Learning Robot Motions from Visual Sensing

Learning from demonstration becomes increasingly popular as an efficient way of robot programming. Not only a scientific interest acts as an inspiration in this case but also the possibility of producing the machines that would find application in different areas of life: robots helping with daily routine at home, high performance automata in industries or friendly toys for children. One way to teach a robot to fulfill complex tasks is to start with simple training exercises, combining them to form more difficult behavior. The objective of the Master’s thesis work was to study robot programming with visual input. Dynamic movement primitives (DMPs) were chosen as a tool for motion learning and generation. Assuming a movement to be a spring system influenced by an external force, making this system move, DMPs represent the motion as a set of non-linear differential equations. During the experiments the properties of DMP, such as temporal and spacial invariance, were examined. The effect of the DMP parameters, including spring coefficient, damping factor, temporal scaling, on the trajectory generated were studied.

Mobile Teleoperation of a Mobile Robot

This thesis describes the design and implementation of a graphical application on a mobile device to teleoperate a mobile robot. The department of information technology in Lappeenranta University conducts research in robotics, and the main motivation was to extend the available teleoperation applications for mobile devices. The challenge was to port existing robot software library onto an embedded device platform, then develop a suitable user interface application that provides sufficient functionality to perform teleoperation tasks over a wireless communication network. This thesis involved investigating previous teleoperation applications and conducted similar experiments to test and evaluate the designed application for functional activity and measure performance on a mobile device which have been identified and achieved. The implemented solution offered good results for navigation purposes particularly for teleoperating a visible robot and suggests solutions for exploration when no environment map for the operator is present.

Learning Robot Environment through Simulation

Traditionally simulators have been used extensively in robotics to develop robotic systems without the need to build expensive hardware. However, simulators can be also be used as a “memory”for a robot. This allows the robot to try out actions in simulation before executing them for real. The key obstacle to this approach is an uncertainty of knowledge about the environment. The goal of the Master’s Thesis work was to develop a method, which allows updating the simulation model based on actual measurements to achieve a success of the planned task. OpenRAVE was chosen as an experimental simulation environment on planning,trial and update stages. Steepest Descent algorithm in conjunction with Golden Section search procedure form the principle part of optimization process. During experiments, the properties of the proposed method, such as sensitivity to different parameters, including gradient and error function, were examined. The limitations of the approach were established, based on analyzing the regions of convergence.

Making Sense of Shared Leadership. A case study of leadership processes and practices without formal leadership structure in the team context

Leadership is essential for the effectiveness of the teams and organizations they are part of. The challenges facing organizations today require an exhaustive review of the strategic role of leadership. In this context, it is necessary to explore new types of leadership capable of providing an effective response to new needs. The presentday situations, characterized by complexity and ambiguity, make it difficult for an external leader to perform all leadership functions successfully. Likewise, knowledge-based work requires providing professional groups with sufficient autonomy to perform leadership functions. This study focuses on shared leadership in the team context. Shared leadership is seen as an emergent team property resulting from the distribution of leadership influence across multiple team members. Shared leadership entails sharing power and influence broadly among the team members rather than centralizing it in the hands of a single individual who acts in the clear role of a leader. By identifying the team itself as a key source of influence, this study points to the relational nature of leadership as a social construct where leadership is seen as social process of relating processes that are co-constructed by several team members. Based on recent theoretical developments concerned with relational, practice-based and constructionist approaches to the study of leadership processes, this thesis proposes the study of leadership interactions, working processes and practices to focus on the construction of direction, alignment and commitment. During the research process, critical events, activities, working processes and practices of a case team have been examined and analyzed with the grounded theory –approach in the terms of shared leadership. There are a variety of components to this complex process and a multitude of factors that may influence the development of shared leadership. The study suggests that the development process of shared leadership is a common sense -making process and consists of four overlapping dimensions (individual, social, structural, and developmental) to work with as a team. For shared leadership to emerge, the members of the team must offer leadership services, and the team as a whole must be willing to rely on leadership by multiple team members. For these individual and collective behaviors to occur, the team members must believe that offering influence to and accepting it from fellow team members are welcome and constructive actions. Leadership emerges when people with differing world views use dialogue and collaborative learning to create spaces where a shared common purpose can be achieved while a diversity of perspectives is preserved and valued. This study also suggests that this process can be supported by different kinds of meaning-making and process tools. Leadership, then, does not reside in a person or in a role, but in the social system. The built framework integrates the different dimensions of shared leadership and describes their relationships. This way, the findings of this study can be seen as a contribution to the understanding of what constitutes essential aspects of shared leadership in the team context that can be of theoretical value in terms of advancing the adoption and development process of shared leadership. In the real world, teams and organizations can create conditions to foster and facilitate the process. We should encourage leaders and team members to approach leadership as a collective effort that the team can be prepared for, so that the response is rapid and efficient.

