Thrust ID: Peer-to-Peer HRI Training and Learning with Humans Rod Grupen (lead) Cynthia Breazeal Nicholas Roy MURI 8 Kickoff Meeting 2007.

Slides:



Advertisements
Similar presentations
Calyxinfo Walking through Calyx Info The Organisation.
Advertisements

B1: Technical Merit List short term research directions and areas –Mobility assistant, builds model of environment, peer-to-peer interaction with human.
Applying the SOA RA Utah Public Safety ESB Project Utah Department of Technology Services April 10, 2008 Prepared by Robert Woolley.
ASSESSMENT AND TESTS FOR ADAPTED PHYSICAL EDUCATION.
Physical Education Introduction
0 General information Rate of acceptance 37% Papers from 15 Countries and 5 Geographical Areas –North America 5 –South America 2 –Europe 20 –Asia 2 –Australia.
Laboratory for Perceptual Robotics – Department of Computer Science Hierarchical Mechanisms for Robot Programming Shiraj Sen Stephen Hart Rod Grupen Laboratory.
New Forms of Organising Adaptive Org Network Org Smarter Faster Org New Digital Enterprise Object-oriented Org Flatness & fluidity Vision, direction, values.
Laboratory for Perceptual Robotics Department of Computer Science University of Massachusetts Amherst Natural Task Decomposition with Intrinsic Potential.
Human-machine system.
Robots that Work in Collaboration with People Guy Hoffman and Cynthia Breazeal Robotic Life Group MIT Media Laboratory Cambridge, MA, U.S.A.
L ABORATORY FOR P ERCEPTUAL R OBOTICS U NIVERSITY OF M ASSACHUSETTS A MHERST D EPARTMENT OF C OMPUTER S CIENCE Intent Recognition as a Basis for Imitation.
Mobile Robotics: 10. Kinematics 1
4. Interaction Design Overview 4.1. Ergonomics 4.2. Designing complex interactive systems Situated design Collaborative design: a multidisciplinary.
Robotic Systems Trends, Research, Future CSCi 338 :: Distributed Systems :: Fall 2005 Aleksandar Stefanovski.
Introductory Remarks Robust Intelligence Solicitation Edwina Rissland Daniel DeMenthon, George Lee, Tanya Korelsky, Ken Whang (The Robust Intelligence.
Sociable Machines Cynthia Breazeal MIT Media Lab Robotic Presence Group.
Science Inquiry Minds-on Hands-on.
1 Presentation for WALIS Forum Mark Taylor Manager SLIP Emergency Management Program FESA September 2006 The document and its contents are confidential.
Design of a Multi-Threaded Distributed Telerobotic Framework Mayez Al-Mouhamed, Onur Toker, and Asif Iqbal Mayez Al-Mouhamed, Onur Toker, and Asif Iqbal.
1 1: Inter-Act, 13 th Edition Orientation Orientation.
Networked Control Systems Vincenzo Liberatore. Today: Cyberspace Interact with remote virtual environment – On-line social activities Communicate with.
IMPLEMENTATION ISSUES REGARDING A 3D ROBOT – BASED LASER SCANNING SYSTEM Theodor Borangiu, Anamaria Dogar, Alexandru Dumitrache University Politehnica.
Diane Paul, PhD, CCC-SLP Director, Clinical Issues In Speech-Language Pathology American Speech-Language-Hearing Association
Incident Command System (ICS)
ENGLISH LANGUAGE ARTS AND READING K-5 Curriculum Overview.
Learning HMM-based cognitive load models for supporting human-agent teamwork Xiaocong Fan, Po-Chun Chen, John Yen 소프트컴퓨팅연구실황주원.
Agent architectures Smarter software for astronomers Alasdair Allan University of Exeter, Exeter, U.K.
Content Key factors for success Comparison of cultures Synergy (best of both) Company Vision company Mission company Goals Company culture Type of company.
Center for Firefighter Safety Research and Development.
Chapter 4 Finding out about tasks and work. Terminology GOAL: End result or objective TASK: An activity that a person has to do to accomplish a goal ACTION:
Chapter 4 Realtime Widely Distributed Instrumention System.
L ABORATORY FOR P ERCEPTUAL R OBOTICS U NIVERSITY OF M ASSACHUSETTS A MHERST D EPARTMENT OF C OMPUTER S CIENCE Learning Prospective Robot Behavior Shichao.
