We look at robotic systems made of separate discrete components that, by self-assembling, can organize into physical structures of growing size. We review 22 such systems, exhibiting components ranging from passive mechanical parts to mobile<p>robots. We present a taxonomy of the systems, and discuss their design and function. We then focus on a particular system, the swarm-bot. In swarm-bot, the components that assemble are self-propelled modules that are fully autonomous in power, perception, computation, and action. We examine the additional capabilities and functions self-assembly can offer an autonomous group of modules for the accomplishment of a concrete task: the transport of an object. The design of controllers is accomplished in simulation using<p>techniques from biologically-inspired computing. We show that self-assembly can offer adaptive value to groups that compete in an artificial evolution based on their fitness in task performance. Moreover, we investigate mechanisms that facilitate the design of self-assembling systems. The controllers are transferred to the physical swarm-bot system, and the capabilities of self-assembly and object transport are extensively evaluated in a range of different environments. Additionally, the controller for self-assembly is transferred and evaluated on a different robotic system, a super-mechano colony. Given the breadth and quality of the results obtained, we can say that the swarm-bot qualifies as the current state of the art in self-assembling robots. Our work supplies some initial evidence (in form of simulations and experiments with the swarm-bot) that self-assembly can offer robotic systems additional capabilities and functions useful for the accomplishment of concrete tasks.<p> / Doctorat en Sciences de l'ingénieur / info:eu-repo/semantics/nonPublished

Made available in DSpace on 2015-03-05T13:58:27Z (GMT). No. of bitstreams: 0 Previous issue date: 10 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / O objetivo desta dissertação é propor, testar e avaliar o uso de técnicas de Aprendizado de Máquina (ML) na configuração automática do controle do caminhar de robôs com pernas. Para que este objetivo fosse atingido, um extensa pesquisa de técnicas do estado da arte foi realizada e descrita neste trabalho. Esta pesquisa permitiu a elaboração do modelo proposto, chamado de LegGen, que foi implementado em um protótipo. O protótipo modelo em questão permite a utilização de vários tipos de robôs, compostos de quatro, seis ou mais patas, e além disto permite a evolução da morfologia dos robôs. Utilizando o protótipo, é possível a realização de experimentos com robôs autônomos dotados de pernas, em um ambiente virtual tridimensional realístico, através de simulações baseadas em física. Foi utilizada a biblioteca ODE (Open Dynamics Engine) para a simulação de corpos rígidos e articulações, permitindo assim simular forças agindo nas articulações (atuadores), gravidade e colisões, entre outras propriedades físicas dos / The main goal of this dissertation is to propose, to test and to evaluate the use of Machine Learning (ML) techniques in the automatic con_guration of the gait control in legged robots. In order to achieve this goal, an extensive research about state-of-the-art techniques was accomplished and they are described in this work. This research allowed the development of the proposed model, called LegGen, which was implemented in a prototype. The proposed model allows the use of several different robot models with four, six or more paws. Besides that, the prototype allows also to study the robot's morphology evolution. The implemented prototype allows to accomplish experiments with autonomous legged robots, in a realistic three-dimensional virtual environment, through physics based simulations. The ODE (Open Dynamics Engine) software library was used in the physical simulation of rigid bodies and articulations, allowing to simulate forces acting in the articulations (actuators), gravity and collisions, among other