Design and development of the architecture of an agricultural mobile robot

Parameters such as tolerance, scale and agility utilized in data sampling for using in Precision Agriculture required an expressive number of researches and development of techniques and instruments for automation. It is highlighted the employment of methodologies in remote sensing used in coupled to a Geographic Information System (GIS), adapted or developed for agricultural use. Aiming this, the application of Agricultural Mobile Robots is a strong tendency, mainly in the European Union, the USA and Japan. In Brazil, researches are necessary for the development of robotics platforms, serving as a basis for semi-autonomous and autonomous navigation systems. The aim of this work is to describe the project of an experimental platform for data acquisition in field for the study of the spatial variability and development of agricultural robotics technologies to operate in agricultural environments. The proposal is based on a systematization of scientific work to choose the design parameters utilized for the construction of the model. The kinematic study of the mechanical structure was made by the virtual prototyping process, based on modeling and simulating of the tension applied in frame, using the.

Design and implementation of robot gripper interface

This thesis presents a design for an asynchronous interface to Robotiq adaptive gripper s-model. Designed interface is a communication layer that works on top of modbus layer. The design contains function definitions, finite state machine and exceptions. The design was not fully implemented but enough was so that it can be used. The implementation was done with c++ in linux environment. Additionally to the implementation a simple demo program was made to show the interface is used. Also grippers closing speed and force were measured. There is also a brief introduction into robotics and robot grasping.

Novel Methods for Error Modeling and Parameter Identification of a Redundant Serial-Parallel Hybrid Robot

To obtain the desirable accuracy of a robot, there are two techniques available. The first option would be to make the robot match the nominal mathematic model. In other words, the manufacturing and assembling tolerances of every part would be extremely tight so that all of the various parameters would match the “design” or “nominal” values as closely as possible. This method can satisfy most of the accuracy requirements， but the cost would increase dramatically as the accuracy requirement increases. Alternatively, a more cost-effective solution is to build a manipulator with relaxed manufacturing and assembling tolerances. By modifying the mathematical model in the controller, the actual errors of the robot can be compensated. This is the essence of robot calibration. Simply put, robot calibration is the process of defining an appropriate error model and then identifying the various parameter errors that make the error model match the robot as closely as possible. This work focuses on kinematic calibration of a 10 degree-of-freedom (DOF) redundant serial-parallel hybrid robot. The robot consists of a 4-DOF serial mechanism and a 6-DOF hexapod parallel manipulator. The redundant 4-DOF serial structure is used to enlarge workspace and the 6-DOF hexapod manipulator is used to provide high load capabilities and stiffness for the whole structure. The main objective of the study is to develop a suitable calibration method to improve the accuracy of the redundant serial-parallel hybrid robot. To this end, a Denavit–Hartenberg (DH) hybrid error model and a Product-of-Exponential (POE) error model are developed for error modeling of the proposed robot. Furthermore, two kinds of global optimization methods, i.e. the differential-evolution (DE) algorithm and the Markov Chain Monte Carlo (MCMC) algorithm, are employed to identify the parameter errors of the derived error model. A measurement method based on a 3-2-1 wire-based pose estimation system is proposed and implemented in a Solidworks environment to simulate the real experimental validations. Numerical simulations and Solidworks prototype-model validations are carried out on the hybrid robot to verify the effectiveness, accuracy and robustness of the calibration algorithms.

Perfil hematológico de equinos submetidos à prova de Team Penning

As variações nos parâmetros hematológicos são utilizadas com intuito de avaliar o grau de treinamento ou estado clínico do animal. A avaliação hematológica de eqüinos em repouso tem sido objeto de estudo, a fim de estabelecer uma relação com treinamento ou capacidade atlética. Objetivou-se avaliar o perfil hematológico de eqüinos submetidos à prova de Team Penning, correlacionando o sexo e freqüência da atividade física. Mediante punção da veia jugular externa coletaram-se dois mL de sangue de 29 eqüinos, 18 machos e 11 fêmeas, em repouso (Momento I) e após o exercício (Momento II). As amostras de sangue foram processadas em analisador hematológico automático veterinário (ABC VET - Horiba ABX Diagnostics). Os animais foram divididos em Grupos A, B, C e D, de acordo com o número de participações na prova. Observou-se que os valores de volume globular, hemoglobina, hemácias, leucócitos, neutrófilos em bastonetes e segmentados, e monócitos aumentaram após o exercício físico, ao contrário do número de linfócitos e eosinófilos, que reduziram. Não existiram diferenças significativas (p<0,05) entre machos e fêmeas ao confrontar as relações antes/depois. Além disso, evidenciou-se que o valor da relação MI/MII para volume globular, hemoglobina e número de hemácias variou de acordo com a freqüência do exercício. Conclui-se que a prova de Team Peninng ocasiona alterações hematológicas em eqüinos, com interferência da freqüência do exercício, independente do sexo.

