DOCSLIB.ORG

DEPENDABLE PATH PLANNING for AUTONOMOUS CONTROL AUTONOMOUS for PATH PLANNING DEPENDABLE Autonomous Control

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
DEPENDABLE PATH PLANNING for AUTONOMOUS CONTROL AUTONOMOUS for PATH PLANNING DEPENDABLE Autonomous Control Mälardalen University Licentiate Thesis 288 Lan Anh Trinh Dependable Path Planning For DEPENDABLE PLANNING PATH FOR AUTONOMOUS CONTROL Autonomous Control Lan Anh Trinh Address: P.O. Box 883, SE-721 23 Västerås. Sweden ISBN 978-91-7485-451-0 2019 Address: P.O. Box 325, SE-631 05 Eskilstuna. Sweden E-mail: [email protected] Web: www.mdh.se ISSN 1651-9256 1 Mälardalen University Press Licentiate Theses No. 288 DEPENDABLE PATH PLANNING FOR AUTONOMOUS CONTROL Lan Anh Trinh 2019 School of Innovation, Design and Engineering 2 Copyright © Lan Anh Trinh, 2019 ISBN 978-91-7485-451-0 ISSN 1651-9256 Printed by E-Print AB, Stockholm, Sweden 3 To my family. 4 Acknowledgments I would like to express my thanks to many persons who have directly and indi- rectly helped me on the path that leads to this dissertation. First and foremost, I especially thank my supervisors, Professor Dr. Mikael Ekstrom¨ and Dr. Baran Cur¨ ukl¨ u,¨ who have guided and supported my research with warm encourage- ment and insightful advice. I also thank for their great helps in life so that I can understand more about Swedish culture, overcome all difficulties, settle down and feel that Sweden is my second mother land. I also especially thank all MDH gangs, PhD students in Malardalen Uni- versity, who are very good, friendly, and enthusiastic. Even though we do not communicate much, you guys always give me nice advices when needed. Many thanks to all of my friends in Robotics Group, who have been always very nice and friendly teammates, Fredrik, Carl, and others, especially two my office-mates Gita and Branko, who have helped me a lots in both researches and life. Many next thanks to DPAC leaders who have proposed an excellent project so that I have learnt a lots and enjoyed working within the project. I am always thankful to administrative ladies who have made all the complicated administrative procedures to become easy and smooth. Last but not least, I would like to especially thank my family in Vietnam, my husband, and my little Sam for their unconditional supports, endless love, and encouragement. They are my accompany at every stage in my educa- tion and life. They are the ones I can always share the burden of stress. My motivation is also contributed by the love from them and their belief for this iv 5 v dissertation. I want to dedicate this thesis to them whom I love most in my life. Lan Anh Trinh Vaster¨ as,˚ December, 2019 6 7 Sammanfattning Att byta fran˚ automatisk till autonom kontroll har visat sig vara ett av de vik- tigaste teknikskiften vid utvecklingen av robotar idag. Den autonoma kon- trollen gor¨ det mojligt¨ for¨ en robot att ha mer frihet samt mojlighet¨ till di- rekt interaktion med manniskor¨ och andra robotar. Att ha en palitlig˚ plattform for¨ autonom kontroll blir daavg˚ orande¨ nar¨ vid byggandet av ett sadant˚ sys- tem. Tillforlitligheten¨ hos en robotagent representeras av ett antal huvudat- tribut sasom˚ tillganglighet,¨ dvs systemets kontinuerliga drift over¨ ett tidsinter- vall, tillforlitlighet,¨ dvs systemets form¨ aga˚ att tillhandahalla˚ korrekta tjanster,¨ och sakerhet,¨ dvs. robotagenten maste˚ sakerst¨ alla¨ sakra¨ kontroller for¨ att und- vika katastrofala konsekvenser for¨ anvandare,¨ andra robotar och slutligen miljon.¨ Med tanke paatt˚ banplanering ar¨ en av nyckelkomponenterna i ett autonomt kontrollsystem for¨ robotagenter, syftar arbetena som presenteras i denna avhan- dling att bygga en palitlig,˚ dvs saker,¨ palitlig˚ och effektiv banplaneringsal- goritm for¨ en grupp robotar som delar sitt arbetsutrymme med manniskor.¨ For¨ det forsta¨ foresl¨ as˚ en ny metod for¨ banplanering av flera robotagenter baserat padipolfl˚ odesf¨ alt.