Movement Imitation: Linking Perception and Action Advanced Topics in Computer Vision, 2004 Lior Noy Department of Computer Science and Applied Mathematics.

Slides:



Advertisements
Similar presentations
Cognitive Systems, ICANN panel, Q1 What is machine intelligence, as beyond pattern matching, classification and prediction. What is machine intelligence,
Advertisements

By: Ryan Wendel.  It is an ongoing analysis in which videos are analyzed frame by frame  Most of the video recognition is pulled from 3-D graphic engines.
Perception and Perspective in Robotics Paul Fitzpatrick MIT Computer Science and Artificial Intelligence Laboratory Humanoid Robotics Group Goal To build.
University of Minho School of Engineering Centre ALGORITMI Uma Escola a Reinventar o Futuro – Semana da Escola de Engenharia - 24 a 27 de Outubro de 2011.
Intelligent systems Colloquium 1 Positive and negative of logic in thinking and AI.
Yiannis Demiris and Anthony Dearden By James Gilbert.
Module 14 Thought & Language. INTRODUCTION Definitions –Cognitive approach method of studying how we process, store, and use information and how this.
Uncertainty Representation. Gaussian Distribution variance Standard deviation.
Region labelling Giving a region a name. Image Processing and Computer Vision: 62 Introduction Region detection isolated regions Region description properties.
CIS 678 Artificial Intelligence problems deduction, reasoning knowledge representation planning learning natural language processing motion and manipulation.
Matching brain and body dynamics Daniel Wolpert: – "Why don't plants have brains?" – "Plants don't have to move!" Early phases of embodied artificial intelligence:
Computing With Images: Outlook and applications
Computer Vision for Interactive Computer Graphics Mrudang Rawal.
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.
MIRROR Project Review IST Brussels – December 1 st, 2003.
Sensory-Motor Primitives as a Basis for Imitation: Linking Perception to Action and Biology to Robotics Presentation by Dan Hartmann 21 Feb 2006.
Summer 2011 Wednesday, 8/3. Biological Approaches to Understanding the Mind Connectionism is not the only approach to understanding the mind that draws.
Jochen Triesch, UC San Diego, 1 COGS Visual Modeling Jochen Triesch & Martin Sereno Dept. of Cognitive Science UC.
Computational aspects of motor control and motor learning Michael I. Jordan* Mark J. Buller (mbuller) 21 February 2007 *In H. Heuer & S. Keele, (Eds.),
Advanced Computer Vision Structure from Motion. Geometric structure-from-motion problem: using image matches to estimate: The 3D positions of the corresponding.
Intelligent Agents: an Overview. 2 Definitions Rational behavior: to achieve a goal minimizing the cost and maximizing the satisfaction. Rational agent:
Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Cognitive Robots © 2014, SNU CSE Biointelligence Lab.,
Function Approximation for Imitation Learning in Humanoid Robots Rajesh P. N. Rao Dept of Computer Science and Engineering University of Washington,
© H. Hajimirsadeghi, School of ECE, University of Tehran Conceptual Imitation Learning Based on Functional Effects of Action Hossein Hajimirsadeghi School.
Learning and Recognizing Human Dynamics in Video Sequences Christoph Bregler Alvina Goh Reading group: 07/06/06.
UW Contributions: Past and Future Martin V. Butz Department of Cognitive Psychology University of Würzburg, Germany
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
CSCE 5013 Computer Vision Fall 2011 Prof. John Gauch
2 2  Background  Vision in Human Brain  Efficient Coding Theory  Motivation  Natural Pictures  Methodology  Statistical Characteristics  Models.