Dynamic optimization for the trajectory planning of robot manipulators in the presence of obstacles

This paper presents an approach to the solution of moving a robot manipulator with minimum cost along a specified geometric path in the presence of obstacles. The main idea is to express obstacle avoidance in terms of the distances between potentially colliding parts. The optimal traveling time and the minimum mechanical energy of the actuators are considered together to build a multiobjective function. A simple numerical example involving a Cartesian manipulator arm with two-degree-of-freedom is described.

Modeling, optimizing and simulating robot calibration with accuracy improvement

This work describes techniques for modeling, optimizing and simulating calibration processes of robots using off-line programming. The identification of geometric parameters of the nominal kinematic model is optimized using techniques of numerical optimization of the mathematical model. The simulation of the actual robot and the measurement system is achieved by introducing random errors representing their physical behavior and its statistical repeatability. An evaluation of the corrected nominal kinematic model brings about a clear perception of the influence of distinct variables involved in the process for a suitable planning, and indicates a considerable accuracy improvement when the optimized model is compared to the non-optimized one.

Control of a one-legged robot with energy savings

This paper presents a new strategy to control an one-legged robot aiming to reduce the energy expended by the system. To validate this algorithm, a classic method as benchmark was used. This method has been extensively validated by simulations and experimental prototypes in the literature. For simplicity reasons, the work is restricted to the two dimensional case due to simplicity reasons. This new method is compared to the classic one with respect to performance and energy expended by the system. The model consists on a springy leg, a simple body, and an actuated hinge-type hip. The new control strategy is composed of three parts, considering the hopping height, the forward speed, and the body orientation separately. The method exploits the system passive dynamics, defined as non-forced response of the system. In this case, the model is modified adding a spring to the hip. The method defines a desired leg trajectory close to the passive hip swing movement. Simulation results for both methods are analyzed and compared.

Speed Control of an Autonomous Mobile Robot: Comparison between a PID Control and a Control Using Fuzzy Logic

An Autonomous Mobile Robot battery driven, with two traction wheels and a steering wheel is being developed. This Robot central control is regulated by an IPC, which controls every function of security, steering, positioning localization and driving. Each traction wheel is operated by a DC motor with independent control system. This system is made up of a chopper, an encoder and a microcomputer. The IPC transmits the velocity values and acceleration ramp references to the PIC microcontrollers. As each traction wheel control is independent, it's possible to obtain different speed values for each wheel. This process facilities the direction and drive changes. Two different strategies for speed velocity control were implemented; one works with PID, and the other with fuzzy logic. There were no changes in circuits and feedback control, except for the PIC microcontroller software. Comparing the two different speed control strategies the results were equivalent. However, in relation to the development and implementation of these strategies, the difficulties were bigger to implement the PID control.

A Test Bed Applied Mobile Robot Navigation

It is presented a test bed applied to studies on dynamics, control, and navigation of mobile robots. A cargo ship scale model was chosen, which can be radio-controlled or operated autonomously through an embedded control system. A control program, which manages on board mission execution, is implemented on a microcontroller. Navigation is based on an electronic compass, which includes automatic compensation for pitch and roll motions. Heading control loop is based on this sensor, and on a rudder positioning system. A propulsion control system is also implemented. Typical manoeuvres as the turning test and "zig-zag", were implemented and tested. They are included on a manoeuvre library, and can be accessed independently or in combined modes. The embedded system is also in charge of signal acquisition and storing during the missions. It is possible to analyse experiments on identification of ship dynamics, control, and navigation, through the data transferred to a PC by serial communication. Navigation is going to be improved by including inertial sensors on board, and a DGPS. Preliminary tests are aimed to ship identification, and manoeuvrability, using free model tests. Future steps include extending this system for developing other mobile robots as, ROVs, AUVs, and aerial vehicles.