¨ For¨ att initialisera vagarna¨ fran˚ en startpunkt till ett mal˚ anvands¨ banplanering med Theta* - algoritmen for¨ en uppsattning¨ av agenter. For¨ att hantera statiska hinder for¨ en robot som ar¨ pav˚ ag¨ till malet˚ definieras ett statiskt flodesf¨ alt¨ langs¨ den konfigurerade banan. Ett dipolfalt¨ beraknas¨ sedan for¨ att undvika kollision med andra agenter och personer. I detta tillvagag¨ angss˚ att¨ antas varje robotagent vara en kalla¨ till ett magnetiskt dipolfalt,¨ i vilket det magnetiska momentet ar¨ riktat i agentens rorelseriktning,¨ vii 8 viii med en styrka som ar¨ proportionell mot dess hastighet. De magnetiska dipol- dipolinteraktionerna mellan dessa agenter genererar darepulsiva˚ krafter for¨ att hjalpa¨ dem att undvika kollision. Samtidigt anvands¨ felanalys med Petri-nat¨ av flera robotar for¨ att forst¨ asamarbetet˚ mellan flera robotagenter for¨ att losa¨ de gemensamma uppgifterna. Darefter¨ appliceras Petri-natet¨ tillsammans med vagplaneringen¨ for¨ att undvika kollisioner genom synkroniserade rorelser¨ hos robotar genom exempelvis en korsning. Under tiden har kontinuerligt flervags-¨ planering undersokts¨ for¨ att stodja¨ feltoleransen for¨ sokplaneringsalgoritmen.¨ Detta for¨ att hantera dodl¨ aget¨ dar¨ agenten tar mycket lang˚ tid att nam˚ alet˚ eller till och med inte kan gora¨ det. Agenten har forsetts¨ med olika planer- ade vagar¨ till malet˚ och vaxlar¨ proaktivt mellan dessa nar¨ det behovs¨ for¨ att undvika dodl¨ aget.¨ Slutligen har hela ramverket implementerats i en allmant¨ anvand¨ plattform, robotoperativsystem (ROS), och utvarderats¨ genom Gazebo- simulator. 9 Abstract Changing from automatic to autonomous control has emerged as the main shift on the development of robots nowadays. The autonomous control allows robot to have more freedom as well as direct interactions with human and other robots. Having a dependable platform for autonomous control becomes crucial when building such a system. The dependability of a robotic agent is presented by main attributes including availability, i.e. the continuous operations of the system over a time interval, reliability, i.e. the ability of the system to provide correct services, and safety, i.e. the robotic agent must ensure safe controls to avoid any catastrophic consequences on users, other robots, and finally the environment. Considering path planning is one of the key components of an autonomous control system for robotic agents, the works presented in this the- sis aim at building a dependable, i.e. safe, reliable and effective, path planning algorithm for a group of robots that share their working space with humans. Firstly, the method for path planning of multiple robotic agents is proposed based on a novel dipole flow field idea. The any angle-path planning with Theta* algorithm is employed to initialise the paths from a starting point to a goal for a set of agents. To deal with static obstacles while a robot is going on the way to its goal, a static flow field along the configured path is defined. A dipole field is then calculated to avoid the collision of agents with the other agents and human subjects. In this approach, each robotic agent is assumed to be a source of a magnetic dipole field in which the magnetic moment is aligned with the moving direction of the agent, with a strength proportional the ix 10 x velocity. The magnetic dipole-dipole interactions between these agents gen- erate repulsive forces to help them to avoid collision. Meanwhile, the fault analysis of multiple robots with Petri net is demonstrated to understand the cooperation of multiple robotic agents to solve the shared tasks. Thereafter, the Petri net is applied together with the path planning to address the collision avoidance by synchronising the movement of robots through a cross. Continu- ously, the multiple path planning has investigated to support fault tolerance for the path planning algorithm. This is to deal with the deadlock situation where the agent takes very long time to reach the goal or even is not able to do so. The agent is equipped with different paths to the goal and proactively switch among the plans whenever needed to avoid the deadlock. Finally, the whole framework has been implemented by a widely used platform, robot operating system (ROS), and evaluated through Gazebo simulator. 