Symbiotic Brain-Machine Interfaces Justin C. Sanchez, Ph.D. Assistant Professor Neuroprosthetics Research Group (NRG) University.

Slides:



Advertisements
Similar presentations
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California
Advertisements

Markov Decision Process
Teaching an Agent by Playing a Multimodal Memory Game: Challenges for Machine Learners and Human Teachers AAAI 2009 Spring Symposium: Agents that Learn.
Chapter 4 Introduction to Cognitive Science
Robotics, Intelligent Sensing and Control Lab (RISC) University of Bridgeport Department of Computer Science and Engineering Robotics, Intelligent Sensing.
Institute for Theoretical Physics and Mathematics Tehran January, 2006 Value based decision making: behavior and theory.
Controlling Assistive Machines in Paralysis Using Brain Waves and Other Biosignals HCC 741- Dr. Amy Hurst Wajanat Rayes.
Artificial Intelligence
Adapted from Hayrettin Gürkök, U. of Twente, NL
Brain Computer Interface Presenter : Jaideo Chaudhari.
Introduction to HCC and HCM. Human Centered Computing Philosophical-humanistic position regarding the ethics and aesthetics of a workplace Any system.
Survey of Current Neuroengineering Research. Cochlear Implant ● Direct Electrical Stimulation of Auditory Nerve ● Microphone, Signal Processor, Transmission.
Reinforcement Learning
Provisional draft 1 ICT Work Programme Challenge 2 Cognition, Interaction, Robotics NCP meeting 19 October 2006, Brussels Colette Maloney, PhD.
CSE 490i: Design in Neurobotics Yoky Matsuoka (instructor) Lecture: TTH 10:30-11:20 EEB 003 Labs: TTH 11:30-1:20 CSE 003E.
A brain-machine interface instructed by direct intracortical microstimulation Joseph E. O’Doherty, Mikhail A. Lebedev, Timothy L. Hanson, Nathan A. Fitzsimmons.
IJCNN, International Joint Conference on Neural Networks, San Jose 2011 Pawel Raif Silesian University of Technology, Poland, Janusz A. Starzyk Ohio University,
Robotics for Intelligent Environments
By Claire Hoelmer, Suyesh Acharya, and Sydney Gibson.
Intelligent Agents: an Overview. 2 Definitions Rational behavior: to achieve a goal minimizing the cost and maximizing the satisfaction. Rational agent:
PROGRAMMING LEARNING: DIFFICULTIES AND SUPPORT TOOLS António José Mendes – University of Coimbra.
OMICS Group Contact us at: OMICS Group International through its Open Access Initiative is committed to make genuine and.
FINDINGS FROM TWO STUDIES BY THE CSS – ETH ZURICH PRESENTED BY STEFAN BREM SWISS FEDERAL OFFICE FOR CIVIL PROTECTION Examining Crisis Mapping.
Assistive Technology Clinical Outcomes Research Management System (AT-CORMS) Tool Utilizing the International Classification of Functioning (ICF) Cognitive.
Succeeding with Technology Information, Decision Support… Decision Making and Problem Solving Management Information Systems Decision Support Systems Group.
Information Technology Industry Report Brown University ADSP Lab 余 渊 善
Introduction GAM 376 Robin Burke Winter Outline Introductions Syllabus.
Shaun McGorry Executive Briefing July 16, Introduction: Robotics  Robots are becoming increasingly present in our daily lives  Robot: a virtual.
NW Computational Intelligence Laboratory Implementing DHP in Software: Taking Control of the Pole-Cart System Lars Holmstrom.
SYSTEMS BIOLOGY AND NEUROENGINEERING Christine P. Hendon, PhD Assistant Professor Electrical Engineering.
Computer system overview1 The Effects of Computers Pervasive in all professions How have computers affected my life? How have computers affected my life?
BUGS Relevant Research Areas: Insects: –Tele-control of insects: Ability to control some motor function of an insect through an external link –Tele-sense.
COMPUTER-ASSISTED LANGUAGE LEARNING (CALL)
BRAINGATE NEURAL- INTERFACE SYSTEM BY
By Brett Kotowski BME Section 2 Presentation 1.  Neurotechnology  Neurotechnology is the use of engineering applications to scan, alter or enhance the.
Graz-Brain-Computer Interface: State of Research By Hyun Sang Suh.
Operant Conditioning of Cortical Activity E Fetz, 1969.
Chapter 16. Basal Ganglia Models for Autonomous Behavior Learning in Creating Brain-Like Intelligence, Sendhoff et al. Course: Robots Learning from Humans.
 A direct communication pathway between the brain and an external device.  Directed at assisting, augmenting, or repairing human cognitive or sensory-motor.
Reinforcement Learning 主講人:虞台文 Content Introduction Main Elements Markov Decision Process (MDP) Value Functions.
What is Neural Engineering Tae-Seong Kim, Ph.D.. Neural Engineering Neural engineering also known as Ne uroengineering is a discipline that uses engineering.
Synthesis and Processing of Materials U.S. Army Research, Development and Engineering Command Cognition, Computers and Cooperation Presented at TRADOC.
DARPA ITO/MARS Project Update Vanderbilt University A Software Architecture and Tools for Autonomous Robots that Learn on Mission K. Kawamura, M. Wilkes,
Curiosity-Driven Exploration with Planning Trajectories Tyler Streeter PhD Student, Human Computer Interaction Iowa State University
Riga Technical University Department of System Theory and Design Usage of Multi-Agent Paradigm in Multi-Robot Systems Integration Assistant professor Egons.
Workshop on direct brain/computer interface & control Febo Cincotti Fondazione Santa Lucia IRCCS Brussels, August 2, 2006.
Brain Chips.
Abstract This presentation questions the need for reinforcement learning and related paradigms from machine-learning, when trying to optimise the behavior.
Reinforcement Learning 主講人:虞台文 大同大學資工所 智慧型多媒體研究室.
Oregon Branch IDA Salem, Oregon “Cerebrodiversity In The Classroom-- Lessons From Neuroscience” Part 1 - Slides 1-32 Gordon F. Sherman, Ph.D. Newgrange.
Presentation by A.Sudheer kumar Dept of Information Technology 08501A1201.
Using Feedback in MANETs: a Control Perspective Todd P. Coleman University of Illinois DARPA ITMANET TexPoint fonts used.
Chapter 15. Cognitive Adequacy in Brain- Like Intelligence in Brain-Like Intelligence, Sendhoff et al. Course: Robots Learning from Humans Cinarel, Ceyda.
Brain Computer Interfaces...
Control-Theoretic Approaches for Dynamic Information Assurance George Vachtsevanos Georgia Tech Working Meeting U. C. Berkeley February 5, 2003.
Hierarchical Systolic Array Design for Full-Search Block Matching Motion Estimation Noam Gur Arie,August 2005.
BRAIN GATE TECHNOLOGY.. Brain gate is a brain implant system developed by the bio-tech company Cyberkinetics in 2003 in conjunction with the Department.
Brain Jean V Bellissard Georgia Institute of Technology School of Physics Fall 2015.
Maestro AI Vision and Design Overview Definitions Maestro: A naïve Sensorimotor Engine prototype. Sensorimotor Engine: Combining sensory and motor functions.
Does the brain compute confidence estimates about decisions?
Brain Chip Technology | Presented to- Dr. Jia Uddin, BRAC University 2 Dung Beetle, Can lift upto 1141 times of it’s own body weight..
Overview of Artificial Intelligence (1) Artificial intelligence (AI) Computers with the ability to mimic or duplicate the functions of the human brain.
Reinforcement learning for dialogue systems
PETRA 2014 An Interactive Learning and Adaptation Framework for Socially Assistive Robotics: An Interactive Reinforcement Learning Approach Konstantinos.
Reinforcement Learning
Sinhgad College of Engineering Department of Information Technology
Joelle Pineau: General info
Dr. Unnikrishnan P.C. Professor, EEE
Designing High-Performance Neural Prostheses
Brain-Machine Interfaces beyond Neuroprosthetics
Presentation transcript:

