Control of a humanoid robot using EEG. Problem EEG is low bandwidth Hard to exercise fine grained control.

Slides:

Advertisements

Similar presentations

Sustainable Energy – Sustainable ATC Surveillance Workshop – Eurocontrol, Brussels, April 2010 Agenda Item Wind Turbine Interference – Possible Mitigations.

Advertisements

Sec 1-4 Concepts: Classifying Angles Objectives: Given an angle, name, measure and classify it as measured by a s.g.

Breakout session B questions. Research directions/areas Multi-modal perception cognition and interaction Learning, adaptation and imitation Design and.

Evaluation of segmentation. Example Reference standard & segmentation.

IntroductionMethods Participants  7 adults with severe motor impairment.  9 adults with no motor impairment.  Each participant was asked to utilize.

Brain-computer interfaces: classifying imaginary movements and effects of tDCS Iulia Comşa MRes Computational Neuroscience and Cognitive Robotics Supervisors:

Image classification in natural scenes: Are a few selective spectral channels sufficient?

NeuroPhone: Brain-Mobile Phone Interface using a Wireless EEG Headset Source: MobiHeld 2010 Presented By: Corey Campbell.

Mid-level Visual Element Discovery as Discriminative Mode Seeking Harley Montgomery 11/15/13.

Corpus Development EEG signal files and reports had to be manually paired, de-identified and annotated: Corpus Development EEG signal files and reports.

III 1 Sorin Alexe RUTCOR, Rutgers University, Piscataway, NJ URL: rutcor.rutgers.edu/~salexe Datascope - a new tool.

Node-level Representation and System Support for Network Programming Jaein Jeong.

Online Automation and Control: An Experiment in Distance Engineering Education INTERDISCIPLINARY ROBOTICS AND INTELLIGENT SYSTEMS CONTROL (RISC) LABORATORY.

A commonly used feature to discriminate between hand and foot movements is the variance of the EEG signal at certain electrodes. To this end, one calculates.

Optimization of Signal Significance by Bagging Decision Trees Ilya Narsky, Caltech presented by Harrison Prosper.

Welcome to CS201!!! Introduction to Programming Using Visual Basic.

Online Automation and Control: An Experiment in Distance Engineering Education Tarek Sobh Sarosh Patel INTERDISCIPLINARY ROBOTICS AND INTELLIGENT SYSTEMS.

Feature extraction Feature extraction involves finding features of the segmented image. Usually performed on a binary image produced from.

Brief overview of ideas In this introductory lecture I will show short explanations of basic image processing methods In next lectures we will go into.

Jen Stirrup MVP CopperBlue Consulting. Flexible: Can model anything Powerful: Enterprise scale Secure: Fine grain control Near real time: 15 minute.

CMPUT 617 (Topics in Computing Science): Advanced Image Analysis Nilanjan Ray Fall 2012 Computing Science University of Alberta.

Abstract EEGs, which record electrical activity on the scalp using an array of electrodes, are routinely used in clinical settings to.

Human tracking and counting using the KINECT range sensor based on Adaboost and Kalman Filter ISVC 2013.

Convolutional Neural Networks for Image Processing with Applications in Mobile Robotics By, Sruthi Moola.

West Virginia University

1 9/10/2015 PanelDog DC Graphical LCD Meter Series.

Data Processing Machine Learning Algorithm The data is processed by machine algorithms based on hidden Markov models and deep learning. They are then utilized.

Teaching Deliberative Navigation Using the LEGO RCX and Standard LEGO Components Gary R. Mayer, Dr. Jerry Weinberg, Dr. Xudong Yu

KYLE PATTERSON Automatic Age Estimation and Interactive Museum Exhibits Advisors: Prof. Cass and Prof. Lawson.

EXERCISE 4. NO.1 (Worse) Modification of the heuristics was made by Lacksonen and Enscore (1993) to solve the dynamic layout problem. (Better) Lacksonen.

Learning a Fast Emulator of a Binary Decision Process Center for Machine Perception Czech Technical University, Prague ACCV 2007, Tokyo, Japan Jan Šochman.

EFFICIENT ROAD MAPPING VIA INTERACTIVE IMAGE SEGMENTATION Presenter: Alexander Velizhev CMRT’09 ISPRS Workshop O. Barinova, R. Shapovalov, S. Sudakov,

Oppenheimer Technologies Rick King Jonathan Creekmore.

Distributed Virtual Environments Introduction. Outline What are they? DVEs vs. Analytic Simulations DIS –Design principles Example.

