Eric Beowulf Martinson

Eric Beowulf Martinson

RESEARCH INTERESTS

Autonomous Mobile Robotics, Human-Robot Interaction, Computational Perception, Machine Learning, Signal Processing 

EDUCATION

Georgia Institute of Technology

Atlanta, GA

Ph.D.in Computer Science

“Acoustical Awareness for Intelligent Robotic Action”

November, 2007

M.S. in Computer Science

May, 2006

University of California, Irvine

Irvine, CA

B.S. in Information and Computer Science,

B.S. in Mechanical Engineering

March 2000

University of Sydney

Sydney, Australia

Education Abroad Program (EAP)

1998

RESEARCH EXPERIENCE

Toyota InfoTechnology Center, USA
Senior Researcher

Object Delivery with a Mobile Manipulator - Robotics Team Leader
  • Develop novel methods of robotic interaction with the disabled, blind, and/or elderly
  • Machine learning research, including deep learning, into people detection, recognition, and activity estimation for mobile robot using stereo vision and other RGB-D sensors
  • Deployed full delivery system to multiple indoor environments, including internationally
Cognitive Computing - Team Leader
  • Investigate the human brain, predicting human behavior with recurrent neural networks.


 
U.S. Naval Research Lab
NRC Post-Doctoral Fellow 
Robot Firefighter - Demonstration Team Leader
  • Lead a team of researchers in demonstrating the use of a humanoid robot in support of Navy firefighters. Demonstrated before the Chief of Naval Research, and Presidential Science Advisor, John Holdren.
  • Constructed fire detection algorithms and robot manipulation for fire suppression.
  • Integrated gesture, speech recognition, manipulation, and mobility
Robot Audition
  • Developed 3D mapping capabilities for a mobile robot using time-of-flight cameras, integrating the result into perceptual simulations.
  • Designed a perceptual-fusion based person-identification system for a humanoid robot utilizing face, speaker, and clothing recognition.    
Summer Intern
·        Designed sound source localization algorithms for mobile robots
·        Developed an auditory interface using speech for a mobile information kiosk 
 
 
Washington, D.C.
Jan, 2010 - Dec, 2012
 
 










Summer 2005, Summer 2006

HRL Laboratories 
Contractor
  • Developed a theoretical framework for programming a manipulator by human demonstration
  • Demonstrated learning of multi-part assembly from observations of unordered sub-tasks
Summer Intern
  • Designed and tested algorithms for the behavioral organization of mobile autonomous sensor array
 
Malibu, CA 

Mar - Dec, 2009





Summer 2003

 

 

 

Kharkov National University of Radio-Electronics

Fulbright Fellow

  • Critical Language Enhancement Award (4 months), Russian
  • Using a mobile robot and microphone array to detect hardware failures acoustically in manufacturing.

Kharkov, Ukraine

Jan, 2008 - Present


Evolution Robotics
ERSP Product Testing
  • Ran comprehensive tests of the behavioral capabilities of the ERSP robotic development platform for linux.
 
Atlanta, GA

May, 2003

 

Georgia Institute of Technology, DARPA MARS Project

Research Assistant

  • Implemented Q-learning for the autonomous selection of pre-defined behaviors, and/or assemblages to enhance application performance in individual robots and robot teams.
 
Atlanta, GA

Fall 2000 to Spring 2003

 

Yamaha Motors
Consultant
  • Performed web research on innovative small motor applications
 
Irvine, CA

June 1999 to March 2000

TEACHING EXPERIENCE

Georgia Institute of Technology, College of Computing

Teaching Assistant, CS4400 – Introduction to Database Systems

·        Bi-Weekly Office Hours

·        Grading of projects and quizzes

·        Lead TA (5 Semesters)

·        Designed semester long project arc

·        Coordinated teaching efforts of 4-5 TA’s

·        Managed grades for 3 class sections (200-300 students)

·        Lectured in absence of professor or guest lecturer

Atlanta, GA

Fall, 2003 to Fall, 2007

 
Georgia Institute of Technology, College of Computing

Teaching Assistant, CS4001 – Computing and Society

·        Grading of written essays and short-answer based exams

 
Atlanta, GA

Summer, 2007

 
Georgia Institute of Technology, College of Computing

Teaching Assistant, CS4631 – Introduction to Perception and Robotics

·        Grading programming projects / exams

 
Atlanta, GA

Spring, 2003

INVITED TALKS

  • Learning to Listen with Eyes, Ears and Feet, National Robotics Engineering Center, July 2011      
  • Robot Audition, Robot Control Systems Class, Kharkov National University of Radio-Electronics, Nov 2008
  • Auditory Scene Modeling for Mobile Robotics, TAPR Departmental Presentation, Kharkov National University of Radio-Electronics, Apr. 2008