Purpose – The purpose of the study is to expand the knowledge of how wheel motor currents can be combined with machine learning to be used in a collision detection system for autonomous robots, in order to decrease the number of external sensors and open new design opportunities and lowering production costs. Method – The study is conducted with design science research where two artefacts are developed in a cooperation with Globe Tools Group. The artefacts are evaluated in how they categorize data given by an autonomous robot in the two categories collision and non-collision. The artefacts are then tested by generated data to analyse their ability to categorize. Findings – Both artefacts showed a 100 % accuracy in detecting the collisions in the given data by the autonomous robot. In the second part of the experiment the artefacts show that they have different decision boundaries in how they categorize the data, which will make them useful in different applications. Implications – The study contributes to an expanding knowledge in how machine learning and wheel motor currents can be used in a collision detection system. The results can lead to lowering production costs and opening new design opportunities. Limitations – The data used in the study is gathered by an autonomous robot which only did frontal collisions on an artificial lawn. Keywords – Machine learning, K-Nearest Neighbour, Multilayer Perceptron, collision detection, autonomous robots, Collison detection based on current. / Syfte – Studiens syfte är att utöka kunskapen om hur hjulmotorstömmar kan kombineras med maskininlärning för att användas vid kollisionsdetektion hos autonoma robotar, detta för att kunna minska antalet krävda externa sensorer hos dessa robotar och på så sätt öppna upp design möjligheter samt minska produktionskostnader Metod – Studien genomfördes med design science research där två artefakter utvecklades i samarbete med Globe Tools Group. Artefakterna utvärderades sedan i hur de kategoriserade kollisioner utifrån en given datamängd som genererades från en autonom gräsklippare. Studiens experiment introducerade sedan in data som inte ingick i samma datamängd för att se hur metoderna kategoriserade detta. Resultat – Artefakterna klarade med 100% noggrannhet att detektera kollisioner i den giva datamängden som genererades. Dock har de två olika artefakterna olika beslutsregioner i hur de kategoriserar datamängderna till kollision samt icke-kollisioner, vilket kan ge dom olika användningsområden Implikationer – Examensarbetet bidrar till en ökad kunskap om hur maskininlärning och hjulmotorströmmar kan användas i ett kollisionsdetekteringssystem. Studiens resultat kan bidra till minskade kostnader i produktion samt nya design möjligheter Begränsningar – Datamängden som användes i studien samlades endast in av en autonom gräsklippare som gjorde frontalkrockar med underlaget konstgräs. Nyckelord – Maskininlärning, K-nearest neighbor, Multi-layer perceptron, kollisionsdetektion, autonoma robotar

No description available.

Made available in DSpace on 2014-12-17T14:56:04Z (GMT). No. of bitstreams: 1 DennisBA.pdf: 1210954 bytes, checksum: f42a19fb396d47e801ab673ab1f88887 (MD5) Previous issue date: 2005-10-14 / Conselho Nacional de Desenvolvimento Cient?fico e Tecnol?gico / In multi-robot systems, both control architecture and work strategy represent a challenge for researchers. It is important to have a robust architecture that can be easily adapted to requirement changes. It is also important that work strategy allows robots to complete tasks efficiently, considering that robots interact directly in environments with humans. In this context, this work explores two approaches for robot soccer team coordination for cooperative tasks development. Both approaches are based on a combination of imitation learning and reinforcement learning. Thus, in the first approach was developed a control architecture, a fuzzy inference engine for recognizing situations in robot soccer games, a software for narration of robot soccer games based on the inference engine and the implementation of learning by imitation from observation and analysis of others robotic teams. Moreover, state abstraction was efficiently implemented in reinforcement learning applied to the robot soccer standard problem. Finally, reinforcement learning was implemented in a form where actions are explored only in some states (for example, states where an specialist robot system used them) differently to the traditional form, where actions have to be tested in all states. In the second approach reinforcement learning was implemented with function approximation, for which an algorithm called RBF-Sarsa($lambda$) was created. In both approaches batch reinforcement learning algorithms were implemented and imitation learning was used as a seed for reinforcement learning. Moreover, learning from robotic teams controlled by humans was explored. The proposal in this work had revealed efficient in the robot soccer standard problem and, when implemented in other robotics systems, they will allow that these robotics systems can efficiently and effectively develop assigned tasks. These approaches will give high adaptation capabilities to requirements and environment changes. / Em sistemas multi-rob?s a arquitetura de controle e a estrat?gia de trabalho representam um desafio para os pesquisadores. ? importante que a arquitetura de controle seja robusta, de forma que se adapte naturalmente ?s mudan?as nas caracter?sticas do problema e tamb?m que a estrat?gia de trabalho permita aos rob?s desenvolver as tarefas atribu?das eficaz e eficientemente, levando em considera??o a restri??o de que os rob?s v?o interagir diretamente em ambientes povoados de seres humanos. Neste contexto, este trabalho explora duas abordagens para a coordena??o de uma frota de rob?s desenvolvendo tarefas cooperativas. Ambas as abordagens s?o baseadas em uma mistura de aprendizado por imita??o e por experi?ncia. Assim, na primeira abordagem desenvolveu-se uma arquitetura de controle, uma m?quina de infer?ncia difusa para reconhecimento de fatos em jogos de futebol, um software narrador de jogos baseado na m?quina de infer?ncia difusa, e a implementa??o de aprendizado por imita??o a partir de observa??o e an?lise de outros times rob?ticos. Al?m disso, aplicou-se eficientemente abstra??o de estados em aprendizado por refor?o no problema padr?o de futebol de rob?s. Finalmente, o aprendizado por refor?o foi implementado de forma que as a??es somente s?o executadas em certos estados (por exemplo os estados onde algum sistema rob?tico especialista j? as utilizou) diferentemente da forma tradicional onde as a??es no banco de conhecimento t?m que ser testadas em todos os estados. No caso da segunda abordagem, implementou-se aprendizado por refor?o com aproxima??o de fun??es, para o que foi criado um algoritmo chamado RBF-Sarsa($lambda$). Em ambas as abordagens implementou-se o aprendizado por refor?o em lotes e o aprendizado por imita??o como semente para aprendizado por refor?o. Al?m disso, explorou-se o aprendizado com times de rob?s controlados por seres humanos. As propostas deste trabalho mostraram-se eficientes no problema padr?o de futebol de rob?s, e ao serem implementadas em outros sistemas rob?ticos permitir?o que os mesmos sejam eficazes e eficientes no desenvolvimento das tarefas atribu?das com um alto grau de adapta??o ?s mudan?as dos requerimentos e do ambiente.

