Logo: University of Southern California

Events Calendar

Events for November 26, 2013

  • Graduate Engineering Online Info Session

    Tue, Nov 26, 2013 @ 09:00 AM - 10:00 AM

    Viterbi School of Engineering Graduate Admission

    Workshops & Infosessions

    The USC Viterbi School of Engineering is a top-10 ranked graduate engineering program by U.S News and World Report. Join us for an online information session to learn about the exciting opportunities available.

    Register Now

    Location: Online

    Audiences: Everyone Is Invited

    Posted By: Ray Fujioka/GAPP

  • Rapid MRI for Sleep Apnea and Speech Production Research

    Tue, Nov 26, 2013 @ 10:00 AM - 11:00 AM

    Ming Hsieh Department of Electrical Engineering

    Conferences, Lectures, & Seminars

    Speaker: Dr. Yoon Kim, University of Southern California

    Talk Title: Rapid MRI for Sleep Apnea and Speech Production Research

    Series: Medical Imaging Seminar Series

    Abstract: The human upper airway serves important functions such as speech, deglutition, and respiration. Understanding the nature or disorder of the upper airway functions has been of great interest in speech scientists, linguists, otolaryngologists, sleep medicine physicians, etc. MRI is noninvasive and has provided spatio-temporal information on the shaping of the tongue, soft palate, lips, and posterior/lateral pharyngeal walls with high frame rate (~20 fps).

    In this talk, I will introduce our technical developments for the two NIH R01 projects: 1) dynamics of vocal tract shaping and 2) phenotyping of sleep-disordered breathing in pediatric obesity using dynamic MRI. On rapid MRI of speech, the talk will be an overview of 1) speech MRI acquisition environment, 2) novel acquisition techniques in real-time 2D, high-resolution 3D, and dynamic 3D imaging, and 3) various applications of real-time speech MRI. On rapid MRI of sleep, the talk will focus on 1) our sleep MR imaging protocols, 2) upper airway compliance measurement during inspiratory loading and 3) demonstrations of airway narrowing/collapse patterns during natural sleep in overweight and obese adolescents with sleep-disordered breathing.

    Biography: Yoon Kim received his PhD in Electrical Engineering from USC in 2010. He is a postdoctoral research associate at USC from 2011 to 2013, working in the Magnetic Resonance Engineering Lab directed by Prof. Krishna Nayak. His research focuses on MRI pulse sequence design and image reconstruction for upper airway imaging and cardiac imaging. He is a recipient of American Heart Association postdoctoral fellowship award.

    Host: Professor Krishna Nayak

    More Info: http://mhi.usc.edu/medical-imaging-seminar-series/

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

    Audiences: Everyone Is Invited

    Posted By: Talyia Veal

  • PhD Defense - Mrinal Kalakrishnan

    Tue, Nov 26, 2013 @ 12:00 PM - 02:00 PM

    Computer Science

    University Calendar

    PhD Candidate: Mrinal Kalakrishnan

    Committee members:

    Stefan Schaal (chair)
    Gaurav Sukhatme
    Francisco Valero-Cuevas (outside member)

    Time: Nov 26th 12:00pm
    Location: RTH 422

    Title: Learning objective functions for autonomous motion generation


    Planning and optimization methods have been widely applied to the problem of trajectory generation for autonomous robotics. The performance of such methods, however, is critically dependent on the choice of objective function being optimized, which is non-trivial to design. On the other hand, efforts on learning autonomous behavior from user-provided demonstrations have largely been focused on reproducing behavior similar in appearance to the demonstrations, which often fails to generalize well to new situations. An alternative approach, known as Inverse Reinforcement Learning (IRL), is to learn an objective function that the demonstrations are assumed to be optimal under. With the help of a planner or trajectory optimizer, such an approach allows the system to synthesize novel behavior in situations that were not experienced in the demonstrations.

    We present novel algorithms for IRL that have successfully been applied in two real-world, competitive robotics settings: (1) In the domain of rough terrain quadruped locomotion, we present an algorithm that learns an objective function for foothold selection based on "terrain templates". The learner automatically generates and selects the appropriate features which form the objective function, which reduces the need for feature engineering while attaining a high level of generalization. (2) For the domain of autonomous manipulation, we present a probabilistic model of optimal trajectories, which results in new algorithms for inverse reinforcement learning and trajectory optimization in high-dimensional settings. We apply this method to two problems in robotic manipulation: redundancy resolution in inverse kinematics, and trajectory optimization for grasping and manipulation.

    Both methods have proven themselves as part of larger integrated systems in competitive settings against other teams, where testing was conducted by an independent test team in situations that were not seen during training.

    Location: Ronald Tutor Hall of Engineering (RTH) - 422

    Audiences: Everyone Is Invited

    Posted By: Lizsl De Leon