Project for Active and Robot Vision Course

Tässä työssä raportoidaan harjoitustyön kehittäminen ja toteuttaminen Aktiivisen- ja robottinäön kurssille. Harjoitustyössä suunnitellaan ja toteutetaan järjestelmä joka liikuttaa kappaleita robottikäsivarrella kolmiuloitteisessa avaruudessa. Kappaleidenpaikkojen määrittämiseen järjestelmä käyttää digitaalisia kuvia. Tässä työssä esiteltävässä harjoitustyötoteutuksessa käytettiin raja-arvoistusta HSV-väriavaruudessa kappaleiden segmentointiin kuvasta niiden värien perusteella. Segmentoinnin tuloksena saatavaa binäärikuvaa suodatettiin mediaanisuotimella kuvan häiriöiden poistamiseksi. Kappaleen paikkabinäärikuvassa määritettiin nimeämällä yhtenäisiä pikseliryhmiä yhtenäisen alueen nimeämismenetelmällä. Kappaleen paikaksi määritettiin suurimman nimetyn pikseliryhmän paikka. Kappaleiden paikat kuvassa yhdistettiin kolmiuloitteisiin koordinaatteihin kalibroidun kameran avulla. Järjestelmä liikutti kappaleita niiden arvioitujen kolmiuloitteisten paikkojen perusteella.

Canonical solution groups of a homomorphism : manipulator kinematics, nonparametric regression and distributed object systems

The kinematic mapping of a rigid open-link manipulator is a homomorphism between Lie groups. The homomorphisrn has solution groups that act on an inverse kinematic solution element. A canonical representation of solution group operators that act on a solution element of three and seven degree-of-freedom (do!) dextrous manipulators is determined by geometric analysis. Seven canonical solution groups are determined for the seven do! Robotics Research K-1207 and Hollerbach arms. The solution element of a dextrous manipulator is a collection of trivial fibre bundles with solution fibres homotopic to the Torus. If fibre solutions are parameterised by a scalar, a direct inverse funct.ion that maps the scalar and Cartesian base space coordinates to solution element fibre coordinates may be defined. A direct inverse pararneterisation of a solution element may be approximated by a local linear map generated by an inverse augmented Jacobian correction of a linear interpolation. The action of canonical solution group operators on a local linear approximation of the solution element of inverse kinematics of dextrous manipulators generates cyclical solutions. The solution representation is proposed as a model of inverse kinematic transformations in primate nervous systems. Simultaneous calibration of a composition of stereo-camera and manipulator kinematic models is under-determined by equi-output parameter groups in the composition of stereo-camera and Denavit Hartenberg (DH) rnodels. An error measure for simultaneous calibration of a composition of models is derived and parameter subsets with no equi-output groups are determined by numerical experiments to simultaneously calibrate the composition of homogeneous or pan-tilt stereo-camera with DH models. For acceleration of exact Newton second-order re-calibration of DH parameters after a sequential calibration of stereo-camera and DH parameters, an optimal numerical evaluation of DH matrix first order and second order error derivatives with respect to a re-calibration error function is derived, implemented and tested. A distributed object environment for point and click image-based tele-command of manipulators and stereo-cameras is specified and implemented that supports rapid prototyping of numerical experiments in distributed system control. The environment is validated by a hierarchical k-fold cross validated calibration to Cartesian space of a radial basis function regression correction of an affine stereo model. Basic design and performance requirements are defined for scalable virtual micro-kernels that broker inter-Java-virtual-machine remote method invocations between components of secure manageable fault-tolerant open distributed agile Total Quality Managed ISO 9000+ conformant Just in Time manufacturing systems.

Minimum description length, regularisation and multi-modal data

Conventional feed forward Neural Networks have used the sum-of-squares cost function for training. A new cost function is presented here with a description length interpretation based on Rissanen's Minimum Description Length principle. It is a heuristic that has a rough interpretation as the number of data points fit by the model. Not concerned with finding optimal descriptions, the cost function prefers to form minimum descriptions in a naive way for computational convenience. The cost function is called the Naive Description Length cost function. Finding minimum description models will be shown to be closely related to the identification of clusters in the data. As a consequence the minimum of this cost function approximates the most probable mode of the data rather than the sum-of-squares cost function that approximates the mean. The new cost function is shown to provide information about the structure of the data. This is done by inspecting the dependence of the error to the amount of regularisation. This structure provides a method of selecting regularisation parameters as an alternative or supplement to Bayesian methods. The new cost function is tested on a number of multi-valued problems such as a simple inverse kinematics problem. It is also tested on a number of classification and regression problems. The mode-seeking property of this cost function is shown to improve prediction in time series problems. Description length principles are used in a similar fashion to derive a regulariser to control network complexity.

