Presentation is loading. Please wait.

Presentation is loading. Please wait.

Advanced Topics in Robotics CS 790 (X)

Similar presentations


Presentation on theme: "Advanced Topics in Robotics CS 790 (X)"— Presentation transcript:

1 Advanced Topics in Robotics CS 790 (X)
Lecture 1 Instructor: Monica Nicolescu

2 General Information Instructor: Dr. Monica Nicolescu Class webpage:
Office hours: Wednesday 10am-noon, 1-2pm Room: SEM 239 Class webpage: Time and place Tuesday, Thursday: 1:00-2:15pm WRB 4051 CS 790(X) - Lecture 1

3 What will we Learn? Cover fundamental aspects of robotics
Control architectures Sensing and perception Advanced robotics techniques Robot learning by demonstration Navigation and mapping Multiple robot systems: coordination and cooperation Human-robot interaction Biologically inspired robotics Hands-on experience CS 790(X) - Lecture 1

4 Readings and Presentations
Two papers (on average) discussed at each lecture Each paper is presented by a student For some lectures we will have one background reading Presentation guidelines (papers) At most 30 minutes Briefly summarize the paper Discuss the paper, its strengths, weaknesses, any points needing clarification Addressing any questions the other students may have Presentation guidelines (background reading) At most 45 minutes Area challenges, existing approaches, case studies CS 790(X) - Lecture 1

5 Readings and Paper Reports
For each paper, all students must submit, at the beginning of the class a brief report of the paper Report format (typed) Student’s name Title and authors of the paper A short paragraph summarizing the contributions of the paper A critique of the paper that addresses the strengths and weaknesses of the paper Summary of background reading if applicable Area challenges, existing approaches, case studies CS 790(X) - Lecture 1

6 Project Individual project on topics covered in class
Project topics: an implementation of either: a single robot system (involving complex behavior and demonstrated on a physical robot) or a multi-robot system (involving cooperation/ communication/ coordination between robots and demonstrated in simulation or on a physical robot) CS 790(X) - Lecture 1

7 Project/Lab Testbeds The Robot Operating System ( ROS provides libraries and tools to create robot applications ROS provides hardware abstraction, device drivers, libraries, visualizers, message-passing, package management Stage is a ROS-compatible high-fidelity indoor multi-robot simulation testbed Allows for direct porting to ROS-compatible physical robots CS 790(X) - Lecture 1

8 Project/Lab Testbeds 11 ActivMedia Pioneer 3 DX
sonar sensors, laser, PTZ camera, onboard computer One Player-compatible ActivMedia Pioneer 1 AT robot 7 sonar sensors and requires the use of a laptop (not provided) 10 Robosapien robots On-board CPU 10 Create robots 1.2 GHz CPU CS 790(X) - Lecture 1

9 Project/Lab Testbeds NAO humanoid robot Baxter humanoid robot
PR2 humanoid robot CS 790(X) - Lecture 1

10 Project Report Should include the following: Title, author Abstract
Introduction and motivation Review of relevant literature Problem definition: project goals, assumptions, constraints, and evaluation criteria Details of proposed approach Results and objective experimental evaluation Discussion (strengths and weaknesses) and conclusion References Appendix (relevant code or algorithms) CS 790(X) - Lecture 1

11 Class Policy Grading Late submissions Attendance Paper reports: 20%
Paper presentations: 20% Participation in class discussions: 20% Final project: 40% Late submissions No late submissions will be accepted Attendance Full participation in class discussions and labs CS 790(X) - Lecture 1

12 Important Dates/Milestones
February 17 Project topic proposal and presentation (5 slides) One page that outlines the specific goals, contribution, implementation platform and the proposed approach April 14 Project status presentations (3-5 slides) 5 minute in-class presentation Partial report that describes the current status of the project Abstract, introduction and motivation, relevant literature review, problem definition (goals, constraints, etc.), what has been done, what is still to be done CS 790(X) - Lecture 1

13 Important Dates/Milestones
May 12 Project final presentations  Project final demonstrations Project final reports due CS 790(X) - Lecture 1

14 Optional Textbooks Basic topics Advanced topics Broad topics
The Robotics Primer, Author: Maja Mataric' Advanced topics Behavior-Based Robotics, 2001 Author: Ron Arkin Available at the library Broad topics Springer Handbook of Robotics, 2008 Siciliano, Bruno; Khatib, Oussama, editors CS 790(X) - Lecture 1

15 Where do Robots Come From?
The term robot comes from “robota” (subordinate work) Karel Capek’s 1921 play RUR (Rossum’s Universal Robots) Robotics grew out of the fields of control theory, cybernetics and AI 1940s: first explorations of the connection between human intelligence and machines, around the time of cybernetics 1960s: early robots are built, benefitting from two technologies: numerical control machines for precise manufacturing, and teleoperators for remote radioactive material handling Robotics = the science and technology of robots CS 790(X) - Lecture 1

16 A Brief History of Robotics
1970s: industrial robots, became essential components in the automation of flexible manufacturing systems, due to development of integrated circuits, digital computers and miniaturized components General industry: metal products, the chemical, the electronics and the food industries Early AI had a strong impact on how it evolved (1950s-1970s), emphasizing reasoning and abstraction, removal from direct situatedness and embodiment 1980s: robotics was defined as the science which studies the intelligent connection between perception and action CS 790(X) - Lecture 1