11 List of Publications Papers Included in the Licentiate Thesis1 Paper A Fault Tolerant Analysis for Dependable Autonomous Agents Using Colored Time Petri Nets Authors: Lan Anh Trinh, Baran Cur¨ ukl¨ u,¨ Mikael Ekstrom¨ Status: Published in 9th International Conference on Agents and Artificial In- telligence, ICAART 2017. Paper B Toward Shared Working Space of Human and Robotics Agents Through Dipole Flow Field for Dependable Path Planning Authors: Lan Anh Trinh, Mikael Ekstrom,¨ Baran Cur¨ ukl¨ u¨ Status: Published in Frontiers in Neurorobotics, volume 12, May 2018. Paper C Petri Net Based Navigation Planning with Dipole Field and Dy- namic Window Approach for Collision Avoidance Authors: Lan Anh Trinh, Mikael Ekstrom,¨ Baran Cur¨ ukl¨ u¨ Status: Published in 6th International Conference on Control, Decision and Information Technologies, CODIT 2019. Paper D Multi-Path Planning for Autonomous Navigation of Multiple Robots in a Shared Workspace with Humans 1The included papers have been reformatted to comply with the thesis layout xi 12 xii Authors: Lan Anh Trinh, Mikael Ekstrom,¨ Baran Cur¨ ukl¨ u¨ Status: Submitted. 13 xiii Additional Peer-Reviewed Publications, not Included in the Licentiate Thesis • ”Dipole Flow Field for Dependable Path Planning of Multiple Agents”. Lan Anh Trinh, Mikael Ekstrom,¨ Baran Cur¨ ukl¨ u.¨ Workshop on Shared Autonomoy, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017. • ”Failure Analysis for Adaptive Autonomous Agents using Petri Nets”. Mirgita Frasheri, Lan Anh Trinh, Baran Cur¨ ukl¨ u,¨ Mikael Ekstrom.¨ The 11th International Workshop on Multi-Agent Systems and Simulation (MAS&S’17). • ”Dependability for Autonomous Control with a Probability Approach”. Lan Anh Trinh, Baran Cur¨ ukl¨ u,¨ Mikael Ekstrom.¨ Newsletter in ERCIM News 109, Autonomous Vehicles. 14 15 Contents I Thesis 1 1 Introduction 3 2 Backgrounds 7 2.1 DEPENDABILITY AND PETRI NET . .7 2.1.1 Dependability . .7 2.1.2 Petri nets . 10 2.2 PATH PLANNING AND THETA* . 11 2.3 DYNAMIC WINDOW APPROACH . 14 3 Related Works 17 3.1 DEPENDABILITY FOR AUTONOMOUS CONTROL .
Load more

Recommended publications
  • Contributions to Adaptive Mission Planning for Cooperative Robotics in the Internet of Things
    Universidad Politécnica de Madrid Departamento de Ingeniería Telemática y Electrónica Contributions to Adaptive Mission Planning for Cooperative Robotics in the Internet of Things Author: Néstor Lucas Martínez, MSc Supervisor: José Fernán Martínez Ortega, PhD This dissertation is submitted for the degree of PhD. in Systems and Services Engineering for the Information Society Escuela Técnica Superior de Ingeniería y Sistemas de Telecomunicación March 2021 DOCTORADO EN INGENIERÍA DE SISTEMAS Y SERVICIOS PARA LA SOCIEDAD DE LA INFORMACIÓN Tesis Doctoral Título Contributions to Adaptive Mission Planning for Cooperative Robotics in the Internet of Things Autor Néstor Lucas Martínez VºBº Director Dr. José-Fernán Martínez Ortega Tribunal Presidente M. Encarnación Pastor Martín Secretario Lourdes López Santidrián Vocal Celeste Campo Vázquez Vocal Miguel Ángel López Carmona Vocal Roemi Emilia Fernández Saavedra Suplente Juan Ramón Velasco Pérez Suplente Rodolfo E. Haber Guerra Lugar de lectura E.T.S.I. y Sistemas de Telecomunicación (U.P.M.) Fecha de lectura Calificación El Presidente El secretario Los vocales Tesis Doctoral para la obtención del título de Doctor por la Universidad Politécnica de Madrid This Ph.D. Thesis is dedicated to my family and friends. With a special memory to all the people affected by the COVID-19 global pandemic. Declaration I hereby declare that except where specific reference is made to the work of others, the contents of this dissertation are original and have not been submitted in whole or in part for consideration for any other degree or qualification in this, or any other university. This dissertation is my own work and contains nothing which is the outcome of work done in collaboration with others, except as specified in the text and Acknowledgements.