High Performance Multi-Standard Architecture for DCT Computation in H.264/AVC High Profile and HEVC Codecs

A new high performance architecture for the computation of all the DCT operations adopted in the H.264/AVC and HEVC standards is proposed in this paper. Contrasting to other dedicated transform cores, the presented multi-standard transform architecture is supported on a completely configurable, scalable and unified structure, that is able to compute not only the forward and the inverse 8×8 and 4×4 integer DCTs and the 4×4 and 2×2 Hadamard transforms defined in the H.264/AVC standard, but also the 4×4, 8×8, 16×16 and 32×32 integer transforms adopted in HEVC. Experimental results obtained using a Xilinx Virtex-7 FPGA demonstrated the superior performance and hardware efficiency levels provided by the proposed structure, which outperforms its more prominent related designs by at least 1.8 times. When integrated in a multi-core embedded system, this architecture allows the computation, in real-time, of all the transforms mentioned above for resolutions as high as the 8k Ultra High Definition Television (UHDTV) (7680×4320 @ 30fps).

A fractional approach for the motion planning of redundant and hyper-redundant manipulators

The trajectory planning of redundant robots through the pseudoinverse control leads to undesirable drift in the joint space. This paper presents a new technique to solve the inverse kinematics problem of redundant manipulators, which uses a fractional differential of order α to control the joint positions. Two performance measures are defined to examine the strength and weakness of the proposed method. The positional error index measures the precision of the manipulator's end-effector at the target position. The repeatability performance index is adopted to evaluate if the joint positions are repetitive when the manipulator execute repetitive trajectories in the operational workspace. Redundant and hyper-redundant planar manipulators reveal that it is possible to choose in a large range of possible values of α in order to get repetitive trajectories in the joint space.

Stiffness based trajectory planning and feedforward based vibration suppression control of parallel robot machines

The dissertation proposes two control strategies, which include the trajectory planning and vibration suppression, for a kinematic redundant serial-parallel robot machine, with the aim of attaining the satisfactory machining performance. For a given prescribed trajectory of the robot's end-effector in the Cartesian space, a set of trajectories in the robot's joint space are generated based on the best stiffness performance of the robot along the prescribed trajectory. To construct the required system-wide analytical stiffness model for the serial-parallel robot machine, a variant of the virtual joint method (VJM) is proposed in the dissertation. The modified method is an evolution of Gosselin's lumped model that can account for the deformations of a flexible link in more directions. The effectiveness of this VJM variant is validated by comparing the computed stiffness results of a flexible link with the those of a matrix structural analysis (MSA) method. The comparison shows that the numerical results from both methods on an individual flexible beam are almost identical, which, in some sense, provides mutual validation. The most prominent advantage of the presented VJM variant compared with the MSA method is that it can be applied in a flexible structure system with complicated kinematics formed in terms of flexible serial links and joints. Moreover, by combining the VJM variant and the virtual work principle, a systemwide analytical stiffness model can be easily obtained for mechanisms with both serial kinematics and parallel kinematics. In the dissertation, a system-wide stiffness model of a kinematic redundant serial-parallel robot machine is constructed based on integration of the VJM variant and the virtual work principle. Numerical results of its stiffness performance are reported. For a kinematic redundant robot, to generate a set of feasible joints' trajectories for a prescribed trajectory of its end-effector, its system-wide stiffness performance is taken as the constraint in the joints trajectory planning in the dissertation. For a prescribed location of the end-effector, the robot permits an infinite number of inverse solutions, which consequently yields infinite kinds of stiffness performance. Therefore, a differential evolution (DE) algorithm in which the positions of redundant joints in the kinematics are taken as input variables was employed to search for the best stiffness performance of the robot. Numerical results of the generated joint trajectories are given for a kinematic redundant serial-parallel robot machine, IWR (Intersector Welding/Cutting Robot), when a particular trajectory of its end-effector has been prescribed. The numerical results show that the joint trajectories generated based on the stiffness optimization are feasible for realization in the control system since they are acceptably smooth. The results imply that the stiffness performance of the robot machine deviates smoothly with respect to the kinematic configuration in the adjacent domain of its best stiffness performance. To suppress the vibration of the robot machine due to varying cutting force during the machining process, this dissertation proposed a feedforward control strategy, which is constructed based on the derived inverse dynamics model of target system. The effectiveness of applying such a feedforward control in the vibration suppression has been validated in a parallel manipulator in the software environment. The experimental study of such a feedforward control has also been included in the dissertation. The difficulties of modelling the actual system due to the unknown components in its dynamics is noticed. As a solution, a back propagation (BP) neural network is proposed for identification of the unknown components of the dynamics model of the target system. To train such a BP neural network, a modified Levenberg-Marquardt algorithm that can utilize an experimental input-output data set of the entire dynamic system is introduced in the dissertation. Validation of the BP neural network and the modified Levenberg- Marquardt algorithm is done, respectively, by a sinusoidal output approximation, a second order system parameters estimation, and a friction model estimation of a parallel manipulator, which represent three different application aspects of this method.