No description available.

No description available.

<div>The recent progress of machine learning, driven by pervasive data and increasing computational power, has shown its potential to achieve higher robot autonomy. Yet, with too much focus on generic models and data-driven paradigms while ignoring inherent structures of control systems and tasks, existing machine learning methods typically suffer from data and computation inefficiency, hindering their public deployment onto general real-world robots. In this thesis work, we claim that the efficiency of autonomous robot learning can be boosted by two strategies. One is to incorporate the structures of optimal control theory into control-objective learning, and this leads to a series of control-induced learning methods that enjoy the complementary benefits of machine learning for higher algorithm autonomy and control theory for higher algorithm efficiency. The other is to integrate necessary human guidance into task and control objective learning, leading to a series of paradigms for robot learning with minimal human guidance on the loop.</div><div><br></div><div>The first part of this thesis focuses on the control-induced learning, where we have made two contributions. One is a set of new methods for inverse optimal control, which address three existing challenges in control objective learning: learning from minimal data, learning time-varying objective functions, and learning under distributed settings. The second is a Pontryagin Differentiable Programming methodology, which bridges the concepts of optimal control theory, deep learning, and backpropagation, and provides a unified end-to-end learning framework to solve a broad range of learning and control tasks, including inverse reinforcement learning, neural ODEs, system identification, model-based reinforcement learning, and motion planning, with data- and computation- efficient performance.</div><div><br></div><div>The second part of this thesis focuses on the paradigms for robot learning with necessary human guidance on the loop. We have made two contributions. The first is an approach of learning from sparse demonstrations, which allows a robot to learn its control objective function only from human-specified sparse waypoints given in the observation (task) space; and the second is an approach of learning from</div><div>human’s directional corrections, which enables a robot to incrementally learn its control objective, with guaranteed learning convergence, from human’s directional correction feedback while it is acting.</div><div><br></div>

Indiana University-Purdue University Indianapolis (IUPUI) / There have been many endeavors to design humanoid robots that have human characteristics such as dexterity, autonomy and intelligence. Humanoid robots are intended to cooperate with humans and perform useful work that humans can perform. The main advantage of humanoid robots over other machines is that they are flexible and multi-purpose. In this thesis, a human-like robotic arm is designed and used in a task which is typically performed by humans, namely, catching a ball. The robotic arm was designed to closely resemble a human arm, based on anthropometric studies. A rigid multibody dynamics software was used to create a virtual model of the robotic arm, perform experiments, and collect data. The inverse kinematics of the robotic arm was solved using a Newton-Raphson numerical method with a numerically calculated Jacobian. The system was validated by testing its ability to find a kinematic solution for the catch position and successfully catch the ball within the robot's workspace. The tests were conducted by throwing the ball such that its path intersects different target points within the robot's workspace. The method used for determining the catch location consists of finding the intersection of the ball's trajectory with a virtual catch plane. The hand orientation was set so that the normal vector to the palm of the hand is parallel to the trajectory of the ball at the intersection point and a vector perpendicular to this normal vector remains in a constant orientation during the catch. It was found that this catch orientation approach was reliable within a 0.35 x 0.4 meter window in the robot's workspace. For all tests within this window, the robotic arm successfully caught and dropped the ball in a bin. Also, for the tests within this window, the maximum position and orientation (Euler angle) tracking errors were 13.6 mm and 4.3 degrees, respectively. The average position and orientation tracking errors were 3.5 mm and 0.3 degrees, respectively. The work presented in this study can be applied to humanoid robots in industrial assembly lines and hazardous environment recovery tasks, amongst other applications.