PATENTS

  1. E. Martinson, V. Yalla, "Augmenting Layer-Based Object Recognition with Deep Convolutional Neural Networks", US Patent #9542626, Jan 10, 2017
  2. E. Martinson, O. Olabiyi, K. Oguchi "Individualized Adaptation of Driver Action Prediction Models" US Patent Applied for Nov 2016
  3. O. Olabiyi, E. Martinson, "Efficient Driver Action Prediction System Based on Temporal Fusion of Sensor Data Using Deep Recurrent Neural Network" US Patent Applied for Nov 2016
  4. E. Martinson, "Efficient Layer-Based Object Recognition," US Patent #9355334, May 31, 2016
  5. E Martinson, P. Cottrell, "Gait Analysis Medical Assistant Robot," US Patent Applied for May 2016
  6. E Martinson, D Kim, "Autonomous Human-Centric Place Recognition," US Patent Applied for Mar 2016
  7. E. Martinson, "Guiding Computational Perception through a Shared Auditory Space," US Patent #9301722, Apr 5, 2016
  8. E. Sisbot, V. Yalla, E. Martinson, "Classifying Routes of Travel," US Patent Applied for Oct 2014
  9. E Martinson, D Kim, E. Sisbot, "Adapting Object Handover from Robot to Human Using Perceptual Affordances," US Patent Applied for May 2016
  10. E. Martinson et al  "Object Detection and Localized Extremity Guidance," US Patent Applied for Mar 2015
  11. E. Martinson et al "Providing Personalized Patient Care Based on Electronic Health Record Associated with a User," US Patent Applied for Feb 2015
  12. L. Barajas, E. Martinson, D. Payton, R. Uhlenbrock, “Method and System for Training a Robot Using Human-Assisted Task Demonstration”, US Patent# 20130245824, Sep 19 2013
  13. D. Payton and E. Martinson, “Arranging Mobile Sensors into a Predetermined Pattern”, US Patent # 7379840, May 27, 2008

