Francisco Pastor
University of Málaga
12 Papers
23 Citations
Francisco Pastor is an academic researcher from University of Málaga. The author has contributed to research in topics: Computer science & Tactile sensor. The author has an hindex of 4, co-authored 10 publications.
Chat about Author
Papers
Bayesian and Neural Inference on LSTM-Based Object Recognition From Tactile and Kinesthetic Information
Francisco Pastor,Jorge García-González,Juan M. Gandarias,Daniel Medina,Pau Closas,Alfonso García-Cerezo,Jesús M. Gómez-de-Gabriel +6 more
- 01 Jan 2021
TL;DR: An experiment with 36-classes is carried out to evaluate and compare the performance of the fused, tactile, and kinesthetic perception systems and the results show that the Bayesian-based classifiers improves capabilities for object recognition and outperforms the Neural-based approach.
Using 3D Convolutional Neural Networks for Tactile Object Recognition with Robotic Palpation
TL;DR: A novel method of active tactile perception based on 3D neural networks and a high-resolution tactile sensor installed on a robot gripper and a new representation of tactile information as 3D tactile tensors is described.
49
Underactuated Gripper with Forearm Roll Estimation for Human Limbs Manipulation in Rescue Robotics
Juan M. Gandarias,Francisco Pastor,Antonio Jose Muñoz-Ramirez,Alfonso García-Cerezo,Jesús M. Gómez-de-Gabriel +4 more
- 01 Nov 2019
TL;DR: This paper addresses the development of a gripper and methods for the robotic manipulation of a laying victim’s forearm, initiated by the robot, and validated based on experimental results, and provides robust and precise grasping, tolerant to location inaccuracy with inexpensive sensors.
18
Upper-Limb Kinematic Parameter Estimation and Localization Using a Compliant Robotic Manipulator
TL;DR: In this paper, a pose estimation method using a compliant robotic manipulator is proposed for upper-limb manipulation using proprioceptive data obtained from a collaborative robot with a Cartesian impedance-based controller.
Active Tactile Recognition of Deformable Objects with 3D Convolutional Neural Networks
Juan M. Gandarias,Francisco Pastor,Alfonso García-Cerezo,Jesús M. Gómez-de-Gabriel +3 more
- 09 Jul 2019
TL;DR: A 3D Convolutional Neural Network (3D CNN) called TactNet3D has been created to classify tactile information from 9 deformable objects, showing that it can classify deformable Objects with an accuracy of 96.39% with time series of pressure distributions.
14