    [Show full text]
  • Insectomorphic Cargo-Carrying Robot on a Raft
    CLAWAR 2020: 23rd International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, Moscow, Russian Federation, 24-26 August 2020. https://doi.org/10.13180/clawar.2020.24-26.08.14 INSECTOMORPHIC CARGO-CARRYING ROBOT ON A RAFT YURY F. GOLUBEV and VICTOR V. KORYANOV Keldysh Institute of Applied Mathematics, Russian Academy of Sciences, Moscow, 125047 Russia E-mail: [email protected], [email protected] The algorithm of the hexapod robot motion control is described. The aim of the motion is to ship the robot on a raft together with a cargo to the other shore of a body of water in the simple case when the robot imparts to the raft an initial push from the shore. The motion consists of transporting the cargo from the shore to the raft, moving the cargo across the moving raft, and carrying the cargo from the raft to the other shore. The algorithm was worked out using computer simulation within the complete dynamical model of motion taking into account the nonstationary action of water on the raft. Computer simulation was performed using the Universal Mechanism software package. Numerical results prove the validity of the algorithm if enough data about the motion for the purpose of control is available. 1. Introduction An autonomous mobile robot designed for working on a rough terrain must be able to use environment conditions and various objects available in the area not only as a means for its motion [1] but also as a means for shipping useful cargos [2-4]. A hexapod mobile robot can potentially accomplish such tasks because it is able to release weight from a pair of its legs without violating the static stability [1].
    [Show full text]
  • Artificial Intelligence Definitions Ai Based
    Sold to Muhammad Shakur (#7XO5FTFO) ARTIFICIAL INTELLIGENCE: Dangers to Humanity Table of Contents ARTIFICIAL INTELLIGENCE DEFINITIONS Artificial Narrow Intelligence Artificial General Intelligence Artificial Super Intelligence Notice: AI BASED COMPANIES, ORGANIZATIONS, APPS AND PERSONS OF INTEREST. Huawei SECTION 2 Human Targeting Capability SECTION 3 Drone Swarm Automation Via Robots, Command Centers & AI Sold to Muhammad Shakur (#7XO5FTFO) MICRO-BOTIC (MBT) TERRORISM, ASSASSINATION & ESPIONAGE WITH BIO-METRIC SOFTWARE The Insect Drone CHINA DEPLOYS ROBOT POLICE ON CITIZENS 500 Smart Cities, Surveillance, and Tracking of Human Being’s via 5G and Robotics SECTION 4 China’s Military has Access to Bio-Metric & Facial Recognition Data of 6 Billion People World-Wide How they Extract your Data & Track You AI Automated Tracking at Shopping Centers SECTION 5 ONE BELT ONE ROAD – Bio-Digital Social Programming TRUMPS HUAWEI FIGHT IS REALLY ABOUT AI AUTOMATED ROBOTICS MOBILIZED WITH 5G Sold to Muhammad Shakur (#7XO5FTFO) HUMAN ORGAN TRAFFICKING & CONCENTRATION CAMPS IN CHINA ARTIFICIAL INTELLIGENCE WITH FACIAL RECOGNITION HUNTS HONG KONG YOUTH FOR CAPTURE, RAPE & SO CALLED SUICIDE China has Access to 6 Billion Peoples Bio-Metric/Facial Recognition Data SECTION 7 Bio-Digital Social Programming SECTION 8 Smart Phones, IoT, Apps, Computers, and Electronic Devices SECTION 9 AI Platforms Produce Destruction Codes Artificial Intelligence Sex Robots Programmed for Deep Learning Sold to Muhammad Shakur (#7XO5FTFO) Neurological Damage From Connecting Robot
    [Show full text]
  • Experience with Rover Navigation for Lunar-Like Terrains
