To boldly go where no man has gone before!

Size: px

Start display at page:

Download "To boldly go where no man has gone before!"

Dylan Campbell
5 years ago
Views:

1 To boldly go where no man has gone before! T.J. Kirk (from Star Trek)

Department of Computer Science and Engineering University of Texas at

2 University of Texas at Arlington CSE 4360/5364 Autonomous Robots Dr. Gian Luca Mariottini, Ph.D. Department of Computer Science and Engineering University of Texas at Arlington WEB : Class Schedule: Mon. & Wed., 1:00-2:20pm Office Hours: Mon. & Wed., 2:20-4:00pm

3 Am I a robot? (Yes/No) A B D C E F

4 Application domains of Robotics More than you can imagine! extreme environments space underwater medical robotics assistive rehabilitative surgical mine exploration de-mining civil and naval construction automatic refueling museum guide fire fighting home cleaning agriculture lawn mowing emergency rescue food industry entertainment inspection and surveillance humanoids Robots are exciting for what they do but, more than that, for how they work!

Robotics in Industry Robota (= servitude in slavic language) are

5 Robotics in Industry Robota (= servitude in slavic language) are artificial human-like creatures built for being inexpensive workers in the theater play Rossum s Universal Robots (R.U.R.) written by Karel Capek in 1920 Computer NumericallyControlled Machines (CNC) 1950 Mechanical Telemanipulators 1970 flexibility of use accuracy of positioning adaptability to changing conditions repeatability of operations

6 Estimated worldwide operational stock of industrial robots

7 Estimated annual shipment of industrial robots

8 Industrial Applications manipulation (pick-and-place) assembly spray painting and coating arc welding spot welding with pneumatic or servo-controlled gun laser cutting and welding gluing and sealing mechanical finishing operations (e.g., grinding)

9 Robotic Palletizing pallet = a portable platform on which good scan be moved, stacked, and stored

10 Automatic Refueling Oscar robot (France) Smart Pump refueler system (ISE, USA)

11 Food Industry Motoman SP-100X Ulixes Robot (IMT, Germany) (aligns 1000 sausages per hour!)

12 Space Applications NASA's Sojourner (1st robot on Mars, 1997) Canadarm (on the ISS)

13 Underwater Robotics Odyssey IV (MIT) - Typically actuated by thrusters (directional forces on tail) - Cannot translate sideways (kinematic constraints) Odin III (Univ. Hawaii) (omnidirectional)

depth: 37 m sensors: two cameras (front/back), acoustic sensor for

14 Underwater Robotics Aqua Robot (McGill University) size and weight: 50x65x13 cm, 18 kg locomotion: through six independently actuated flippers maximum depth: 37 m sensors: two cameras (front/back), acoustic sensor for localization (sonar), tri-ocular sensor (structured light) power source: 48V lithium battery

15 DARPA Challenge Blue Team (U.Berkley, TA&M) Carnegie Mellon

16 Humanoid Robots NAO (Aldebaran Robotics) Justin Robot (DLR, GErmany)

17 Medical Robotics MOVAID Project to aid disabled people (Scuola Superiore St.Anna, Pisa, ITALY) PAM-AID (Trinity College, Ireland)

18 Autonomously Robotic Laparoscopy

19 Robotics for Rescue Operations MARS Lab, University of Minnesota

20 Mine Exploration Carnegie Mellon

21 De-mining Tele-operated system on tracks used by the police for bomb disposal PEMEX (EPFL, Lausanne) (lightweight robot with oscillating head for mine detection)

22 Assistive Robotics Omnivision sensing 3-D object locations Robot control Courtesy from Charlie Kemp, director of the Healthcare Robotics Center at Georgia Tech;

23 Home Cleaning Roomba (irobot) Orazio (myrobot)

24 Military Applications Autonomously Flying Quadrotor and Mapping (UPenn) Big Dog (Boston Dynamics)

25 Multi-robot Formation Control Team of Robots Formation Control

26 Medical Robotics: Hospital & Nursing HELPmate robot - works in hospitals as auxiliary personnel Care-o-bot

27 Tele-Operated Surgery DaVinci by Intuitive Surgical

28 Systems for the visually-impaired Goal: Determine user s location Identify surroundings (parks, bench, trees, etc.) Represent objects with unique sounds Audio waypoints (e.g. metasounds) to destination path 3D (top)... N-views Structure-from-Motion MAP localization (RANSAC/LM) Georgia Institute of Technology

29 Key Problems in Robotics a) Who am I? b) Where am I? c) Where should I go? d) How do I get there? a) Requires study of : - robotic structures; - robotic sensors; - robotic actuators b) kinematics and localization c) task planning/control d) motion planning / motion control How am I supposed to get there How do I actually get there

30 Intelligent...action...perception Components of a robotic system: Mechanical system: Locomotion apparatus (wheels, tracks, legs,...) Manipulation apparatus (mechanical arm, end-effector, artificial hand). Actuation system: Provides the capability to exert an action (locomotion or manipulation). Sensory system: Proprioceptive sensors = acquire data on the status of the robot. (e.g., position, joint angles, etc.) Exteroceptive sensors = acquire data on the external status of environment. Control system: It commands the execution of the action with respect to the goals.

