed for estimating the success of future candidate grasps and video predictive generating observations. However, none yet studied these two strategies side-by-side addressing aforementioned grasping problem. We investigate compare a model-free approach, to estimate grasp, against model-based alternative that exploits learnt model generates observation gripper about grasp an object. Our experiments demonstrate despite end-to-end obtaining best...
Developing autonomous assistants to help with domestic tasks is a vital topic in robotics research. Among these tasks, garment folding one of them that still far from being achieved mainly due the large number possible configurations crumpled piece clothing may exhibit. Research has been done on either estimating pose as whole or detecting landmarks for grasping separately. However, such works constrain capability robots perceive states by limiting representations single task. In this paper,...
O objetivo deste trabalho foi o de identificar e classificar as unidades homogêneas presentes nos campos naturais do bioma Pampa pelo uso das imagens Sentinel-2, fundamentado pelas distintas composições dos da região Campanha pela presença áreas invadidas com Eragrostis plana Nees (capim-anonni-2). A área estudo compreendeu a Complexo Eólico Cerro Chato em Santana Livramento- RS. análise utilizou imagens, uma contendo apenas bandas 10 metros outra composta 20 resolução espacial. Para...
Recently simulation methods have been developed for optical tactile sensors to enable the Sim2Real learning, i.e., firstly training models in before deploying them on real robot. However, some artefacts objects are unpredictable, such as imperfections caused by fabrication processes, or scratches natural wear and tear, thus cannot be represented simulation, resulting a significant gap between simulated images. To address this gap, we propose novel texture generation network that maps images...