K. J. O’Hara AMRS: Behavior Recognition and Opponent Modeling Oct Behavior Recognition and Opponent Modeling in Autonomous Multi-Robot Systems.
Beyond Gazing, Pointing, and Reaching A Survey of Developmental Robotics Authors: Max Lungarella, Giorgio Metta.
CS 4630: Intelligent Robotics and Perception Case Study: Motor Schema-based Design Chapter 5 Tucker Balch.
Visual motion Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys.
Bayesian goal inference in action observation by co-operating agents EU-IST-FP6 Proj. nr Raymond H. Cuijpers Project: Joint-Action Science and.
Project ArteSImit Artefact Structural Learning through Imitation (TU München, U Parma, U Tübingen, U Minho, KU Nijmegen) Giorgio Panin - TUM.
Imitation and Social Intelligence for Synthetic Characters Daphna Buchsbaum, MIT Media Lab and Icosystem Corporation Bruce Blumberg, MIT Media Lab.
Relative Hidden Markov Models Qiang Zhang, Baoxin Li Arizona State University.
DARPA ITO/MARS Project Update Vanderbilt University A Software Architecture and Tools for Autonomous Robots that Learn on Mission K. Kawamura, M. Wilkes,
Controlling the Behavior of Swarm Systems Zachary Kurtz CMSC 601, 5/4/
MURI Annual Review, Vanderbilt, Sep 8 th, 2009 Heterogeneous Sensor Webs for Automated Target Recognition and Tracking in Urban Terrain (W911NF )
The Interplay Between Mathematics/Computation and Analytics Haesun Park Division of Computational Science and Engineering Georgia Institute of Technology.
Chapter 7. Learning through Imitation and Exploration: Towards Humanoid Robots that Learn from Humans in Creating Brain-like Intelligence. Course: Robots.
Neural Networks Presented by M. Abbasi Course lecturer: Dr.Tohidkhah.
Chapter 1. Imitation: Thoughts about Theories in Imitation and Social Learning in Robots, Humans and Animals, Nehaniv and Dautenhaln. Course: Robots.
Chapter 8. Learning of Gestures by Imitation in a Humanoid Robot in Imitation and Social Learning in Robots, Calinon and Billard. Course: Robots Learning.
VEHICLE INTELLIGENCE LAB
Quiz Week 8 Topical. Topical Quiz (Section 2) What is the difference between Computer Vision and Computer Graphics What is the difference between Computer.
The Symbolic Qualia Ken Asada Humanoid Science Conf.
Slide no 1 Cognitive Systems in FP6 scope and focus Colette Maloney DG Information Society.
Optical flow and keypoint tracking Many slides adapted from S. Seitz, R. Szeliski, M. Pollefeys.
Chapter 21 Robotic Perception and action Chapter 21 Robotic Perception and action Artificial Intelligence ดร. วิภาดา เวทย์ประสิทธิ์ ภาควิชาวิทยาการคอมพิวเตอร์
Computational Intelligence: Methods and Applications Lecture 26 Density estimation, Expectation Maximization. Włodzisław Duch Dept. of Informatics, UMK.
Introduction to Cogsci April 07, Central Theme Cognitive Science was occuppied with the algorithmic level for much of its history: successive manipulation.
Robot Vision SS 2009 Matthias Rüther ROBOT VISION 2VO 1KU Matthias Rüther.
Modelling & Simulation of Semiconductor Devices Lecture 1 & 2 Introduction to Modelling & Simulation.
A Bayesian Model of Imitation in Infants and Robots
A. M. R. R. Bandara & L. Ranathunga
Learning Fast and Slow John E. Laird
Chapter 11: Artificial Intelligence
Modeling the development of mirror neurons Problem Solution
Adaptive Systems Research Group, University of Hertfordshire
Artificial Intelligence (CS 370D)
Image Segmentation Techniques
CSc4730/6730 Scientific Visualization
Movement Imitation: Linking Perception and Action
Turning to the Masters: Motion Capturing Cartoons
WELCOME.
Christoph F. Eick: A Gentle Introduction to Machine Learning
Optical flow and keypoint tracking
Toward a Great Class Project: Discussion of Stoianov & Zorzi’s Numerosity Model Psych 209 – 2019 Feb 14, 2019.
Presentation transcript:

Movement Imitation: Linking Perception and Action Advanced Topics in Computer Vision, 2004 Lior Noy Department of Computer Science and Applied Mathematics Weizmann Institute of Science

Movement Imitation - Example

semantic world (objects, actions) realm of raw-data (pixels, muscles activation) Action Perception Imitation: Linking Perception and Action Imitation

Outline 2. Programming By Demonstration 1. Movement Imitation 3. Robotic Movement Imitation Primitives Based Approach (Mataric’) Real Time Tracking (“mirror-game”) (Ude et al.) 4. Direct Perception and Imitation

A Variety of Probes into Imitation Imitation Ethology Cognitive psychology Developmental psychology Neurophysiology Human Brain Imaging Robotics

Possible Questions In Imitation Research 1. What is the content of imitation? 2. How perceptions are transformed to actions? 3. What are the processes of learning by imitation? 4. How to evaluate imitation? What is a “ good ” imitation? 5. How does the ability to imitate develop?

Evaluating Imitation Robot Following in a Hilly Environment

Evaluating Imitation

Programming By Demonstration (PbD) Methods to program a robot 1. Human Programming 2. Reinforcement Learning 3. Programming by Demonstration

Programming By Demonstration (PbD) Applications  Navigation  Locomotion  Playing air-hockey  Manipulating blocks  Balancing a pole  Hitting a tennis-serve  Grasping unfamiliar objects  Imitating dancing movement

PbD – Application Example The “Golden Maze”

PbD – Application Example Playing Air-Hockey

PbD – Application Example Box Manipulations

Three Approaches for PbD 1.Symbolic 1.Symbolic 2.Control-Based 3.Statistical

Symbolic Approach for PbD o Analyze observed actions in terms of sub-goals o Match actions needed to fulfill these sub-goals o Create a symbolic description of the environment ( ”object A is above object B” ) o Learn a series of symbolic if-then rules ( ”if object A is above object B then grasp-object[ object B ]” )

Example: Symbolic Approach for PbD (Kunyushi et al., 1994) … but how do you symbolically describes “hitting a tennis serve”?

Control-Based Approach for PbD  No symbolic parsing of perceived actions  Assume a pre-defined control policy  Acquire needed parameters from observation

Control-Based Approach Inverse Models Sometime assume known inverse models (converting desired effect to needed commands) motor commands joint angles end-effector position Forward Models Inverse Models

Example: Control-Based Approach for PbD (Schaal, 2003) Tennis movie

Statistical Approach for PbD  No prior assumption on used control policy  Statistically match perception and action  Can this be done? More on this later…

Example: Statistical Approach for PbD PCA (Asada, 1995)

Example: Statistical Approach for PbD Learning: Perform random action A(i) Record resulted optical flow f(i) Compute principal-component p1(i), p2(i) Learn the connection A(i) – {p1(i), p2(i)}

Outline 2. Programming By Demonstration 1. Movement Imitation 3. Robotic Movement Imitation Primitives Based Approach (Mataric’) Real Time Tracking (“mirror-game”) (Ude et al.) 4. Direct Perception and Imitation

PbD for Movement Imitation Pre-Cursor 1: Cartoons Retargeting (Bregler et al., 2002)

Cartoons Retargeting Two Types of Deformations 1. Affine deformation 1. Key shape deformation y x

Cartoons Retargeting Affine Deformations  Affine parameters y x

Cartoons Retargeting Affine Deformations

Cartoons Retargeting Key Shape Deformations  S k are the key shapes

Cartoons Retargeting Key Shape Deformations

Cartoons Retargeting - Results More on: “Animating human motion”, Speakers : Simon Adar, Yoram Atir

PbD for Movement Imitation Pre-Cursor 2: Guided Movement Synthesis (Zelnik-Manor, Hassner & Irani, 2004)

Event-Based Analysis of Video (Zelnik-Manor & Irani, 2001)

Guided Movement Synthesis (a.k.a. “Movement Imitation”?)

PbD for Movement Imitation Pre-Cursor 2: Movement Synthesis

PbD for Movement Imitation Case Study: Primitive-Based Approach The Problem: How to convert visual input to motor output? A Possible Solution: Use a common, sparse representation: sensory-motor primitives. X1X2...XnX1X2...Xn J1J2...JmJ1J2...Jm == … but what primitives to use? movement primitive1 movement primitive2... movement primitive K

Movement Imitation Using Sensory-Motor Primitives Motor primitives: Sequences of action that accomplish a complete goal-directed behavior. Examples: 1. Move hand in “straight line”, “parabola” (Felix…). 2. Perform “grasping”, “a tennis serve”.

Imitation Learning Using Sensory-Motor Primitives (Schaal, Ijspeert & Billard, 2003)

Inspiration for Using Sensory-Motor Primitives (Rizzolatti et al., 2002; Gallese et al. 1996) Evidence for: 1. C oding of goal-directed actions. 2. Shared representations of perception and action. Example – Mirror Neurons.

Movement Imitation Using Sensory-Motor Primitives (Mataric’,1998) General Principles: 1.Selective attention focusing on end-points movements. 2.Sensory-motor primitives as integrative representation. 3.Learning new skills as compositions of primitives. 4.Experimental test-beds.

What Sensory-Motor Primitives to Use? Primitives Innate Pre-defined control policies (e.g., central pattern generators) Learned Un-supervised clustering (using PCA, Isomap ) Joints Space (“motor space”) End-Points Space (“visual space”)

“Experiment in Imitation Using Perceptuo-Motor Primitives”, (Weber, Jenkins & Mataric’,2001) 1.Extract hand (end-point) movements. 2.Perform Vector-Quantization to get invariant representation.