31 ...and applied to our scenario!

32 So...what is a Robot? A = yes D = no B = no C = no E = yes F = no

Course Content - Robot Modeling - Robot Control Intro to Robot Systems Robot Kinematics Inverse Kinematics Robot Jacobians Linear Control of Manipulators 1st Homework

Assignment Probabilistic Approaches to Robot Localization Kalman Filter (KF) and Extended-KF - Robot Localization Robot Localization and Mapping - Advanced apps.

33 Course Content - Robot Modeling - Robot Control Intro to Robot Systems Robot Kinematics Inverse Kinematics Robot Jacobians Linear Control of Manipulators 1st Homework Assignment - Robot Sensing - Motion Panning Sensors for Robotics Mobile Robots Robot Motion Planning Trajectory Generation and Tracking 1st Project 2nd Homework Assignment Probabilistic Approaches to Robot Localization Kalman Filter (KF) and Extended-KF - Robot Localization Robot Localization and Mapping - Advanced apps. Computer Vision in Robotics Adaptation and Learning 3rd Homework Assignment Final Project (please note that these course topics are preliminary and might undergo slight changes)

34 Course Prerequisites, Goals and Outcomes Prerequisites include CSE 2320 and CSE MATLAB programming experience is strongly recommended. C/C++ programming experience can be beneficial for the final project. Feel free to contact the advisor in case you have specific questions. CSE 4360/5364 is designed to: Introduce the student to fundamentals of robotics, robot control, and sensing. Explore the mathematical/algebraic foundations of robot kinematics, control and localization. Explore and familiarize with robot planning and navigation techniques. Upon successful completion of the course, each student will be able to: Recognize the features and peculiarities of different robotic devices. Understand rigid body kinematics and relationships between 3-D refer. frames. Describe direct and inverse kinematics. Compare the characteristics of different sensing devices (encoders, pinhole and stereo cameras, etc.). Understand and implement motion planning algorithms. Understand and discuss different algorithms for robot localization and mapping.

35 Course Text There is no required textbook for this course. However, selected parts of other textbooks (see list below) will be used as part of the course readings. Copies of these material will be put on reserve in the Science and Engineering Library. -- B. Siciliano, L. Sciavicco, L. Villani, G. Oriolo "Robotics: Modelling, Planning and Control", 3rd Edition, Springer,09 -- John J. Craig "Introduction to Robotics: Mechanics and Control", Addison Wesley, Jean-Claude Latombe "Robot Motion Planning", Kluwer Academic Publishers -- R. Cipolla "Computer Vision and Robotics", Cambridge University, UK (on-line course material) -- Y. Ma, S. Soatto, J. Kosecka, S. Sastry "An Invitation to 3-D Vision. From Images to Geometric Models", Springer 2003

36 Homework Assignments Students will be graded based on three homework assignments and two course projects. Homework Assignments: theoretical questions, programming assignments (in MATLAB), etc. related to the topics of the course. Dates will be announced in class. Tentatively, course grades will be based on the following: Assignments % of final grade Homeworks (total) 40 % 1st Course Project 20 % nd 2 Course Project 40 % Percent Grade 90 %-100 % 80 %-89.9 % 70 %-79.9 % 60 %-69.9 % <60 % Letter A B C D F Note 1: For students enrolled in CSE 5364 the homeworks will contain additional problems (not required for CSE 4360). Note 2: All work turned in for grading must be the student's own work. (see also the course's webpage) Note 3: MATLAB (with some toolboxes) is available also in NH 231

Course Projects 1st Course project : designing and implementing a particular

topics and chosen by the student or proposed by the instructor.

37 Course Projects 1st Course project : designing and implementing a particular algorithm related to topics studied in the course (assigned by the instructor). Final project : Designing and implementing a final project related to course topics and chosen by the student or proposed by the instructor. Abstract submission is mandatory before the deadline (to be announced in class). The course project can be done either individually or in a team (~max 2 students). RTL will be made available. Students will report their findings in a research report, and will present in-class their design and demo (dates will be announced)

38 References A. De Luca Notes from Robotics 1, University of Rome, La Sapienza, 2010 V. Kumar, G. Bekey and Y. Zheng Ch.5 Industrial, Personal and Service Robots, 2010 B. Siciliano Robotics, Springer 2009 (Ch.1)

Autonomous and Mobile Robotics Prof. Giuseppe Oriolo. Introduction: Applications, Problems, Architectures

Autonomous and Mobile Robotics Prof. Giuseppe Oriolo Introduction: Applications, Problems, Architectures organization class schedule 2017/2018: 7 Mar - 1 June 2018, Wed 8:00-12:00, Fri 8:00-10:00, B2 6