Design of traction transmission and suspension systems for an omni-directional mobile robot

This project aims to design and manufacture a mobile robot with two Universal Robot UR10 mainly used indoors. In order to obtain omni-directional maneuverability, the mobile robot is constructed with Mecanum wheels. The Mecanum wheel can move in any direction with a series of rollers attached to itself. These rollers are angled at 45º about the hub’s circumference. This type of wheels can be used in both driving and steering with their any-direction property. This paper is focused on the design of traction system and suspension system, and the velocity control of Mecanum wheels in the close-loop control system. The mechanical design includes selection of bearing housing, couplers which are act as connection between shafts, motor parts, and other needed components. The 3D design software SolidWorks is utilized to assemble all the components in order to get correct tolerance. The driving shaft is designed based on assembled structure via the software as well. The design of suspension system is to compensate the assembly error of Mecanum wheels to guarantee the stability of the robot. The control system of motor drivers is realized through the Robot Operating System (ROS) on Ubuntu Linux. The purpose of inverse kinematics is to obtain the relationship among the movements of all Mecanum wheels. Via programming and interacting with the computer, the robot could move with required speed and direction.

Health, Education and Employment in a Forward-Backward Dichotomy Based on Standard of Living Index for the Tribes in Kerala

The Paper unfolds the paradox that exists in the tribal community with respect to the development indicators and hence tries to cull out the difference in the standard of living of the tribes in a dichotomous framework, forward and backward. Four variables have been considered for ascertaining the standard of living and socio-economic conditions of the tribes. The data for the study is obtained from a primary survey in the three tribal predominant districts of Wayanad, Idukki and Palakkad. Wayanad was selected for studying six tribal communities (Paniya, Adiya, Kuruma, Kurichya, Urali and Kattunaika), Idukki for two communities (Malayarayan and Muthuvan) and Palakkad for one community (Irula). 500 samples from 9 prominent tribal communities of Kerala have been collected according to multistage proportionate random sample framework. The analysis highlights the disproportionate nature of socio-economic indicators within the tribes in Kerala owing to the failure of governmental schemes and assistances meant for their empowerment. The socio-economic variables, such as education, health, and livelihood have been augmented with SLI based on correlation analysis gives interesting inference for policy options as high educated tribal communities are positively correlated with high SLI and livelihood. Further, each of the SLI variable is decomposed using Correlation and Correspondence analysis for understanding the relative standing of the nine tribal sub communities in the three dimensional framework of high, medium and low SLI levels. Tribes with good education and employment (Malayarayan, Kuruma and Kurichya) have a better living standard and hence they can generally be termed as forward tribes whereas those with a low or poor education, employment and living standard indicators (Paniya, Adiya, Urali, Kattunaika, Muthuvans and Irula) are categorized as backward tribes

A study on semigroup action on fuzzy subsets, inverse fuzzy automata and related topics