    Experience with Rover Navigation for Lunar-Like Terrains Reid Simmons, Eric Krotkov, Lonnie Chrisman, Fabio Cozman, Richard Goodwin, Martial Hebert, Lalitesh Katragadda, Sven Koenig, Gita Krishnaswamy, Yoshikazu Shinoda, and William Whittaker The Robotics’s Institute, Carnegie Mellon University Pittsburgh, PA 15213 Paul Klarer Sandia National Laboratories Albuquerque, NM 87185 Abstract vision, local obstacle avoidance, position estimation, and mixed-mode operation (autonomous, semi-autonomous, Reliable navigation is critical for a lunar rover, both for and teleoperated). The aim is to provide both the autonomous traverses and safeguarded, remote technologies and evaluations of their effectiveness, in order teleoperation. This paper describes an implemented system to enable mission planners to make informed cost/benefit that has autonomously driven a prototype wheeled lunar tradeoffs in deciding how to control the lunar rovers. rover over a kilometer in natural, outdoor terrain. The The research reported here is a descendant of our navigation system uses stereo terrain maps to perform previous work in rugged terrain navigation for legged local obstacle avoidance, and arbitrates steering rovers [15, 16]. Other efforts have taken similar approaches recommendations from both the user and the rover. The to navigation for wheeled planetary rovers [1, 3, 4, 5, 17], paper describes the system architecture, each of the major including the use of obstacle avoidance using stereo vision. components, and the experimental results to date. Our work is distinguished by its emphasis on long-distance traversal, mixed mode driving, and use of efficient stereo Introduction vision using only general-purpose processors. The lure of the Moon is strong — and humans are once To date, we have concentrated on the autonomous again responding to the challenge.
    [Show full text]
  • Modeling and Experimental Validation of a Parallel Microrobot for Biomanipulation
    Dipartimento di Ingegneria dell'Informazione Corso di Laurea Magistrale in Ingegneria Biomedica Master Degree thesis Modeling and experimental validation of a parallel microrobot for biomanipulation Supervisors: Candidate: Arianna Menciassi Arianna Saracino Sinan D. Haliyo Academic Year: 2014-2015 17 Luglio 2015 Contents Introduction ii 1 STATE OF THE ART 1 1.1 Microrobotics overview . .1 1.2 Sensing and Actuation at the Microscale . .4 1.2.1 Sensing . .4 1.2.2 Actuation . .5 1.3 The role of Virtual Reality (VR) in micro-scale tasks . .9 1.3.1 Micromanipulation . 14 1.3.2 Microassembly . 18 1.3.3 Surgical micromanipulation . 20 1.3.4 Bio-micromanipulation . 22 1.4 Robots for micromanipulation: parallel robots . 25 1.4.1 Comparing Performaces of Serial and Parallel Robots . 25 1.4.2 Parallel robot's architectures . 28 1.4.3 Applications . 31 2 MODELING A COMMERCIAL PARALLEL MICROPOSITIONER 33 2.1 Thesis objectives . 33 2.2 SmarPod micropositioning system . 34 2.2.1 System's overview . 34 2.2.2 Micropositioner's architecture . 37 2.2.3 Calculating the number of Degrees of Freedom (DoF) . 40 2.3 Defining IGM and DGM for parallel robots . 42 2.4 Analytical Model . 43 2.4.1 Position . 43 2.4.2 Orientation . 46 3 THE ROLE OF VIRTUAL REALITY IN MODELING A PARALLEL MICROMANIPULATOR 49 3.1 Blender software overview . 49 1 CONTENTS 3.1.1 User interface . 51 3.2 Importing SmarPod's model . 52 3.2.1 Recovering positions of rotules . 54 3.3 Simulation-Aided IGM . 56 3.3.1 Position .
