Resilient Machines Through Continuous Self-Modeling Pattern Recognition 2010.04.06 Seung-Hyun Lee Soft Computing Lab. Josh Bongard,Victor Zykov, and Hod.

Slides:



Advertisements
Similar presentations
Dialogue Policy Optimisation
Advertisements

Science is a way of knowing.
Algorithm and Complexity Analysis
Network Research Lab. Sejong University, Korea Jae-Kwon Seo, Kyung-Geun Lee Sejong University, Korea.
Behavioral Theories of Motor Control
Intelligent Environments1 Computer Science and Engineering University of Texas at Arlington.
Optimal Design Laboratory | University of Michigan, Ann Arbor 2011 Design Preference Elicitation Using Efficient Global Optimization Yi Ren Panos Y. Papalambros.
ROBOT BEHAVIOUR CONTROL SUCCESSFUL TRIAL OF MARKERLESS MOTION CAPTURE TECHNOLOGY Student E.E. Shelomentsev Group 8Е00 Scientific supervisor Т.V. Alexandrova.
SOMM: Self Organizing Markov Map for Gesture Recognition Pattern Recognition 2010 Spring Seung-Hyun Lee G. Caridakis et al., Pattern Recognition, Vol.
Tracking a moving object with real-time obstacle avoidance Chung-Hao Chen, Chang Cheng, David Page, Andreas Koschan and Mongi Abidi Imaging, Robotics and.
1 Life-and-Death Problem Solver in Go Author: Byung-Doo Lee Dept of Computer Science, Univ. of Auckland Presented by: Xiaozhen Niu.
Ratbert: Nearest Sequence Memory Based Prediction Model Applied to Robot Navigation by Sergey Alexandrov iCML 2003.
1 Design of a controller for sitting of infants Semester Project July 5, 2007 Supervised by: Ludovic Righetti Prof. Auke J. Ijspeert Presented by: Neha.
Source-Channel Prediction in Error Resilient Video Coding Hua Yang and Kenneth Rose Signal Compression Laboratory ECE Department University of California,
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Robin McDougall, Ed Waller and Scott Nokleby Faculties of Engineering & Applied Science and Energy Systems & Nuclear Science 1.
1 Efficiently Learning the Accuracy of Labeling Sources for Selective Sampling by Pinar Donmez, Jaime Carbonell, Jeff Schneider School of Computer Science,
Mining Large Data at SDSC Natasha Balac, Ph.D.. A Deluge of Data Astronomy Life Sciences Modeling and Simulation Data Management and Mining Geosciences.
1 PSO-based Motion Fuzzy Controller Design for Mobile Robots Master : Juing-Shian Chiou Student : Yu-Chia Hu( 胡育嘉 ) PPT : 100% 製作 International Journal.
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
1 Research on Animals and Vehicles Chapter 8 of Raibert By Rick Cory.
Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology Unsupervised pattern recognition models for mixed feature-type.
Cristian Urs and Ben Riveira. Introduction The article we chose focuses on improving the performance of Genetic Algorithms by: Use of predictive models.
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
Advances in Modeling Neocortex and its impact on machine intelligence Jeff Hawkins Numenta Inc. VS265 Neural Computation December 2, 2010 Documentation.
Energy-Aware Scheduling with Quality of Surveillance Guarantee in Wireless Sensor Networks Jaehoon Jeong, Sarah Sharafkandi and David H.C. Du Dept. of.
2 2  Background  Vision in Human Brain  Efficient Coding Theory  Motivation  Natural Pictures  Methodology  Statistical Characteristics  Models.
Boundary Recognition in Sensor Networks by Topology Methods Yue Wang, Jie Gao Dept. of Computer Science Stony Brook University Stony Brook, NY Joseph S.B.
Classification and Ranking Approaches to Discriminative Language Modeling for ASR Erinç Dikici, Murat Semerci, Murat Saraçlar, Ethem Alpaydın 報告者:郝柏翰 2013/01/28.
A Regression Approach to Music Emotion Recognition Yi-Hsuan Yang, Yu-Ching Lin, Ya-Fan Su, and Homer H. Chen, Fellow, IEEE IEEE TRANSACTIONS ON AUDIO,
Chih-Ming Chen, Student Member, IEEE, Ying-ping Chen, Member, IEEE, Tzu-Ching Shen, and John K. Zao, Senior Member, IEEE Evolutionary Computation (CEC),
Particle Filters.
DISCRIMINATIVE TRAINING OF LANGUAGE MODELS FOR SPEECH RECOGNITION Hong-Kwang Jeff Kuo, Eric Fosler-Lussier, Hui Jiang, Chin-Hui Lee ICASSP 2002 Min-Hsuan.
Evolving Virtual Creatures & Evolving 3D Morphology and Behavior by Competition Papers by Karl Sims Presented by Sarah Waziruddin.
