This work presents torque control and force sensing strategies for the new dexterous CEA hand. It is only based on proprioceptive signals and does not rely on external force sensors. We primarily focus on the mechatronic design rationale of the robotic hand. A modular approach simplifies the complex hand assembly and permits to concentrate efforts on one basic unit which is replicated throughout the hand. An optimized mechanical design of this unit assures backdrivability through the whole mechanism, including actuators and transmission of movement to the joints. Based on this feature, external forces applied to the finger can be sensed at the motor level. Overall, this mechatronic design contributes to the improvement of manipulation skills of robotic hands, thanks to the combination of high performance mechanics, high sensitivity to external forces and torque control capability without using external force sensor. Experimental results confirm the validity of our design approach, which provides a highly integrated method for sensing the interacting force.
Resumo-Tecnologias atuais de armazenamento permitem gerar grandes bases de dados, as quais podem possuir informações desconhecidas. Dessa forma, são necessárias tecnologias voltadas a explorar essas bases, tendo-se o data mining como uma dessas tecnologias, que utiliza algoritmos para extrair conhecimento e padrões presentes nos dados. Este artigo demonstra a aplicação do Standard Ant Clustering Algorithm, Ant Based Clustering e Adaptative Ant-Clustering Algorithm, pertencentes à tarefa de agrupamento, para análise de dados referente aos indicadores do monitoramento de bacias hidrográficas da região carbonífera do Sul de Santa Catarina. A tarefa de agrupamento objetiva reunir uma base de dados em grupos de dados semelhantes, sendo que os algoritmos aplicados nessa pesquisa simulam o comportamento da organização de cemitérios observados em espécies de formigas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.