000203568 001__ 203568
000203568 005__ 20190509132515.0
000203568 0247_ $$2doi$$a10.5075/epfl-thesis-6434
000203568 02470 $$2urn$$aurn:nbn:ch:bel-epfl-thesis6434-3
000203568 02471 $$2nebis$$a10279432
000203568 037__ $$aTHESIS
000203568 041__ $$aeng
000203568 088__ $$a6434
000203568 245__ $$aLearning Reach-to-Grasp Motions From Human Demonstrations
000203568 269__ $$a2014
000203568 260__ $$bEPFL$$c2014$$aLausanne
000203568 336__ $$aTheses
000203568 502__ $$aDr A. Karimi (président) ; Prof. A. Billard (directrice) ; Prof. R. Alterovitz,  Prof. H. Bleuler,  Prof. J. Steil (rapporteurs)
000203568 520__ $$aReaching over to grasp an item is arguably the most commonly used motor skill by humans. Even under sudden perturbations, humans seem to react rapidly and adapt their motion to guarantee success. Despite the apparent ease and frequency with which we use this ability, a complete understanding of the underlying mechanisms cannot be claimed. It is partly due to such incomplete knowledge that adaptive robot motion for reaching and grasping under perturbations is not perfectly achieved. In this thesis, we take the discriminative approach for modelling trajectories of reach-to-grasp motion from expert demonstrations. Throughout this thesis, we will employ time-independent (autonomous) flow based representations to learn reactive motion controllers which can then be ported onto robots. This thesis is divided into three main parts. The first part is dedicated to biologically inspired modelling of reach-to-grasp motions with respect to the hand-arm coupling. We build upon previous work in motion modelling using autonomous dynamical systems (DS) and present a coupled dynamical system (CDS) model of these two subsystems. The coupled model ensures satisfaction of the constraints between the hand and the arm subsystems which are critical to the success of a reach-to-grasp task. Moreover, it reduces the complexity of the overall motion planning problem as compared to considering a combined problem for the hand and the arm motion. In the second part we extend the CDS approach to incorporate multiple grasping points. Such a model is beneficial due to the fact that many daily life objects afford multiple grasping locations on their surface. We combine a DS based approach with energy-function learning to learn a multiple attractor dynamical system where the attractors are mapped to the desired grasping points. We present the Augmented-SVM (ASVM) model that combines the classical SVM formulation with gradient constraints arising from the energy function to learn the desired dynamical function for motion generation. In the last part of this thesis, we address the problem of inverse-kinematics and obstacle avoidance by combining our flow-based motion generator with global configuration-space planners. We claim that the two techniques complement each other. On one hand, the fast reactive nature of our flow based motion generator can used to guide the search of a randomly exploring random tree (RRT) based global planner. On the other hand, global planners can efficiently handle arbitrary obstacles and avoid local minima present in the dynamical function learned from demonstrations. We show that combining the information from demonstrations with global planning in the form of a energy-map considerably decreases the computational complexity of state-of-the-art sampling based planners. We believe that this thesis has the following contributions to Robotics and Machine Learning. First, we have developed algorithms for fast and adaptive motion generation for reach-grasp motions. Second, we formulated an extension to the classical SVM formulation that takes into account the gradient information from data. We showed that instead of being limited as a classifier or a regressor, the SVM framework can be used as a more general function approximation technique. Lastly, we have combined our local methods with global approaches for planning to achieve arbitrary obstacle avoidance and considerable reduction in the computation complexity of the global planners.
000203568 6531_ $$aReaching Movements
000203568 6531_ $$aHand arm coupling
000203568 6531_ $$aNonlinear dynamical system
000203568 6531_ $$aCoupled dynamical system
000203568 6531_ $$aMultiple attractor dynamical system
000203568 6531_ $$aImitation learning
000203568 6531_ $$aSupport vector machine
000203568 6531_ $$aGradient constraints
000203568 700__ $$0243007$$g198224$$aShukla, Ashwini
000203568 720_2 $$aBillard, Aude$$edir.$$g115671$$0240594
000203568 8564_ $$uhttps://infoscience.epfl.ch/record/203568/files/EPFL_TH6434.pdf$$zn/a$$s16497310$$yn/a
000203568 909C0 $$xU10660$$0252119$$pLASA
000203568 909CO $$pthesis$$pthesis-bn2018$$pDOI$$ooai:infoscience.tind.io:203568$$qDOI2$$qGLOBAL_SET$$pSTI
000203568 917Z8 $$x108898
000203568 917Z8 $$x108898
000203568 917Z8 $$x108898
000203568 918__ $$dEDPR$$cIMT$$aSTI
000203568 919__ $$aLASA
000203568 920__ $$b2014$$a2014-11-28
000203568 970__ $$a6434/THESES
000203568 973__ $$sPUBLISHED$$aEPFL
000203568 980__ $$aTHESIS