2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011), June 27-30, 2011, Grand Hyatt Taipei, Taipei, Taiwan

Statistical analysis of 3-dimensional motions of humans, animals or objects is instrumental to establish how these motions differ, depending on various influences or parameters. When such motions involve no stretching or tearing, they may be described by the elements of a Lie group called the Special Euclidean Group, denoted SE(3). Statistical analysis of trajectories lying in SE(3) is complicated by the basic properties of the group, such as non-commutativity, non-compactness and lack of a bi-invariant metric. This necessitates the generalization of the ideas of “mean” and “variance” to apply in this setting. We describe how to exploit the unique properties of a formalism called Conformal Geometric Algebra to express these generalizations and carry out such statistical analyses efficiently; we introduce a practical method of visualizing trajectories lying in the 6-dimensional group manifold of SE(3); and we show how this methodology can be applied, for example, in testing theoretical claims about the influence of an attended object on a competing action applied to a different object. The two prevailing views of such movements differ as to whether mental action-representations evoked by an object held in working memory should perturb only the early stages of subsequently reaching to grasp another object, or whether the perturbation should persist over the entire movement. Our method yields “difference trajectories” in SE(3), representing the continuous effect of a variable of interest on an action, revealing statistical effects on the forward progress of the hand as well as a corresponding effect on the hand’s rotation. / Graduate / 0405 / 0541 / 0623

This thesis focuses on the problem of determining appropriate skeletal configurations for which a virtual animated character moves to desired positions as smoothly, rapidly, and as accurately as possible. During the last decades, several methods and techniques, sophisticated or heuristic, have been presented to produce smooth and natural solutions to the Inverse Kinematics (IK) problem. However, many of the currently available methods suffer from high computational cost and production of unrealistic poses. In this study, a novel heuristic method, called Forward And Backward Reaching Inverse Kinematics (FABRIK), is proposed, which returnsvisually natural poses in real-time, equally comparable with highly sophisticated approaches. It is capable of supporting constraints for most of the known joint types and it can be extended to solve problems with multiple end effectors, multiple targets and closed loops. FABRIK wascompared against the most popular IK approaches and evaluated in terms of its robustness and performance limitations. This thesis also includes a robust methodology for marker prediction under multiple marker occlusion for extended time periods, in order to drive real-time centre of rotation (CoR) estimations. Inferred information from neighbouring markers has been utilised, assuming that the inter-marker distances remain constant over time. This is the firsttime where the useful information about the missing markers positions which are partially visible to a single camera is deployed. Experiments demonstrate that the proposed methodology can effectively track the occluded markers with high accuracy, even if the occlusion persists for extended periods of time, recovering in real-time good estimates of the true joint positions. In addition, the predicted positions of the joints were further improved by employing FABRIK to relocate their positions and ensure a fixed bone length over time. Our methodology is tested against some of the most popular methods for marker prediction and the results confirm that our approach outperforms these methods in estimating both marker and CoR positions. Finally, an efficient model for real-time hand tracking and reconstruction that requires a minimumnumber of available markers, one on each finger, is presented. The proposed hand modelis highly constrained with joint rotational and orientational constraints, restricting the fingers and palm movements to an appropriate feasible set. FABRIK is then incorporated to estimate the remaining joint positions and to fit them to the hand model. Physiological constraints, such as inertia, abduction, flexion etc, are also incorporated to correct the final hand posture. A mesh deformation algorithm is then applied to visualise the movements of the underlying hand skeleton for comparison with the true hand poses. The mathematical framework used for describing and implementing the techniques discussed within this thesis is Conformal GeometricAlgebra (CGA).

Conformal geometric algebra is defined in the thesis. Representations of geometric objects and possibilities of their geometric transformations are presented. Conformal geometric algebra is applied to the calculation of forward kinematics of a robotic manipulator UR10 from Universal Robots. It is also applied to determine the position of the machine based on the location and rotation of two cameras. Then it is used in an inverse task, where based on records from the two cameras, dimensions of the UR10 manipulator and possibilities of its movement, the mutual position of these cameras is determined. And consequently the possibilities of their location in space. Finally, the derived procedures are implemented in a custom program created in the CluCalc environment, using which a sample example verifying the correctness of these procedures is calculated.

Tato diplomová práce má za cíl seznámit čtenáře se stále ještě relativně novou a neznámou oblastí matematiky, s geometrickou algebrou. Nejdříve jsou uvedeny základní definice a poté jsou studovány vlastnosti obecné geometrické algebry. Další velká část textu se věnuje Konformní geometrické algebře, která je v současnosti jedna z nejvíce zkoumaných a aplikovaných geometrických algeber. Jsou popsány její algebraické a geometrické vlastnosti, konkrétně schopnost reprezentovat určité geometrické objekty jako vektory. Taktéž umožňuje počítat jejich průniky a konformní transformace. Další část textu je zaměřena na aplikace Konformní geometrické algebry, nejdříve k popisu kinematiky robotické ruky a poté v binokulárním viděni.

This thesis focuses on robotic 3D vision for application in Bin Picking. The new method based on Conformal Geometric Algebra (CGA) is proposed and tested for identification of spheres in Pointclouds created with 3D scanner. The speed, precision and scalability of this method is compared to traditional descriptors based method. It is proved that CGA maintains the same precision as the traditional method in much shorter time. The CGA based approach seems promising for the use in the future of robotic 3D vision for identification and localization of spheres.