17 A Brief History of Robotics
1990s: the need to use robots in hazardous environments (field robotics), or to enhance the human operator ability (human augmentation), or to improving the quality of life (service robotics). 2000: from industrial robotics to challenges of the human world (human-centered and life-like robotics) Need for a higher degree of autonomy! Wide range of applications biomechanics, haptics, neurosciences, virtual simulation, animation, surgery, and sensor networks CS 790(X) - Lecture 1

18 What is in a Robot? Sensors Effectors and actuators
Used for locomotion and manipulation Controllers for the above systems Coordinating information from sensors with commands for the robot’s actuators CS 790(X) - Lecture 1

19 Challenges of Robot Control
Perception Limited, noisy sensors, diversity of sensors Actuation Limited capabilities of robot effectors Thinking Time consuming, different time scales for response, real-time demands, everything happens concurrently and asynchronously Environments Dynamic, impose fast reaction times Lots of architectures exists No single architecture is best for all applications CS 790(X) - Lecture 1

20 Robot Architectures Robot control is the means by which the sensing and action of a robot are coordinated Robot architectures Structure: how the system is divided into subsystems and how they interact Style: computational concepts Common feature of architectures Modular decomposition of systems into simpler, independent pieces  increase reliability and decrease complexity Software tools Help development in a particular architectural style (specialized languages, communication libraries) CS 790(X) - Lecture 1

21 Spectrum of robot control
From “Behavior-Based Robotics” by R. Arkin, MIT Press, 1998 CS 790(X) - Lecture 1

22 Robot control approaches
Reactive Control Don’t think, (re)act. Deliberative (Planner-based) Control Think hard, act later. Hybrid Control Think and act separately & concurrently. Behavior-Based Control (BBC) Think the way you act. CS 790(X) - Lecture 1

23 W. Grey Walter’s Tortoise
Machina Speculatrix” (1953) 1 photocell, 1 bump sensor, 1 motor, 3 wheels, 1 battery Behaviors: seek light head toward moderate light back from bright light turn and push recharge battery Uses reactive control, with behavior prioritization CS 790(X) - Lecture 1

24 Shakey At Stanford Research Institute (late 1960s)
A deliberative system Visual navigation in a very special world STRIPS planner Vision and contact sensors CS 790(X) - Lecture 1

25 The Art of Robot Architectures
What tasks will the robot perform? Short term, long term, user-initiated, robot initiated What actions are necessary to perform the tasks? Representation, coordination, speed What data is necessary to perform the tasks? How to get it, what sensors are needed, how to represent it, how to update it What computational capabilities does the robot have? What data will be used, on-board/off-board CS 790(X) - Lecture 1

26 The Art of Robot Architectures
Who are the robot’s users? How to command the robot, feedback, interaction, information exchange How will the robot be evaluated? Success criteria, failure modes Will the architecture be used for more than one set of tasks? More than one robot, more than one team of developers Sensing and acting are the hard parts (not the planning) and take the most of the development time CS 790(X) - Lecture 1

27 Sensing Force and tactile Inertial sensors, GPS, odometry
Normal pressure, skin deformation Inertial sensors, GPS, odometry model a robot’s motion or pose (position and orientation) relative to an external frame of reference Sonar sensing Obstacle avoidance, mapping object recognition CS 790(X) - Lecture 1

28 Sensing How to we put it all together? Range sensors 3D vision
Obtain 3D structure for navigation 3D vision How to we put it all together? Usually need a fusion architecture CS 790(X) - Lecture 1

29 Robot Types - Manipulators
Kinematic redundancy: more degrees of freedom than necessary to solve the task 7-DOF Mitsubishi PA10 8-DOF Scienzia Machinale Snake design Robotics Research Corporation NASA dexterous manipulator CS 790(X) - Lecture 1

30 Robot Types - Hands Mechanical constraints: placement of motors and sensors Utah/MIT robot hand Stanford/JPL hand UB hand 3 NASA robonaut CS 790(X) - Lecture 1

31 Robot Types – Legged Robots
Inspired from biological systems: insects, mammals CS 790(X) - Lecture 1

32 Robot Types - Wheeled CS 790(X) - Lecture 1

33 Robot Types - Hybrid Leg – wheel Leg – arm Wall-climbing
CS 790(X) - Lecture 1

34 Robot Types – Humanoid Robots
Biped robots Humanoid torso Hopping robots CS 790(X) - Lecture 1

35 Robots: Alternative Terms
UAV unmanned aerial vehicle UGV (rover) unmanned ground vehicle UUV unmanned undersea vehicle CS 790(X) - Lecture 1

36 Key Concepts Situatedness Embodiment
Agents are strongly affected by the environment and deal with its immediate demands (not its abstract models) directly Embodiment Agents have bodies, are strongly constrained by those bodies, and experience the world through those bodies, which have a dynamic with the environment CS 790(X) - Lecture 1

37 Key Concepts (cont.) Situated intelligence
is an observed property, not necessarily internal to the agent or to a reasoning engine; instead it results from the dynamics of interaction of the agent and environment and behavior are the result of many interactions within the system and w/ the environment, no central source or attribution is possible CS 790(X) - Lecture 1

38 Background Readings M. Matarić: Chapters 1, 3 CS 790(X) - Lecture 1


Download ppt "Advanced Topics in Robotics CS 790 (X)"

Similar presentations


Ads by Google