    [Show full text]
  • Robots and Jobs: Evidence from US Labor Markets Daron Acemoglu
    Robots and Jobs: Evidence from US Labor Markets Daron Acemoglu Massachusetts Institute of Technology Pascual Restrepo Boston University We study the effects of industrial robots on US labor markets. We show theoretically that robots may reduce employment and wages and that their local impacts can be estimated using variation in exposure to ro- bots—defined from industry-level advances in robotics and local indus- try employment. We estimate robust negative effects of robots on em- ployment and wages across commuting zones. We also show that areas most exposed to robots after 1990 do not exhibit any differential trends before then, and robots’ impact is distinct from other capital and tech- nologies. One more robot per thousand workers reduces the employment- to-population ratio by 0.2 percentage points and wages by 0.42%. I. Introduction In 1929, John Maynard Keynes famously predicted that the rapid spread of automation technologies would bring “technological unemployment” We thank David Autor, James Bessen, Lorenzo Caliendo, Amy Finkelstein, Matthew Gentz- kow, Michael Greenstone, Mikell Groover, Steven Miller, Brendan Price, John Van Reenen, three anonymous referees, and participants at various seminars and conferences for com- ments and suggestions; Giovanna Marcolongo, Mikel Petri, and Joonas Tuhkuri for outstand- ing research assistance; and the Institute for Digital Economics and the Toulouse Network of Information Technology for financial support. Data are provided as supplementary material online. Electronically published April 22, 2020 [ Journal of Political Economy, 2020, vol. 128, no. 6] © 2020 by The University of Chicago. All rights reserved. 0022-3808/2020/12806-00XX$10.00 000 This content downloaded from 018.010.087.049 on May 04, 2020 10:58:04 AM All use subject to University of Chicago Press Terms and Conditions (http://www.journals.uchicago.edu/t-and-c).
    [Show full text]
  • 48 Real-Life Robots That Will Make You Think the Future Is Now Maggie Tillman and Adrian Willings | 29 May 2018
    ADVERTISEMENT Latest gadget reviews Best cable management Which Amazon Kindle? Best battery packs Search Pocket-lint search Home > Gadgets > Gadget news 48 real-life robots that will make you think the future is now Maggie Tillman and Adrian Willings | 29 May 2018 POCKET-LINT If you're anything like us, you probably can't wait for the day you can go to the store and easily (and cheaply) buy a robot to clean your house, wait on you and do whatever you want. We know that day is a long way off, but technology is getting better all the time. In fact, some high-tech companies have alreadyADVERTISEMENT developed some pretty impressive robots that make us feel like the future is here already. These robots aren't super-intelligent androids or anything - but hey, baby steps. From Honda to Google, scientists at companies across the world are working diligently to make real-life robots an actual thing. Their machines can be large, heavy contraptions filled with sensors and wires galore, while other ones are tiny, agile devices with singular purposes such as surveillance. But they're all most certainly real. Pocket-lint has rounded up real-life robots you can check out right now, with the purpose of getting you excited for the robots of tomorrow. These existing robots give us hope that one day - just maybe - we'll be able to ring a bell in order to call upon a personal robot minion to do our bidding. Let us know in the comments if you know others worth including.
    [Show full text]
  • Local Encounters in Robot Swarms: from Localization to Density Regulation
    LOCAL ENCOUNTERS IN ROBOT SWARMS: FROM LOCALIZATION TO DENSITY REGULATION A Dissertation Presented to The Academic Faculty By Siddharth Mayya In Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the School of Electrical and Computer Engineering Georgia Institute of Technology December 2019 Copyright c Siddharth Mayya 2019 LOCAL ENCOUNTERS IN ROBOT SWARMS: FROM LOCALIZATION TO DENSITY REGULATION Approved by: Dr. Magnus Egerstedt, Advisor School of Electrical and Computer Dr. Daniel Goldman Engineering School of Physics Georgia Institute of Technology Georgia Institute of Technology Dr. Seth Hutchinson Dr. Dylan Shell School of Interactive Computing Department of Computer Science & Georgia Institute of Technology Engineering Texas A&M University Dr. Yorai Wardi School of Electrical and Computer Date Approved: October 22, 2019 Engineering Georgia Institute of Technology कमयेवाधकारते मा फलेषु कदाचन । मा कमफलहेतुभूमा ते सोऽवकमण ।। योगथः कु कमाण सं यवा धनय । सयसयोः समो भूवा समवं योग उयते ।। karmanyevadhikaraste ma phalesu kadacana ma karmaphalahetur bhur ma te sango ’stv akarmani yogasthah kuru karmani sangam tyaktva dhananjaya siddhyasiddhyoh samo bhutva samatvam yoga ucyate Your right is to action alone, never to its fruits at any time. The fruits of your action should not be your motive, nor should your attachment be to inaction. Perform your activities equipoised, abandoning all attachment to success or failure. Such equanimity is called Yoga. — Bhagavad Gita To mother and father ACKNOWLEDGMENTS This dissertation would not have been possible without various contributions from the people I was fortunate enough to interact with during my time at Georgia Tech. I am still astonished at the extent to which a research advisor and mentor can profoundly influence one’s life.
