Mínimos Cuadrados Recursivos para un Manipulador que Aprende por Demostración

Abstract

En este trabajo, se desarrolla un sistema de control automatizado para permitir que un manipulador aprenda y planifique las trayectorias a partir de las demostraciones dadas por la mano de un usuario. La entrada de datos es adquirida por un sensor, y se aprende su comportamiento a través de un algoritmo de aprendizaje automático basado en los mínimos cuadrados recursivos. Se utiliza un perfil de trayectoria de interpoladores a tramos para evitar el movimiento impulsivo del manipulador. Se realiza el análisis de las cinemáticas directa e inversa para obtener los valores de las variables articulares para el manipulador. Se crea un modelo dinámico usando la formulación de Newton-Euler. Se aplica un control proporcional derivativo al sistema. Los sistemas de monitoreo y control se implementan en una plataforma embebida para fines de prueba.

Flexible Coordination of Flexible Limbs: Decentralized Control Scheme for Inter- and Intra-Limb Coordination in Brittle Stars' Locomotion

“…All experiments were performed on a flat terrain. Ren et al, 2014;Cully et al, 2015;Rubio et al, 2018Rubio et al, , 2019Yen et al, 2018) required a considerable amount of time (more than several tens of seconds) to respond to unexpected physical damage. Meanwhile, we have recently developed a brittle starlike robot that can immediately adapt to unexpected physical damage , yet the number of degrees of freedom within the body was still small.…”

“…The challenge now is how to make the robots coordinate, in real-time, their numerous bodily degrees of freedom under unpredictable circumstances, including changes in the environment and unexpected physical damages to the robots' structure. Previous studies tackled this problem by using learning techniques (Bongard et al, 2006;Mahdavi and Bentley, 2006;Mostafa et al, 2010;Koos et al, 2013;Christensen et al, 2014;Ren et al, 2014;Rubio et al, 2018Rubio et al, , 2019Yen et al, 2018) and trial-and-error methods (Cully et al, 2015), however, the performance level of robots using these techniques is not satisfactory. Specifically, the previous robots could only adapt to predictable circumstances or required a considerably long adaptation time.…”

Dip-coater revolver machine for layer processing on metallic substrates

“…Different robot prototypes and control systems exist in industrial robotics, providing practical solutions for industrial manufacturing processes. (Aguilar-Ibanez et al, 2022;García-Sánchez et al, 2020;Meda-Campaña et al, 2022;Rubio, 2016Rubio, , 2017Rubio, Cruz, et al, 2016;Rubio et al, 2019 The project builds upon the design of an articulated robotic arm as a basis for the dip-coating process. This design offers necessary features for reducing time and movement in the coating manufacturing process.…”