Intel & Carnegie Mellon University Presented by Tim Haines HERB 1.0 : Home Exploring Robotic Butler.

Slides:



Advertisements
Similar presentations
Composition of Functions!!! Objective: I will be able to answer various forms of composition problems.
Advertisements

We consider situations in which the object is unknown the only way of doing pose estimation is then building a map between image measurements (features)
Bilge Mutlu, Andreas Krause, Jodi Forlizzi, Carlos Guestrin, and Jessica Hodgins Human-Computer Interaction Institute, Carnegie Mellon University Robust,
A vision-based system for grasping novel objects in cluttered environments Ashutosh Saxena, Lawson Wong, Morgan Quigley, Andrew Y. Ng 2007 Learning to.
System Integration and Experimental Results Intelligent Robotics Research Centre (IRRC) Department of Electrical and Computer Systems Engineering Monash.
3D Human Body Pose Estimation from Monocular Video Moin Nabi Computer Vision Group Institute for Research in Fundamental Sciences (IPM)
The Free Safety Problem Using Gaze Estimation as a Meaningful Input to a Homing Task Albert Goldfain CSE 668: Animate Vision Principles Final Project Presentation.
Markovito’s Team (INAOE, Puebla, Mexico). Team members.
Stereo.
1 The INRIA Robotics Teams Propose a Large-Scale Initiative Action “Personally Assisted Living” March 18, 2009.
Vision for Robotics ir. Roel Pieters & dr. Dragan Kostić Section Dynamics and Control Dept. Mechanical Engineering {r.s.pieters, January.
Active SLAM in Structured Environments Cindy Leung, Shoudong Huang and Gamini Dissanayake Presented by: Arvind Pereira for the CS-599 – Sequential Decision.
CS 561, Sessions 27 1 Towards intelligent machines Thanks to CSCI561, we now know how to… - Search (and play games) - Build a knowledge base using FOL.
Probabilistic Robotics
Robotics Industry Posts Second Best Year Ever North American robotics industry posted its second best year ever in 2000 [Robotic Industries Association.
VOICe 1.5 Enabling Technology - Final Project Gabe Su.
Finding an Unpredictable Target in a Workspace with Obstacles LaValle, Lin, Guibas, Latombe, and Motwani, 1997 CS326 Presentation by David Black-Schaffer.
December 2, 2014Computer Vision Lecture 21: Image Understanding 1 Today’s topic is.. Image Understanding.
CSCE 641 Computer Graphics: Image-based Modeling (Cont.) Jinxiang Chai.
SLAM: Simultaneous Localization and Mapping: Part II BY TIM BAILEY AND HUGH DURRANT-WHYTE Presented by Chang Young Kim These slides are based on: Probabilistic.
Vision Guided Robotics
Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Cognitive Robots © 2014, SNU CSE Biointelligence Lab.,
Occupant Classification System for Automotive Airbag Suppression A.Jaffer Sharief EEL
Quick Overview of Robotics and Computer Vision. Computer Vision Agent Environment camera Light ?
IMPLEMENTATION ISSUES REGARDING A 3D ROBOT – BASED LASER SCANNING SYSTEM Theodor Borangiu, Anamaria Dogar, Alexandru Dumitrache University Politehnica.
Challenging Environment
Constraints-based Motion Planning for an Automatic, Flexible Laser Scanning Robotized Platform Th. Borangiu, A. Dogar, A. Dumitrache University Politehnica.
Zhengyou Zhang Microsoft Research Digital Object Identifier: /MMUL Publication Year: 2012, Page(s): Professor: Yih-Ran Sheu Student.
SPIE'01CIRL-JHU1 Dynamic Composition of Tracking Primitives for Interactive Vision-Guided Navigation D. Burschka and G. Hager Computational Interaction.
Motion Object Segmentation, Recognition and Tracking Huiqiong Chen; Yun Zhang; Derek Rivait Faculty of Computer Science Dalhousie University.
Perceptual and Sensory Augmented Computing Visual Object Recognition Tutorial Visual Object Recognition Bastian Leibe & Computer Vision Laboratory ETH.
Surface Computing Turning everyday surfaces into interactive intelligent interfaces Co-located input and output Mixed reality: tangible objects, natural.
Fundamentals of Information Systems, Third Edition2 Principles and Learning Objectives Artificial intelligence systems form a broad and diverse set of.
Vrobotics I. DeSouza, I. Jookhun, R. Mete, J. Timbreza, Z. Hossain Group 3 “Helping people reach further”
Computer Vision Lab Seoul National University Keyframe-Based Real-Time Camera Tracking Young Ki BAIK Vision seminar : Mar Computer Vision Lab.
Autonomous Soil Investigator. What Is the ASI? Designed to complete the 2013 IEEE student robotics challenge Collects "soil" samples from a simulated.
Efficient Visual Object Tracking with Online Nearest Neighbor Classifier Many slides adapt from Steve Gu.
Peter Henry1, Michael Krainin1, Evan Herbst1,
Review: Neural Network Control of Robot Manipulators; Frank L. Lewis; 1996.
Vision and Obstacle Avoidance In Cartesian Space.
WELCOME TO ALL. DIGITAL IMAGE PROCESSING Processing of images which are Digital in nature by a Digital Computer.
Lecture 5: Image Interpolation and Features
An MPEG-7 Based Semantic Album for Home Entertainment Presented by Chen-hsiu Huang 2003/08/12 Presented by Chen-hsiu Huang 2003/08/12.
IEEE International Conference on Multimedia and Expo.
Typical DOE environmental management robotics require a highly experienced human operator to remotely guide and control every joint movement. The human.
Quiz Week 8 Topical. Topical Quiz (Section 2) What is the difference between Computer Vision and Computer Graphics What is the difference between Computer.
Computer Vision: 3D Shape Reconstruction Use images to build 3D model of object or site 3D site model built from laser range scans collected by CMU autonomous.
Robot Vision SS 2009 Matthias Rüther ROBOT VISION 2VO 1KU Matthias Rüther.
SLAM Techniques -Venkata satya jayanth Vuddagiri 1.
Toward humanoid manipulation in human-centered environments T. Asfour, P. Azad, N. Vahrenkamp, K. Regenstein, A. Bierbaum, K. Welke, J. Schroder, R. Dillmann.
Artificial Neural Networks By: Steve Kidos. Outline Artificial Neural Networks: An Introduction Frank Rosenblatt’s Perceptron Multi-layer Perceptron Dot.
3D Perception and Environment Map Generation for Humanoid Robot Navigation A DISCUSSION OF: -BY ANGELA FILLEY.
Vision-based Android Application for GPS Assistance in Tunnels
Face Detection and Notification System Conclusion and Reference
MoMat: Mobile Manipulation
Project Overview Introduction Frame Build Motion Power Control Sensors
Support Vector Machines and Kernels
Fast Preprocessing for Robust Face Sketch Synthesis
Vehicle Segmentation and Tracking in the Presence of Occlusions
Project Overview Introduction Frame Build Motion Power Control Sensors
Robust Belief-based Execution of Manipulation Programs
Review on Smart Solutions for People with Visual Impairment
Bowei Tang, Tianyu Chen, and Christopher Atkeson
Outline H. Murase, and S. K. Nayar, “Visual learning and recognition of 3-D objects from appearance,” International Journal of Computer Vision, vol. 14,
Human geography.
for Vision-Based Navigation
Image Segmentation.
Applications Discussion
Learning complex visual concepts
Sign Language Recognition With Unsupervised Feature Learning
Presentation transcript:

Intel & Carnegie Mellon University Presented by Tim Haines HERB 1.0 : Home Exploring Robotic Butler

Ideal Uses for Assistive Agent Assist elderly or disabled  Doing jobs currently done by service animals Cleaning Washing Dishes Laundry Ironing Moving heavy objects

Challenges to Operate in a Human Environment Efficient navigation and mapping Robust object recognition and pose estimating Sophisticated trajectory planning All done in unstructured constantly changing environment

The First Solution!!!

Principles of System Architecture Unlimited computational power is available  This is achieve by using on board and off board computing Sensing and planning algorithms should require minimal human input  Allows for the robot to adapt to new environments

Object recognition using sift Flea- Locating objects Narrow View, Large depth of field Dragonfly-Manipulate objects Wide View, small depth of field

Checkerboard Localization Found to be better than using the laser Down side  Slow, taking 10 to 30 sec  Needs at least 3 checkerboards in 1 image  Tried children's drawings, Failed

Navigating using GATMO Generalized Approach to Tracking Movable Objects Two part maps  Static  Lists of objects

Classification

Vision

Planning Opening doors Planning based on Kinematics, no physics Often Herbs fingers would jam into the door causing a stall

Planning Manipulating objects WGR-Workspace Goal Regions Videos:  QQ QQ  Wy-M&feature=related