PUBLICATIONS

Refereed Publications

  1. D. Kim, E. Martinson, " Human Centric Spatial Affordances for Improving Human Activity Recognition," Intell. Robots and Systems (IROS), Daejeon, Korea, Oct 2016
  2. E. Martinson, V. Yalla, "Augmenting Deep Convolutional Neural Networks with Depth-Based Layered Detection for Human Detection," IROS, Daejeon, Korea, Oct 2016
  3. E. Martinson, A. Blasdel, E. Sisbot, "Personalizing Object Handover with an Electronic Health Record," Accepted to RO-MAN, New York, USA, Aug 2016
  4. E. Martinson, V. Yalla, "Real-Time Human Detection for Robots using CNN with a Feature-Based Layered Pre-filter," RO-MAN, New York, USA, Aug 2016
  5. E. Martinson, V. Yalla, "Guiding Computational Perception through a Shared Auditory Space," Int. Conference on Intelligent Robots and Systems, Chicago, US, Sept 2014
  6. E. Martinson, "Detecting Occluded People for Robotic Guidance," IEEE Int. Symp. on Robot and Human Interactive Communication, Edinburgh, UK, Aug 2014
  7. W. Lawson, J.  Trafton, E. Martinson, "Complexion as a Soft Biometric in Human-Robot Interaction," Int. Conf. on Biometrics: Theory, Application and Systems, Arlington, VA 2013
  8. E. Martinson, W. Lawson, J.G. Trafton, "Identifying People with Soft-Biometrics at Fleet Week," Int. Conference on Human-Robot Interaction, Tokyo, 2013
  9. E. Martinson, W. Lawson, S. Blisard, A. Harrison, J. G. Trafton, "Fighting Fires with Human Robot Teams," Int. Conf on Intelligent Robots and Systems, Vilamoura, Portugal, 2012
  10. E. Martinson, T. Apker, "A Physics Inspired Finite State Machine Controller for Mobile Acoustic Arrays," Int. Symp. on Distributed Autonomous Robotic Systems, Baltimore, 2012
  11. E. Martinson, T. Apker, M. Bugajska, “Optimizing a Reconfigurable Robotic Microphone Array”, Int. Conf on Intelligent Robots and Systems, San Francisco, 2011
  12. E Martinson, W Lawson, “Learning Speaker Recognition Models through Human-Robot Interaction,” International Conf. on Robotics and Automation (ICRA), Shanghai, China 2011
  13. E. Martinson, B. Fransen, “Dynamically Reconfigurable Microphone Arrays”, International Conference on Robotics and Automation (ICRA), Shanghai, China 2011
  14. W. Lawson, E. Martinson, “Multimodal Identification using Markov Logic Networks”, IEEE Conference on Automatic Face and Gesture (FG), San Diego, CA 2011
  15. W. Lawson, E. Martinson, T. Apker, C. Bradel, P. Walker, J. G. Trafton, "ROBOT-Busters," AAAI-11 Video Competition, San Francisco, CA 2011
  16. L. Hiatt, A. Harrison, W. Lawson, E.Martinson, J. G. Trafton, "Robotics Secrets Revealed, Episode 002" AAAI-11, San Francisco, CA 2011 (Award for Most Educational Video
  17. E. Martinson, W. Lawson, G. Trafton, “Person Identification through Perceptual Fusion” Int Conf on Humanoid Robots, Nashville, TN, 2010
  18. E. Martinson. “Simulating Robotic Auditory Environments.” Accepted to the Int Conf on Intelligent Autonomous Systems, Ottawa, Canada,  2010
  19. Martinson, B. Fransen, W. Lawson. "Scene Understanding Through Audio-Visual Fusion." Proceedings of the Workshop on RGB-D: Advanced Reasoning with Depth Cameras, at Robots, Science and Systems, Zaragoza, Spain 2010
  20. E. Martinson, I. Nevludov, and A. Tsymbal. "Evaluation of the Accuracy of Sound Volume Models Created from Robot-Acquired Information." Radiotekhnika (Ukrainian Scientific Magazine), 2009
  21. E. Martinson and A. Schultz, “Discovery of Sound Sources by an Autonomous Mobile Robot,” Autonomous Robots, 27, 2009
  22. E. Martinson, “Using a Mobile Robot to Detect Changes to the Auditory Scene,” Proceedings of the Third International Radio-Electronics Forum, Sudak, Ukraine, Sept 2008
  23. E. Martinson, “Hiding the Acoustic Signature of a Mobile Robot”, Proceedings of the International Conference on Intelligent Robots and Systems (IROS), San Diego, CA, Oct 29-Nov 2, 2007
  24. E. Martinson and A. Schultz, “Robotic Discovery of the Auditory Scene”, Proceedings of the International Conference on Robotics and Automation (ICRA), Rome, Italy, April 10-14, 2007
  25. E. Martinson and D. Brock, “Improving Human-Robot Interaction through Adaptation to the Auditory Scene”, Proceedings of the 2nd ACM/IEEE International Conference on Human-Robot Interaction (HRI), Washington, DC, Mar 9-11, 2007
  26. S. Blisard, B. Fransen, M. Marge, E. Martinson, V. Morariu, S. Thomas, and D. Perzanowski, “Using Vision, Acoustics, and Natural Language for Disambiguation”, Proceedings of the 2nd ACM/IEEE International Conference on Human-Robot Interaction (HRI), Washington, D.C., Mar 9-11, 2007
  27. E. Martinson and A. Schultz, “Auditory Evidence Grids,” in proc. Of Int. Conf. On Intelligent Robots and Systems, Beijing, China, Oct. 2006
  28. D. Brock and E. Martinson, “Using the Concept of Auditory Perspective Taking to Improve Robotic Speech Presentations for Individual Human Listeners”, Proceedings of the AAAI Fall Symposium Workshop on Aurally Informed Performance: Integrating Machine Listening and Auditory Presentation in Robotic Systems, FS-06-01, Oct 6, 2006
  29. D. Brock and E. Martinson, “Exploring the Utility of Giving Robots Auditory Perspective-Taking Abilities”, Proceedings of the International Conference on Auditory Display, London, UK, June 20-23, 2006
  30. E. Martinson and D. Brock, “Auditory Perspective Taking,” in proc. Of Human-Robot Interaction, Salt Lake City, UT, 2006
  31. E. Martinson and D. Payton, Lattice Formation in Mobile Autonomous Sensor Arrays, Lecture Notes in Computer Science, Springer Berlin/Heidelberg, vol. 3342, 2005, p98-111
  32. E. Martinson and R. C. Arkin, Noise Maps for Acoustically Sensitive Navigation”, in proc. Of SPIE, vol. 5609, Oct. 2004
  33. E. Martinson, F. Dellaert. “Marco-Polo Localization”, in proc. Of Int. Conf. On Robotics and Automation, Taipei, Taiwan, Oct 2003
  34. F. Dellaert, F. Alegre, and E. Martinson, “Intrinsic Localization and Mapping with 2 Applications- Diffusion Mapping and Marco Polo Localization”, in proc. of Int. Conf. On Robotics and Automation, Taipei, Taiwan, Oct 2003
  35. E. Martinson, R. Arkin. “Learning to Role-Switch in Multi-Agent Systems”, in proc. Of Int. Conf. On Robotics and Automation, Taipei, Taiwan, Oct 2003
  36. R. Arkin, Y. Endo, B. Lee, D. MacKenzie, and E. Martinson, Multistrategy Learning Methods for Multirobot Systems”, NRL Workshop on Multi-Robot Systems, Washington D.C., 2003.
  37. E. Martinson, A. Stoytchev, R. Arkin, “Robot Behavioral Selection Using Q-learning”.  In proc. Of Intelligent Robots and Systems, Lausanne, Switzerland, Oct. 2002
     
