Control of an anthropomorphic robotic hand for grasping and manipulation tasks

This project focuses on the development of a robust software solution for controlling the Allegro anthropomorphic robotic hand in robotic grasping and manipulation tasks. The aim is to en- hance the hand’s capabilities through advanced control algorithms and integrate tactile sensors to enable force...

Descripción completa

Detalles Bibliográficos
Autor: Pujol Closa, Marina
Tipo de recurso: tesis de maestría
Fecha de publicación:2024
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/419305
Acceso en línea:https://hdl.handle.net/2117/419305
Access Level:acceso abierto
Palabra clave:Algorithms
Robotics
Algorismes
Robòtica
Àrees temàtiques de la UPC::Enginyeria mecànica::Processos de fabricació mecànica::Màquines i mecanismes
Descripción
Sumario:This project focuses on the development of a robust software solution for controlling the Allegro anthropomorphic robotic hand in robotic grasping and manipulation tasks. The aim is to en- hance the hand’s capabilities through advanced control algorithms and integrate tactile sensors to enable force-controlled grasps. The developed software, written in C++ and integrated with the Robot Operating System (ROS) 2 3 , supports both real-world and simulated environments. In this work, the Allegro Hand’s hardware is extensively studied, including its kinematics, joint limitations, and communication protocols. The software package includes forward and inverse kinematics for precise finger control and supports multiple versions of the Allegro Hand. Addi- tionally, a ROS 2 package was developed to integrate the hand with other robotic systems, such as the Mobile Anthropomorphic Dual-Arm Robot (MADAR), and to utilize tactile feedback from Weiss sensors for advanced grasping techniques. The software has been tested across four different versions of the Allegro Hand, demonstrating its ability to accurately control the hand’s movements. The results show significant improve- ments in grasping precision and adaptability, making the software a valuable tool for both re- search and practical applications in robotic manipulation.