Examine the quality of movement in performance of a physical activity
Putting Research to Work in K-8 Science Classrooms Ready, Set, SCIENCE.
Improved Human-Robot Team performance using Chaski Proceeding: HRI '11HRI '11 Proceedings of the 6th international conference on Human-robot interaction.
Issues in (Financial) High Performance Computing John Darlington Director Imperial College Internet Centre Fast Financial Algorithms and Computing 4th.
Thrust III HRI Studies for Human Factors and Performance Evaluation J. A. Adams (Lead – Task A) P. Hinds (Lead – Task B) C. Breazeal J. How N. Roy MURI.
DARPA ITO/MARS Project Update Vanderbilt University A Software Architecture and Tools for Autonomous Robots that Learn on Mission K. Kawamura, M. Wilkes,
Natural Tasking of Robots Based on Human Interaction Cues Brian Scassellati, Bryan Adams, Aaron Edsinger, Matthew Marjanovic MIT Artificial Intelligence.
Teleoperation In Mixed Initiative Systems. What is teleoperation? Remote operation of robots by humans Can be very difficult for human operator Possible.
Riga Technical University Department of System Theory and Design Usage of Multi-Agent Paradigm in Multi-Robot Systems Integration Assistant professor Egons.
Biocomplexity Teacher Workshop May 31 – June 2, 2008 University of Puerto Rico.
1 Object Oriented Logic Programming as an Agent Building Infrastructure Oct 12, 2002 Copyright © 2002, Paul Tarau Paul Tarau University of North Texas.
Behavior-based Multirobot Architectures. Why Behavior Based Control for Multi-Robot Teams? Multi-Robot control naturally grew out of single robot control.
National Research Council Of the National Academies
Coaching Competencies Soft skills, or putting behaviorism to work?
Master Slave Arm System for Telepresence T. Khalil.
ESA Harwell Robotics & Autonomy Facility Study Workshop Autonomous Software Verification Presented By: Rick Blake.
The single assessment process training resource SAP Care Coordinator Role 1 The single assessment process The Care Coordinator Role.
Thrust IIB: Dynamic Task Allocation in Remote Multi-robot HRI Jon How (lead) Nick Roy MURI 8 Kickoff Meeting 2007.
| CDW.com/PeopleWhoGetIT CDW’S JOURNEY TO INTEGRATED TALENT MANAGEMENT Presented by: Dr. Tess Reinhard- Sr. Director of Organizational Capability.
VISUAL LITERACY Viewing and Visually Representing These are an integral part of Reading and Writing and used together to Make Meaning.
Robot Programming from Demonstration, Feedback and Transfer Yoan Mollard, Thibaut Munzer, Andrea Baisero, Marc Toussaint, Manuel Lopes.
Intelligent Agents: Technology and Applications Unit Five: Collaboration and Task Allocation IST 597B Spring 2003 John Yen.
Ali Ghadirzadeh, Atsuto Maki, Mårten Björkman Sept 28- Oct Hamburg Germany Presented by Jen-Fang Chang 1.
Using Scrum to Improve Teamwork, Communication, Quality and Speed.
Functionality of objects through observation and Interaction Ruzena Bajcsy based on Luca Bogoni’s Ph.D thesis April 2016.
SPACE MOUSE. INTRODUCTION  It is a human computer interaction technology  Helps in movement of manipulator in 6 degree of freedom * 3 translation degree.
Foundations for Training Theories and Principles
San Diego May 22, 2013 Giovanni Saponaro Giampiero Salvi
Science engagement: identifying priorities
Overview of Year 1 Progress Angelo Cangelosi & ITALK team
Automation as the Subject of Mechanical Engineer’s interest
Thrust IC: Action Selection in Joint-Human-Robot Teams
Senior Physical Education
Thrust II: Task C Visualization and Interface for Situation Awareness
Being a Coach Practical Lesson 1.
Foundations for Training Theories and Principles
uBot-4 Hardware: Firmware: Pricepoint: $15k
Presentation transcript:

Thrust ID: Peer-to-Peer HRI Training and Learning with Humans Rod Grupen (lead) Cynthia Breazeal Nicholas Roy MURI 8 Kickoff Meeting 2007

MURI 8 Kickoff Meeting 2007 Interactive Training in Human-Robot Teams MIT-Vanderbilt-Stanford UW-UMASS Amherst  Learning from human demonstration  common ground - project proprietary sensory and motor policy spaces into a common frame  asking questions and providing explanations  combine learned policies flexibly and effectively in response to new run-time situations  perform peer-to-peer policies jointly with humans and other robots

MURI 8 Kickoff Meeting 2007 Thrust ID Objectives MIT-Vanderbilt-Stanford UW-UMASS Amherst  build libraries of schema for component tasks underlying triage, hazmat, and HRI  acquaint human partners with capabilities and limitations of robot partners  establish common knowledge about strategies, procedures, and practices  negotiate roles and preferences for joint activity  master joint activities through practice

MURI 8 Kickoff Meeting 2007 Actions MIT-Vanderbilt-Stanford UW-UMASS Amherst  g  g  K  g  T  g  g’

MURI 8 Kickoff Meeting 2007 Developmental Programming MIT-Vanderbilt-Stanford UW-UMASS Amherst l native control basis l temporal structure for development l integration - hard problems use previous solutions for easier problems teleological hypothesis

MURI 8 Kickoff Meeting 2007 Action Schemas - Hierarchy MIT-Vanderbilt-Stanford UW-UMASS Amherst computational model of infant development  stage 1 - touch what you see  stage 2 - the length of your arm  stage 3 - grasp affordances  stage 4 - human collaboration Vgotskian pointing multi-body objects: simultaneous trackability attributes: motion (scale, multi-body kinematics), topological/geometrical attributes, hue, saturation, intensity, texture

MURI 8 Kickoff Meeting 2007 Action Schemas - Generative Models, Teleology, and Transfer Learning MIT-Vanderbilt-Stanford UW-UMASS Amherst teleoperator sorting instruction sorting replay with prior knowledge (1) parse events to find a matching schema. (2) associate goals with schema (3) Replicate demonstration with contingencies

MURI 8 Kickoff Meeting 2007 Commodity Mobile Manipulators MIT-Vanderbilt-Stanford UW-UMASS Amherst …nature routinely selects for dynamics to combine speed and agility with light weight and low power… strength, performance, safety

MURI 8 Kickoff Meeting 2007 Whole-Body Primate/Hominid/Human Model MIT-Vanderbilt-Stanford UW-UMASS Amherst postural stability prehensile skills tool use social organization

MURI 8 Kickoff Meeting 2007 Contributions MIT-Vanderbilt-Stanford UW-UMASS Amherst  multi-agent, and human-robot schema for coordinated action  interactive, socially-guided learning from demonstration (question/explain)  hierarchical composition of skills  communicative actions to convey states, objects, and actions

MURI 8 Kickoff Meeting 2007 Year 1 Demonstrations MIT-Vanderbilt-Stanford UW-UMASS Amherst  component schema for initial triage client sideremote network client side remote network

MURI 8 Kickoff Meeting 2007 Year 1 Demonstrations MIT-Vanderbilt-Stanford UW-UMASS Amherst sample acquisition, and cataloging load carrying strategies that do not violate stability constraints of the platform tool use hazard containment

MURI 8 Kickoff Meeting 2007 Year 2 (and onward) MIT-Vanderbilt-Stanford UW-UMASS Amherst  role engagement and switching in multi-robot, and human-robot strategies  remote humans, prior knowledge, maps, run- time situational awareness, mental models, asymmetric beliefs, affect on communicative actions  UGV/UAV/human coalitions