3.Classify movement to primitives (line, arc, circle). 4.Group adjacent similar primitives. “Experiment in Imitation Using Perceptuo- Motor Primitives”

5.Determine primitives parameters. 6.Project to ego-centric space. “Experiment in Imitation Using Perceptuo- Motor Primitives”

(Weber, Jenkins & Mataric’,2001) “Experiment in Imitation Using Perceptuo- Motor Primitives”

PbD for Movement Imitation Case Study: Real-Time Tracker (Ude et al.,2001) o The Goal: Mimic movements in real-time o The Problem: Large amount of data to process (6 MB/Sec) Need “continuous success” o The Solution: Probabilistic approach to prevent excessive data interactions

“Real-Time Visual System for Interaction with Humanoid Robot” (Ude, Shibata & Atkeson, 2001) Estimate positions of tracked “blobs” in the image Compute 3D coordinates of tracked objects using stereo Transform into via-points for robot hand trajectory Compute motor commands from desired trajectory

Real-Time Tracker Tracking “Blobs” In a Bayesian Setting probability for the pixel at location u to have Intensity I u Given the process k a-priori probability for process k

Real-Time Tracking Minimize Log-Likelihood overall probability to observe image I Goal: determine the parameters that are most likely to produce this image – Maximal Likelihood Problem. computationally easier to minimize the negative log likelihood

Find minimum (using Lagrange Multipliers) and get: probability that pixel u stems from process l Real-Time Tracking Minimize Log-Likelihood

Real-Time Tracking Find Probabilities Parameters The above equations are solved iteratively by the Expectation-Minimization (EM) algorithm Expectation stage: compute P u,l using the current estimate for Ө and ω. Minimization stage: compute new Ө and ω assuming P u,l are constant. from probabilities of pixels to belong to a certain process (e.g. – the human hand) …

“Real-Time Visual System for Interaction with Humanoid Robot” … to object locations

Real-Time Tracking General Stages Estimate positions of tracked “blobs” in the image Compute 3D coordinates of tracked objects using stereo Transform into via-points for robot hand trajectory Compute motor commands from desired trajectory

Real-Time Tracking Estimate Trajectories with B-splines

Real-Time Tracking - Results Robot Compliance Movie

References “Vision-Based Robot Learning for Behavior Acquisition” M. Asada, T. Nakamura, and K. Hosoda. Proc. of IEEE International Conference on Intelligent Robots And Systems 1995 (IROS '95) Workshop on Vision for Robots, pp , “Turning to the masters: Motion capturing cartoons” Bregler C, Loeb L, Chuang E, Deshpande H ACM TRANSACTIONS ON GRAPHICS 21 (3): JUL 2002 “Movement, activity and action: The role of knowledge in the perception of motion” Bobick AF PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY OF LONDON SERIES B- BIOLOGICAL SCIENCES 352 (1358): AUG “Challenges in Building Robots That Imitate People”, Breazeal C. and Scassellati B, in "Imitation in Animals and Artifacts", Kerstin Dautenhahn and Chrystopher Nehaniv, eds. The MIT Press, “Action recognition in the premotor cortex” Gallese V, Fadiga L, Fogassi L, Rizzolatti G BRAIN, 119: Part 2 APR 1996 “Learning by watching - extracting reusable task knowledge from visual observation of human-performance” Kuniyoshi Y, Inaba M, Inoue H IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, 10 (6): DEC 1994 “Sensory-Motor Primitives as a Basis for Learning by Imitation: Linking Perception to Action and Biology to Robotics.” Maja J Mataric, in "Imitation in Animals and Artifacts", Kerstin Dautenhahn and Chrystopher Nehaniv, eds., MIT Press, 2002,

References “From mirror neurons to imitation: facts and speculations”, Rizzolatti G, Fadiga L, Fogassi L and Gallese V, in: Meltzoff AN and Prinz W (Eds.) "The imitative mind: development, evolution, and brain bases", New York: Cambridge University Press, 2002 “Computational approaches to motor learning by imitation” Schaal S, Ijspeert A, Billard A PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY OF LONDON SERIES B- BIOLOGICAL SCIENCES, 358 (1431): MAR “Movement planning and imitation by shaping nonlinear attractors” Schaal S, PROCEEDINGS OF THE 12TH YALE WORKSHOP ON ADAPTIVE AND LEARNING SYSTEMS 2003 “Robots that imitate humans” Scassellati B. Breazeal C. Trends in Cognitive Science, 6(11): , November “Real-time visual system for interaction with a humanoid robot”, Ude A., Shibata T. and Atkeson C. G., Robotics and Autonomous Systems, 37: , Stefan Weber, Odest C. Jenkins, and Maja J. Mataric´. "Imitation Using Perceptual and Motor Primitives". In International Conference on Autonomous Agents, pages , Barcelona, Spain, Jun 2000 "Event-Based Analysis of Video “, Zelnik-Manor L. and Irani M., IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, December 2001 (CVPR'01).

“The great end of life is not knowledge but action.” (Thomas H. Huxley) Perception? Action?