DARPA ITO/MARS Project Update Vanderbilt University A Software Architecture and Tools for Autonomous Robots that Learn on Mission K. Kawamura, M. Wilkes,
A Passive Approach to Sensor Network Localization Rahul Biswas and Sebastian Thrun International Conference on Intelligent Robots and Systems 2004 Presented.
Distributed Algorithms for Multi-Robot Observation of Multiple Moving Targets Lynne E. Parker Autonomous Robots, 2002 Yousuf Ahmad Distributed Information.
AI ● Dr. Ahmad aljaafreh. What is AI? “AI” can be defined as the simulation of human intelligence on a machine, so as to make the machine efficient to.
Intelligent Database Systems Lab Presenter : Kung, Chien-Hao Authors : Eghbal G. Mansoori 2011,IEEE FRBC: A Fuzzy Rule-Based Clustering Algorithm.
Chapter 7. Learning through Imitation and Exploration: Towards Humanoid Robots that Learn from Humans in Creating Brain-like Intelligence. Course: Robots.
A NOVEL METHOD FOR COLOR FACE RECOGNITION USING KNN CLASSIFIER
Intelligent Database Systems Lab Advisor : Dr.Hsu Graduate : Keng-Wei Chang Author : Lian Yan and David J. Miller 國立雲林科技大學 National Yunlin University of.
Inferring High-Level Behavior from Low-Level Sensors Donald J. Patterson, Lin Liao, Dieter Fox, and Henry Kautz.
WERST – Methodology Group
John Lafferty Andrew McCallum Fernando Pereira
A New Approach to Utterance Verification Based on Neighborhood Information in Model Space Author :Hui Jiang, Chin-Hui Lee Reporter : 陳燦輝.
Postgraduate books recommended by Degree Management and Postgraduate Education Bureau, Ministry of Education Medical Statistics (the 2nd edition) 孙振球 主.
Manufacturing versus Construction. Resiliency: adaptation to constant change.
Nonlinear differential equation model for quantification of transcriptional regulation applied to microarray data of Saccharomyces cerevisiae Vu, T. T.,
Evolving RBF Networks via GP for Estimating Fitness Values using Surrogate Models Ahmed Kattan Edgar Galvan.
Chapter 2. From Complex Networks to Intelligent Systems in Creating Brain-Like Intelligence, Olaf Sporns Course: Robots Learning from Humans Park, John.
Chapter 13. How to build an imitator in Imitation and Social Learning in Robots, Humans and Animals Course: Robots Learning from Humans Park, Susang
1 An infrastructure for context-awareness based on first order logic 송지수 ISI LAB.
Learning for Physically Diverse Robot Teams Robot Teams - Chapter 7 CS8803 Autonomous Multi-Robot Systems 10/3/02.
Jivko Sinapov, Kaijen Hsiao and Radu Bogdan Rusu Proprioceptive Perception for Object Weight Classification.
Robot Intelligence Technology Lab. 10. Complex Hardware Morphologies: Walking Machines Presented by In-Won Park
哈工大信息检索研究室 HITIR ’ s Update Summary at TAC2008 Extractive Content Selection Using Evolutionary Manifold-ranking and Spectral Clustering Reporter: Ph.d.
COMPUTE INVERSE KINEMATICS IN A ROBOTIC ARM BY USING FUZZY LOGIC Subject: Robotics Applications Student: Bui Huy Tien Student ID: M961Y204.
Kansas State University Department of Computing and Information Sciences CIS 830: Advanced Topics in Artificial Intelligence Wednesday, January 26, 2000.
Ali Ghadirzadeh, Atsuto Maki, Mårten Björkman Sept 28- Oct Hamburg Germany Presented by Jen-Fang Chang 1.
CSE Advanced Computer Animation Short Presentation Topic: Locomotion Kang-che Lee 2009 Fall 1.
Introduction to Machine Learning, its potential usage in network area,
Adviser:Ming-Yuan Shieh Student:shun-te chuang SN:M
From Action Representation to Action Execution: Exploring the Links Between Mental Representation and Movement William Land1,2,3 Dima Volchenkov3 & Thomas.
An Adaptive Middleware for Supporting Time-Critical Event Response
MURI Kickoff Meeting Randolph L. Moses November, 2008
WELCOME.
Unit: Science & Technology
Multiple Target Localization Based on Alternate Iteration in Wireless Sensor Networks Zhongyou Song, Jie Li , Yuanhong Zhong, Yao Zhou.
Information Processing by Neuronal Populations Chapter 5 Measuring distributed properties of neural representations beyond the decoding of local variables:
Presentation transcript:

Resilient Machines Through Continuous Self-Modeling Pattern Recognition Seung-Hyun Lee Soft Computing Lab. Josh Bongard,Victor Zykov, and Hod Lipson, Science, Vol.314, pp , 2006.

S FT YONSEI UNIV. KOREA 16 Contents Introduction Motivation Self Modeling Experiments Conclusion 1 / 15

S FT YONSEI UNIV. KOREA 16 Introduction Animals –After injured, create qualitatively different compensatory behaviors Robots –How robots can deal with this sort of unexpected damage?  self modeling 2 / 15

S FT YONSEI UNIV. KOREA 16 Motivation How can robot learn its own morphology? –Direct observation? –Database of past experience? How can robot synthesize complex behaviors or recover from damage? –Trial and error?  slow, costly, risky! In this paper, –Inferring morphology: self-directed exploration –Complex behavior or recovering from damage: synthesize new behaviors using the resulting self models 3 / 15

S FT YONSEI UNIV. KOREA 16 Self Modeling 4 / 15 Overall Process Modeling Prediction Testing

S FT YONSEI UNIV. KOREA 16 Self Modeling 5 / 15 Testing In this process –Performs an arbitrary motor action –Records the resulting sensory data

S FT YONSEI UNIV. KOREA 16 Self Modeling 6 / 15 Modeiling Model synthesize component –Synthesizes a set of candidate self-models Method –Before damage(topological modeling) Greedy random-mutation hill climber algorithm 16 parameters Robot initially knows how many body pars it is composed of, the size, weight and mass of each part, and angle-movement relations 15 random models 200 iterations Evaluation: Euclidean distance between the centroid and where the centroid should be –After damage(parametric modeling) Self-model is frozen 8 parameters (volumes and masses are scaled by 10%~200%)

S FT YONSEI UNIV. KOREA 16 Self Modeling 7 / 15 Prediction Action synthesize component –Find a new action most likely to elicit the most information from the robot based on the current self model inferred

S FT YONSEI UNIV. KOREA 16 Self Modeling 8 / 15 After self modeling procedures(16 times repetition) –Create desired behaviors (D) –Execute by the physical robot

S FT YONSEI UNIV. KOREA 16 Self Modeling 9 / 15

S FT YONSEI UNIV. KOREA 16 Experiments Speculation –4 upper and lower leg parts and a main body –8 motorized joints(-90 ~ 90 degree range) 0 degree: flat Positive degree: upwards Negative degree: downwards –2 tilt sensors Self model representation –Planar topological arrangement Damage –Disabled one leg 10 / 15 Robot

S FT YONSEI UNIV. KOREA 16 Experiments Control variables –Computational efforts(250,000 internal model simulations) –Physical actions(16) Three algorithms –Algorithm 1: 16 random physical actions  batch training(modeling) –Algorithm 2: Physical actions  self modeling  random action selection –Algorithm 3(proposed): Physical actions  self modeling  actions selection 11 / 15 Design

S FT YONSEI UNIV. KOREA 16 Experiments 12 / 15 Result

S FT YONSEI UNIV. KOREA 16 Experiments 13 / 15 Result  Model-driven algorithm is more accurate than random baseline algorithms  A robot that actively chooses action on the basis of its current set of hypothesized self-models has a better chance of successfully inferring its own morphology

S FT YONSEI UNIV. KOREA 16 Experiments 14 / 15 Result  Automatically generated self-model was sufficiently predictive to allow the robot to consistently develop forward motion patterns without further physical trials

S FT YONSEI UNIV. KOREA 16 Conclusion Contribution –First physical system Autonomously recover its own morphology with little prior knowledge Optimize the parameters of its morphology after unexpected change – Show the possibility of unknown cognitive process Which organisms actively create and update self models in the brain? How and which sensor-motor signals are used to do this? What form these model take? Does human utilize multiple competing models? 15 / 15 Result

Thank you