     
    Technical Report

1.      E. Martinson, A. Stoytchev, R. Arkin (2001) “Robot Behavioral Selection Using Q-learning”. Tech Report #GIT-CC-01-19, Georgia Institute of Technology, 2001

HONORS  

  •           Toyota ITC 2nd Best Inventor (2013), 3rd Best Inventor (2015)
  • Fulbright Student Fellowship, Ukraine, Jan, 2008-March, 2009
  • President’s Fellowship, Georgia Institute of Technology, Fall 2000 to Fall 2004
  • Honorable Mention, National Science Foundation Fellowship, Spring 2000
  • Summa Cum Laude, Information and Computer Science, Spring 2000
  • Magna Cum Laude, Mechanical and Aerospace Engineering, Spring 2000
  • Regent’s Scholarship, University of California, 1995-1999

ROBOT APPLICATIONS

      Continuous Person Identification through Perceptual Fusion
Face recognition and speaker recognition both provide mechanisms for recognizing an individual. Neither, however, provides the continuous recognition needed by robots. This work fuses multiple modalities for real-time identification and tracking by a humanoid robot.
 
Planning and Control of a Robot Manipulator Through Demonstration.
By first showing the robot how the object should be manipulated, it learns both the task, and when to execute the task based on environmental conditions. 
      
      Acoustic Surveillance by a Mobile Security Guard

This work uses knowledge of sound flow through the environment to identify changed or new sound sources along a mobile security guard robot’s patrol route.  Current work on this application is extending it to the detection of industrial hardware failure.

Acoustically Stealthy Approach

As most robots used for security applications generate a significant amount of motor and fan noise, this work explores masking a robot’s ego-noise with ambient noise sources through autonomous route selection.

Mapping the Auditory Scene

Movement and sampling algorithms were designed for the autonomous discovery and exploration of the soundscape by a mobile robot. The work focused on identifying three aspects (1) discovering source locations with the auditory evidence grid; (2) building models of source directivity; and (3) estimating the volume of noise due to these sound sources found throughout the environment.

The Information Kiosk (Human-Robot Interaction)

A text-to-speech interface is augmented with acoustic sensing and mobility so as to improve the quality of Human-Robot Interaction in a dynamic acoustic environment.

Disambiguation of Natural Language and Vision using Acoustics

A combination of visual and acoustic sensing is used to overcome ambiguity in a natural language interface for human-robot interaction.

Sampled-Data Noise Maps

Extensive auditory sampling of the ambient noise is combined with robot localization information (SICK LMS or overhead cameras) to build Noise Contour Maps.

Lattice Formation by Mobile Robot Teams

Local behaviors, using only local sensing, were designed to build a narrow band sensor array from a group of randomly distributed mobile microphone elements.  A patent was applied for and received.

Marco-Polo Localization

This work uses a team of robots equipped with sound emitters and microphones to solve the range-only SLAM problem.

 
Robot Behavioral Selection Using Q-learning (DARPA MARS)
Implemented Q-learning for the autonomous selection of pre-defined behaviors and/or assemblages to enhance application performance in individual robots and robot teams.

REVIEWER

·       IEEE International Conference on Humanoid Robots (Humanoids) – 2010
 
·       U.S. Fulbright Student and Scholar Grant Proposals, Ukraine – 2008

·       International Conference on Robotics and Automation (ICRA) – 2003, 2007, 2008, 2011 

·       International Conference on Intelligent Robots and Systems (IROS) – 2005, 2006, 2007, 2011, 2012 

·       Human-Robot Interaction – 2006, 2007, 2011 

·          AAAI Fall Symposium – 2006

SKILLS

Programming and Computer Skills
Languages: C/C++, C#, JAVA, Matlab, SQL
Software: Cygwin, Microsoft Robotics Developer Studio, SQL Server, Visual Studio, Player/Stage, OpenCV
 
Robotic Platform Experience
ActivMedia: AmigoBot, Pioneer AT, Pioneer 2-DXE
IRobot: ATRV-Jr, B21r, Create/Roomba
Nomadic Technologies: Nomad 200, Nomad 150
Xitome Design: Mobile Dextrous Social (MDS) Robot
Small Robots: Lego NXT, Evolution Robotics ER1, LynxMotion AL5C Robotic Arm
 
Languages
English: primary language
Russian: intermediate level (evaluated by ALTA Language Testing Services, May 2008)