The Perceptron. Perceptron Pattern Classification One of the purposes that neural networks are used for is pattern classification. Once the neural network.

The Berlin Brain-Computer Interface: Machine Learning-Based Detection of User Specific Brain States Umar Farooq Berlin Brain Computer Interface.

1 Automatic Classification of Bookmarked Web Pages Chris Staff Third Talk February 2007.

EXPERIMENT DESIGN  Variations in Channel Density  The original 256-channel data were downsampled:  127 channel datasets  69 channels datasets  34.

Analysis of Movement Related EEG Signal by Time Dependent Fractal Dimension and Neural Network for Brain Computer Interface NI NI SOE (D3) Fractal and.

First-Person Activity Recognition: What Are They Doing to Me? M. S. Ryoo and Larry Matthies Jet Propulsion Laboratory, California Institute of Technology,

Convergence of the Fourier Series Used in Example 2.3 (and why analysis of the harmonics is important in communication systems)

Dense Color Moment: A New Discriminative Color Descriptor Kylie Gorman, Mentor: Yang Zhang University of Central Florida I.Problem:  Create Robust Discriminative.

User Interface Development Target or Specific User Groups.

Tiered Imaging Aman Kansal,Mohammad Rahimi. High Resolution Imaging Design Objective: Maximize spatial coverage Maximize resolution –Sensing performance.

Intelligent Systems Research Centre University of Ulster, Magee Campus BCI Research at the ISRC, University of Ulster N. Ireland, UK By Dr. Girijesh Prasad.

Convolutional Restricted Boltzmann Machines for Feature Learning Mohammad Norouzi Advisor: Dr. Greg Mori Simon Fraser University 27 Nov

Sub pixelclassification

Machine Learning in Practice Lecture 10 Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.

GeoResources Institute Computational Resources: Collaborative Environment for Mapping, Analysis, and Planning CE MAP Chuck O’Hara Associate.

Titre. Geographic Information System GIS offer powerful tools for adding spatial perspectives to: –Planning –Research –Technology transfer –Impact assessment.

Deep Learning Overview Sources: workshop-tutorial-final.pdf

Show Me Potential Customers Data Mining Approach Leila Etaati.

© Copyright Mistras Group Inc MISTRAS GROUP CONFIDENTIAL Noesis Noesis specializes in Acoustic Emission (AE) data analysis including real-time software.

Constructing Multiple Views The architecture of the window was altered to accommodate switching between waveform, spectrogram, energy, and all combinations.

Bongjae Choi, Sungho Jo Presented by: Yanrong Wo

MATLAB Distributed, and Other Toolboxes

[Ran Manor and Amir B.Geva] Yehu Sapir Outlines Review

Session 7: Face Detection (cont.)

When to engage in interaction – and how

Fabien LOTTE, Cuntai GUAN Brain-Computer Interfaces laboratory

Massachusetts Institute of Technology

Correcting Robot Mistakes in Real Time Using EEG Signals

ARD Needs and Plans for Thematic Pilots

Figure 4. Testing minimal configurations with existing models for spatiotemporal recognition. (A-B) A binary classifier is trained to separate a positive.

Looking to the Future: User-centric

Multiple Instance Learning: applications to computer vision

The Berlin Brain-Computer Interface: Machine Learning-Based Detection of User Specific Brain States Umar Farooq.

A Low-Cost EEG System-Based Hybrid Brain-Computer Interface for Humanoid Robot Navigation and Recognition Bongjae Choi, Sungho Jo Presented by Megan Fillion.

Computer Vision Readings

Ryan Layer CU Boulder CS Ryan Layer

Presentation transcript:

Control of a humanoid robot using EEG

Problem EEG is low bandwidth Hard to exercise fine grained control

Solution Use an autonomous robot Provide various options for user to select from Use P300 to detect which option is selected

User Study 4 training sessions to train classifier for grids: 2x2, 2x3, 3x2.25sec flash alternating between options One binary classifier for P300 Spatial projection algorithm o a multichannel time-series response to an event and projects all the channels to form a single time series that is maximally discriminative.

Brain-Robot Interface Robot offers image choices to the user A border flashes alternating on images User selects an option using P300 response

Results 98.4% classification accuracy 97% accuracy without the spatial filter Grid layout did not have a significant impact

P3 example

Number of Flashes 95% accuracy with 5 flashes Using.25 sec flash, with 4 options, a command can be sent every 5 seconds

Number of Flashes

Generalizing Classification

Training Time

Discussion New mode of interaction Many potential uses