    [Show full text]
  • Commencement2019
    COMMENCEMENT2019 May 18-19 THINK OF YOURSELF AS ON THE THRESHOLD OF UNPARALLELED SUCCESS. A WHOLE, CLEAR, GLORIOUS LIFE LIES BEFORE YOU. ANDREW CARNEGIE FOUNDER, CARNEGIE MELLON UNIVERSITY Welcome To the graduates, families and friends of the Carnegie Mellon Class of 2019: Welcome to Carnegie Mellon University’s 122nd Commencement Ceremony. Today, we celebrate the achievements of the CMU Class of 2019. Since arriving on campus, these students have been immersed in work that matters — in boundary-crossing education and research, outstanding creativity and performance, and community service and engagement. Bound by a core set of values that includes integrity, inclusion, collaboration and empathy, these remarkable graduates have changed this campus for the better, and will change the world. We are especially grateful to the families and friends of the graduates who have come here today to celebrate with us. Graduation from a demanding academic institution like Carnegie Mellon is a team effort: these students could not have succeeded without your steadfast love and support over the years. Today, you share in their well-deserved accomplishments. As one chapter of their lives closes, another begins. Today, the Class of 2019 is joining a worldwide community of more than 112,000 alumni who have experienced the power of a CMU education to make a difference in the world. Graduates: I encourage you to take advantage of this network and remember to share your accumulating knowledge and experiences with the students who follow in your footsteps. On behalf of the entire Carnegie Mellon community, I wish the Class of 2019 great success, fulfillment and happiness in the years ahead.
    [Show full text]
  • Collaborative Adaptive Autonomous Agents Adaptive Collaborative Mirgita Frasheri
    Mälardalen University Licentiate Thesis 271 Mirgita Frasheri Collaborative Adaptive Autonomous Agents COLLABORATIVE ADAPTIVE AUTONOMOUS AGENTS AUTONOMOUS ADAPTIVE COLLABORATIVE Mirgita Frasheri Address: P.O. Box 883, SE-721 23 Västerås. Sweden ISBN 9789174853995 2018 Address: P.O. Box 325, SE-631 05 Eskilstuna. Sweden E-mail: [email protected] Web: www.mdh.se ISSN 16519256 Mälardalen University Press Licentiate Theses No. 271 COLLABORATIVE ADAPTIVE AUTONOMOUS AGENTS Mirgita Frasheri 2018 School of Innovation, Design and Engineering Copyright © Mirgita Frasheri, 2018 ISBN 978-91-7485-399-5 ISSN 1651-9256 Printed by E-Print, Stockholm, Sweden Per¨ mamin, babin, dajen,¨ nen¨ en,¨ dhe gjyshin. Acknowledgements To my mom and dad, for your unbreakable spirits, courage and guts to take whatever life throws and defying odds. For holding my hand when I was learn- ing how to write, or when I was struggling with some hard math problem. For looking after me, always. This life, and everything in it, I owe to you. To my uncle. For walking me to school, German class, and wherever I had to go. For recounting the battles of Alexander the Great before I’d go to an exam, just in case I’d forgotten how to be brave. Thank you for showing me the good music, the kind that gets one through anything, discussing with me the beauty of Van Gogh’s yellow, evolution, partisan battles and everything you thought I needed in order to grow. To my grandparents, my heroes, for my joyous childhood, for showing me what it means to love unconditionally, being there for people, in the best and worst of times.