This thesis comprises five chapters including the introductory chapter. This includes a brief introduction and basic definitions of fuzzy set theory and its applications, semigroup action on sets, finite semigroup theory, its application in automata theory along with references which are used in this thesis. In the second chapter we defined an S-fuzzy subset of X with the extension of the notion of semigroup action of S on X to semigroup action of S on to a fuzzy subset of X using Zadeh's maximal extension principal and proved some results based on this. We also defined an S-fuzzy morphism between two S-fuzzy subsets of X and they together form a category S FSETX. Some general properties and special objects in this category are studied and finally proved that S SET and S FSET are categorically equivalent. Further we tried to generalize this concept to the action of a fuzzy semigroup on fuzzy subsets. As an application, using the above idea, we convert a _nite state automaton to a finite fuzzy state automaton. A classical automata determine whether a word is accepted by the automaton where as a _nite fuzzy state automaton determine the degree of acceptance of the word by the automaton. 1.5. Summary of the Thesis 17 In the third chapter we de_ne regular and inverse fuzzy automata, its construction, and prove that the corresponding transition monoids are regular and inverse monoids respectively. The languages accepted by an inverse fuzzy automata is an inverse fuzzy language and we give a characterization of an inverse fuzzy language. We study some of its algebraic properties and prove that the collection IFL on an alphabet does not form a variety since it is not closed under inverse homomorphic images. We also prove some results based on the fact that a semigroup is inverse if and only if idempotents commute and every L-class or R-class contains a unique idempotent. Fourth chapter includes a study of the structure of the automorphism group of a deterministic faithful inverse fuzzy automaton and prove that it is equal to a subgroup of the inverse monoid of all one-one partial fuzzy transformations on the state set. In the fifth chapter we define min-weighted and max-weighted power automata study some of its algebraic properties and prove that a fuzzy automaton and the fuzzy power automata associated with it have the same transition monoids. The thesis ends with a conclusion of the work done and the scope of further study.

Finding the smallest eigenvalue by the inverse Monte Carlo method with refinement

Finding the smallest eigenvalue of a given square matrix A of order n is computationally very intensive problem. The most popular method for this problem is the Inverse Power Method which uses LU-decomposition and forward and backward solving of the factored system at every iteration step. An alternative to this method is the Resolvent Monte Carlo method which uses representation of the resolvent matrix [I -qA](-m) as a series and then performs Monte Carlo iterations (random walks) on the elements of the matrix. This leads to great savings in computations, but the method has many restrictions and a very slow convergence. In this paper we propose a method that includes fast Monte Carlo procedure for finding the inverse matrix, refinement procedure to improve approximation of the inverse if necessary, and Monte Carlo power iterations to compute the smallest eigenvalue. We provide not only theoretical estimations about accuracy and convergence but also results from numerical tests performed on a number of test matrices.

Path planning of robots in noisy workspaces using learning automata

The problem of a manipulator operating in a noisy workspace and required to move from an initial fixed position P0 to a final position Pf is considered. However, Pf is corrupted by noise, giving rise to Pˆf, which may be obtained by sensors. The use of learning automata is proposed to tackle this problem. An automaton is placed at each joint of the manipulator which moves according to the action chosen by the automaton (forward, backward, stationary) at each instant. The simultaneous reward or penalty of the automata enables avoiding any inverse kinematics computations that would be necessary if the distance of each joint from the final position had to be calculated. Three variable-structure learning algorithms are used, i.e., the discretized linear reward-penalty (DLR-P, the linear reward-penalty (LR-P ) and a nonlinear scheme. Each algorithm is separately tested with two (forward, backward) and three forward, backward, stationary) actions.

An optimal inverse method using Doppler lidar measurements to estimate the surface sensible heat flux

Inverse methods are widely used in various fields of atmospheric science. However, such methods are not commonly used within the boundary-layer community, where robust observations of surface fluxes are a particular concern. We present a new technique for deriving surface sensible heat fluxes from boundary-layer turbulence observations using an inverse method. Doppler lidar observations of vertical velocity variance are combined with two well-known mixed-layer scaling forward models for a convective boundary layer (CBL). The inverse method is validated using large-eddy simulations of a CBL with increasing wind speed. The majority of the estimated heat fluxes agree within error with the proscribed heat flux, across all wind speeds tested. The method is then applied to Doppler lidar data from the Chilbolton Observatory, UK. Heat fluxes are compared with those from a mast-mounted sonic anemometer. Errors in estimated heat fluxes are on average 18 %, an improvement on previous techniques. However, a significant negative bias is observed (on average −63%) that is more pronounced in the morning. Results are improved for the fully-developed CBL later in the day, which suggests that the bias is largely related to the choice of forward model, which is kept deliberately simple for this study. Overall, the inverse method provided reasonable flux estimates for the simple case of a CBL. Results shown here demonstrate that this method has promise in utilizing ground-based remote sensing to derive surface fluxes. Extension of the method is relatively straight-forward, and could include more complex forward models, or other measurements.

