• Multi-Representational Learning from Demonstration through Sequential User Study Development
    ONR award N000141410795
    Georgia Institute of Technology

    (Social Interaction Characteristics for Socially Acceptable Robots).
    SICSAR is a FP7-PEOPLE-2013-IEF - Marie-Curie Action: "Intra-European fellowships for career development".
    * I am not a member of SICSAR but my work on vision has been used in it.

    (What You See Is What You Did)
    WYSIWYD is an EU FP7-ICT-612139, a research project between 6 universities across Europe.

    (Persistent Autonomy through learNing, aDaptation, Observation and Re-plAnning)
    PANDORA is an EU FP7-ICT-288273, STREP, a research project between 5 universities across Europe.
    2012-2014 [Trailer][Repository]

Related publications:
  • Learning Reactive Robot Behavior for Autonomous Valve Turning, IEEE Humanoids, 2014. [PDF]
  • Multi-Objective Reinforcement Learning for AUV Thruster Failure Recovery, IEEE ADPRL/SSCI, 2014. [PDF]
  • Online Discovery of AUV Control Policies to Overcome Thruster Failures, IEEE ICRA, 2014. [PDF]
  • Covariance Analysis as a Measure of Policy Robustness in Reinforcement Learning, IEEE OCEANS, 2014. [PDF]
  • Online Direct Policy Search for Thruster Failure Recovery in Autonomous Underwater Vehicles, ERLARS, 2013. [PDF]
  • On-line Learning to Recover from Thruster Failures on Autonomous Underwater Vehicles, IEEE OCEANS, 2013. [PDF]
  • Autonomous Robotic Valve Turning: A Hierarchical Learning Approach, IEEE ICRA, 2013. [PDF]