    [Show full text]
  • (19) United States (12) Reissued Patent (10) Patent Number: US RE45,870 E Wang Et Al
    USOORE4587OE (19) United States (12) Reissued Patent (10) Patent Number: US RE45,870 E Wang et al. (45) Date of Reissued Patent: Jan. 26, 2016 (54) APPARATUS AND METHOD FOR PATIENT (56) References Cited ROUNDING WITH A REMOTE CONTROLLED ROBOT U.S. PATENT DOCUMENTS 3,821,995 A 7/1974 Aghnides (75) Inventors: Yulun Wang, Goleta, CA (US); Louis 4.413,693. A 1 1/1983 Derby Kavoussi, Lutherville, MD (US) (Continued) (73) Assignee: InTouch Technologies, Inc., Santa FOREIGN PATENT DOCUMENTS Barbara, CA (US) CA 22.89697 A1 1, 1998 CA 22.89697 11, 1998 (21) Appl. No.: 13/543,225 (Continued) OTHER PUBLICATIONS (22) Filed: Jul. 6, 2012 Nakajima et al., “A Multimedia Teleteaching System Using an Elec tronic Whiteboard forTwo-Way Communication of Motion Videos and Chalkboards”, 1993, IEEE, p. 436-441.* Related U.S. Patent Documents (Continued) Reissue of: Primary Examiner — James Trammell (64) Patent No.: 7.289,883 Assistant Examiner — David Testardi Issued: Oct. 30, 2007 (74) Attorney, Agent, or Firm — Knobbe Martens Olson & Appl. No.: 11/650,149 Bear LLP Filed: Jan. 5, 2007 (57) ABSTRACT A method for remotely monitoring a patient. The method includes generating and transmitting input commands to the U.S. Applications: robot from a remote station. The remote station may include (63) Continuation of application No. 10/751,032, filed on a personal computer that is operated by a doctor. The input Jan. 2, 2004, now Pat. No. 7,164,969, which is a con commands can move the robot so that a video image and tinuation-in-part of application No.
    [Show full text]
  • Soccer Robots Implementing Soccer Behaviors in the Webots Simulator for NAO Robots
    Soccer Robots Implementing soccer behaviors in the Webots simulator for NAO robots Kristjan Arumae Sarah Myhre Chris Cassian Olschewski Section 1: Overview_______________________________________________________1 1.1 Team Introduction 1 1.2 Motivation 2 1.3 Project Origin 2 1.4 Goals and Objectives 4 1.5 Project Evaluation 5 1.6 Technical Approach 6 1.7 Hardware 8 1.8 Research 10 1.8.1 CMUnited­98 11 1.8.2 ARAIBO­07 13 1.8.3 Machine Learning for Arm Leg Coordination 15 Section 2: Development Environment__________________________________________17 2.1 Team Organization 17 2.1.1 Google Wiki 17 2.1.2 Asana with Instagantt 20 2.1.3 Github 24 2.1.4 Evaluation 26 2.2 Simulation Software 28 2.2.1 Choreographe 28 2.2.2 Webots for NAO 29 2.2.3 Evaluation 31 2.4 Libraries 31 2.4.1 Naoqi 32 2.4.2 OpenCV 34 2.4.3 Evaluation 35 2.3 IDEs 37 2.3.1 Eclipse 37 2.3.2 Sublime 39 2.3.3 Evaluation 40 Section 3: Build___________________________________________________________42 3.1 Webots Field 42 3.2 Framework 43 3.3 Vision 47 3.4 Movement 51 3.5 Logic Implementation 60 Section 4: Behavior Creation_________________________________________________63 4.1 Chase 63 4.2 Goalie 66 4.3 Defender 71 4.4 Midfielder 71 4.5 Striker 73 Section 5: Design Challenges and Solutions____________________________________76 Section 6: Online Documentation_____________________________________________80 6.1 Simulation Setup 80 6.2 Webots for NAO Environment 81 6.3 First Code 83 6.4 Useful Methods 84 6.5 Soccer Behaviors 84 6.6 Team Templates 85 6.7 Videos 85 6.8 Evaluation 86 Section 7: Administrative Content_____________________________________________88 6.1 Finance 6.2 Consultants 6.2.1 Dr.
    [Show full text]