Ontogenetic Changes in the Bell Morphology and Kinematics and Swimming Behavior of Rowing Medusae: the Special Case of the Limnomedusa Liriope tetraphylla

Swimming animals may experience significant changes in the Reynolds number (Re) of their surrounding fluid flows throughout ontogeny. Many medusae experience Re environments with significant viscous forces as small juveniles but inertially dominated Re environments as adults. These different environments may affect their propulsive strategies. In particular, rowing, a propulsive strategy with ecological advantages for large adults, may be constrained by viscosity for small juvenile medusae. We examined changes in the bell morphology and swimming kinematics of the limnomedusa Liriope tetraphylla at different stages of development. L. tetraphylla maintained an oblate bell (fineness ratio approximate to 0.5-0.6), large velar aperture ratio (R(v) approximate to 0.5-0.8), and rapid bell kinematics throughout development. These traits enabled it to use rowing propulsion at all stages except the very smallest sizes observed (diameter = 0.14 cm). During the juvenile stage, very rapid bell kinematics served to increase Re sufficiently for rowing propulsion. Other taxa that use rowing propulsion as adults, such as leptomedusae and scyphomedusae, typically utilize different propulsive strategies as small juveniles to function in low Re environments. We compared the performance values of the different propulsive modes observed among juvenile medusae.

The effects of anxiety on visual search, movement kinematics, and performance in table tennis: A test of Eysenck and Calvo's processing efficiency theory

Processing efficiency theory predicts that anxiety reduces the processing capacity of working memory and has detrimental effects on performance. When tasks place little demand on working memory, the negative effects of anxiety can be avoided by increasing effort. Although performance efficiency decreases, there is no change in performance effectiveness. When tasks impose a heavy demand on working memory, however, anxiety leads to decrements in efficiency and effectiveness. These presumptions were tested using a modified table tennis task that placed low (LWM) and high (HWM) demands on working memory. Cognitive anxiety was manipulated through a competitive ranking structure and prize money. Participants' accuracy in hitting concentric circle targets in predetermined sequences was taken as a measure of performance effectiveness, while probe reaction time (PRT), perceived mental effort (RSME), visual search data, and arm kinematics were recorded as measures of efficiency. Anxiety had a negative effect on performance effectiveness in both LWM and HWM tasks. There was an increase in frequency of gaze and in PRT and RSME values in both tasks under high vs. low anxiety conditions, implying decrements in performance efficiency. However, participants spent more time tracking the ball in the HWM task and employed a shorter tau margin when anxious. Although anxiety impaired performance effectiveness and efficiency, decrements in efficiency were more pronounced in the HWM task than in the LWM task, providing support for processing efficiency theory.

Built to Bite: Feeding Kinematics, Bite Forces, and Head Shape of a Specialized Durophagous Lizard, Dracaena Guianensis (Teiidae)

Most lizards feed on a variety of food items that may differ dramatically in their physical and behavioral characteristics. Several lizard families are known to feed upon hard-shelled prey (durophagy). Yet, specializations toward true molluscivory have been documented for only a few species. As snails are hard and brittle food items, it has been suggested that a specialized cranial morphology, high bite forces, and an adapted feeding strategy are important for such lizards. Here we compare head and skull morphology, bite forces, and feeding kinematics of a snail-crushing teiid lizard (Dracaena guianensis) with those in a closely related omnivorous species (Tupinambis merianae). Our data show that juvenile D. guianensis differ from T. merianae in having bigger heads and greater bite forces. Adults, however, do not differ in bite force. A comparison of feeding kinematics in adult Dracaena and Tupinambis revealed that Dracaena typically use more transport cycles, yet are more agile in manipulating snails. During transport, the tongue plays an important role in manipulating and expelling shell fragments before swallowing. Although Dracaena is slow, these animals are very effective in crushing and processing hard-shelled prey. J. Exp. Zool. 317A:371381, 2012. (c) 2012 Wiley Periodicals, Inc.