Symbiotic Brain-Machine Interfaces Justin C. Sanchez, Ph.D. Assistant Professor Neuroprosthetics Research Group (NRG) University of Florida

Enabling Neurotechnologies for Overcoming Paralysis Develop direct neural interfaces to bypass injury. Communicate and control (closed- loop, real-time) directly via the interface. Leuthardt

Vision for BMI in Daily Life Lebedev

What are the Building Blocks? Signal Sensing Amplification Pre-Processing Telemetry Interpret Neural Activity Control Scheme Feedback Closed Loop BMI Provide neurophysiologic basis and engineering theory for a fully implantable neural Interface for restoring communication and control

BMI lessons learned Relationship between user and BMI is inherently lopsided. Users are intelligent and can use dynamic brain organization and specialization while BMIs are passive devices that enact commands I/O models have difficulty contending with new environments without retraining Laboratory BMIs need to be better prepared for ADL

Translating Thoughts into Action: The Neural Code Stimulus Neural System Neural Response StimulusNeural Response CodingGivenTo determine DecodingTo determineGiven

Vision for Next Generation Brain- Machine Interaction Intelligent behavior arises from the actions of an individual seeking to maximize received reward in a complex and changing world. Perception-Action Cycle: Adaptive, continuous process of using sensory information to guide a series of goal-directed actions. Behavior Consequences Antecedents

Co-Adaptive BMIs using Reinforcement Learning

Prerequesites for Symbiosis

Co-Adaptive BMI involves TWO intelligent agents involved in a continuous dialogue!!! ROBOT actions rewards brain states RAT’S BRAIN environment RAT’S BRAIN COMPUTER AGENT

Decoding using Reinforcement Learning Rather than knowledge of the kinematic hand trajectory only a performance score is supplied. The score could represent reward or penalty, but does not directly provide information about how to correct for the error. Reward based learning - try to choose strategy to maximize rewards. RL originated from optimal control theory in Markov Decision Processes.

Experimental Co-Adaptive BMI Paradigm Incorrect Target Correct Target Starting Position Match LEDs Grid-space Match LEDs Rat’s Perspective Water Reward Map workspace to grid Rat Robot Arm Left Lever Right Lever 27 discrete actions 26 movements 1 stationary

Agent - Value function estimation

Evidence for Symbiosis Valuation Change in Computer Agent Brain Reorganization Overall Performance

Key Concepts for the Future Fully implantable interfaces are only half of the story. Sharing of goals enables brain-computer dialogue and symbiosis Need for intelligent decoders that assist and co-adapt with the user.

History of Man-Machine Interaction “Implanting tiny machines into the nerves of the heart would make us less human” Today, over half a million pacemakers are implanted annually! We are at the frontier for integrating machines with the nervous system to restore and enhance function. Nicolelis

Tremendous team effort! Jack DiGiovanna - BME Babak Mahmoudi - BME This work is supported by NSF project No. CNS Jose Principe - ECE Jose Fortes - ECE

Please visit the lab website for publications and additional information. Neuroprosthetics Research Group