Momentum transfer continuum between preshape and grasping based on fluidics

Özyer, Barış
This dissertation propose a new fluidics based framework to determine a continuum between preshaping and grasping so as to appropriately preshape a multi-fingered robot hand for creating an optimal initialization of grasp. The continuum of a hand preshape closing upon an object that creates an initial object motion tendency of the object based on the impact moment patterns generated from the fingers is presented. These motion tendencies should then be suitable for the proper initiation of the grasping task. The aim is motivated by human like behavior where we preshape and land on an object to initiate a certain grasping behavior without losing the continuum during the "preshaping to grasping" phases. The continuity of momentum transfer phenomena is inspired by fluid dynamics that deals with fluid flow. We have adapted governing equations based on the physical principles of the fluid flow to generate momentum transfer from the robotic fingers, closing upon the object surface to fluid medium particles then from these fluid medium particles to the grasping object. Smoothed Particular Hydrodynamics (SPH) which is a mesh free particle method and finite volume approximation is used to analyze fluid flow equations. The fingers of the robotic hand and object are modeled by solidified fluid elements and also can be compliance. For evaluating the optimal grasp initialization of different hand preshape, we propose a decision support system consisting of artificial feed forward neural network based on the moment distribution on the object determines either : 1) given initial position and orientation of a robot hand, what preshape is suitable for generating a desired moment distribution on the surface of a given object in order to trigger a desired rotation in a desired direction when approaching with this preshaped hand or 2) given a predetermined hand preshape what initial position, orientation and hand aperture are suitable to generate a desired rotation upon approach and without causing the retroceeding of the object.


Implementation of a closed-loop action generation system on a humanoid robot through learning by demonstration
Tunaoğlu, Doruk; Şahin, Erol; Department of Computer Engineering (2010)
In this thesis the action learning and generation problem on a humanoid robot is studied. Our aim is to realize action learning, generation and recognition in one system and our inspiration source is the mirror neuron hypothesis which suggests that action learning, generation and recognition share the same neural circuitry. Dynamic Movement Primitives, an efficient action learning and generation approach, are modified in order to fulfill this aim. The system we developed (1) can learn from multiple demonstr...
Robotic system design for reshaping estimated human intention in human-robot interactions
Durdu, Akif; Erkmen, İsmet; Erkmen, Aydan Müşerref; Department of Electrical and Electronics Engineering (2012)
This thesis outlines the methodology and experiments associated with the reshaping of human intention via based on the robot movements in Human-Robot Interactions (HRI). Although works on estimating human intentions are quite well known research areas in the literature, reshaping intentions through interactions is a new significant branching in the field of human-robot interaction. In this thesis, we analyze how previously estimated human intentions change based on his/her actions by cooperating with mobile...
Hierarchical behavior categorization using correlation based adaptive resonance theory
Yavaş, Mustafa; Alpaslan, Ferda Nur; Department of Computer Engineering (2011)
This thesis introduces a novel behavior categorization model that can be used for behavior recognition and learning. Correlation Based Adaptive Resonance Theory (CobART) network, which is a kind of self organizing and unsupervised competitive neural network, is developed for this purpose. CobART uses correlation analysis methods for category matching. It has modular and simple architecture. It can be adapted to different categorization tasks by changing the correlation analysis methods used when needed. Cob...
Equivalent linearization of 2-way fuzzy adaptive system under nonparametric uncertainty and inconsistency
Gurkan, E; Banks, SP; Erkmen, Aydan Müşerref; Erkmen, İsmet (2002-09-18)
Our aim in this paper is to design a 2-way fuzzy adaptive controller for a flexible robot arm and to analyze the stability of this controller using describing function technique. The 2-way fuzzy adaptive system is used in order to model the nonparametric uncertainties and inconsistencies present in the nonlinear system. The use of intuitionistic fuzzy sets in the 2-way fuzzy adaptive structure makes it possible to model such uncertainties. The proposed architecture is used as a controller for a flexible-joi...
Imitation of human body poses and hand gestures using a particle based fluidics method
Tilki, Umut; Erkmen, İsmet; Erkmen, Aydan Müşerref; Department of Electrical and Electronics Engineering (2012)
In this thesis, a new approach is developed, avoiding the correspondence problem caused by the difference in embodiment between imitator and demonstrator in imitation learning. In our work, the imitator is a fluidic system of dynamics totally different than the imitatee, which is a human performing hand gestures and human body postures. The fluidic system is composed of fluid particles, which are used for the discretization of the problem domain. In this work, we demonstrate the fluidics formation control s...
Citation Formats
B. Özyer, “Momentum transfer continuum between preshape and grasping based on fluidics,” Ph.D. - Doctoral Program, Middle East Technical University, 2012.