Select a calendar:
Filter October Events by Event Type:
Events for October 12, 2021
-
CS Undergraduate Live Chat Drop-in Advisement
Tue, Oct 12, 2021 @ 01:30 PM - 02:30 PM
Thomas Lord Department of Computer Science
Student Activity
CS Advisors will be available on Tuesdays/Wednesdays/Thursdays this fall from 1:30pm to 2:30pm to assist undergraduates in our four majors (CSCI, CSBA, CSGA, and CECS) via Live Chat. Access the live chat through our website at https://cs.usc.edu/chat
Location: Online - Live Chat
Audiences: Undergrad
Contact: USC Computer Sciecne
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
CS Colloquium: Thomas Howard (University of Rochester) - Enabling Grounded Language Communication for Human-Robot Teaming
Tue, Oct 12, 2021 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Thomas Howard, University of Rochester
Talk Title: Enabling Grounded Language Communication for Human-Robot Teaming
Series: Computer Science Colloquium
Abstract: The ability for robots to effectively understand natural language instructions and convey information about their observations and interactions with the physical world is highly dependent on the sophistication and fidelity of the robot's representations of language, environment, and actions. As we progress towards more intelligent systems that perform a wider range of tasks in a greater variety of domains, we need models that can adapt their representations of language and environment to achieve the real-time performance necessitated by the cadence of human-robot interaction within the computational resource constraints of the platform. In this talk I will review my laboratory's research on algorithms and models for robot planning, mapping, control, and interaction with a specific focus on language-guided adaptive perception and bi-directional communication with deliberative interactive estimation.
Register in advance for this webinar at:
https://usc.zoom.us/webinar/register/WN_Rf6FW9NNSIWBkuNs9P5EcQ
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Thomas Howard is an assistant professor in the Department of Electrical and Computer Engineering at the University of Rochester. He also holds secondary appointments in the Department of Biomedical Engineering and Department of Computer Science, is an affiliate of the Goergen Institute of Data Science and directs the University of Rochester's Robotics and Artificial Intelligence Laboratory. Previously he held appointments as a research scientist and a postdoctoral associate at MIT's Computer Science and Artificial Intelligence Laboratory in the Robust Robotics Group, a research technologist at the Jet Propulsion Laboratory in the Robotic Software Systems Group, and a lecturer in mechanical engineering at Caltech.
Howard earned a PhD in robotics from the Robotics Institute at Carnegie Mellon University in 2009 in addition to BS degrees in electrical and computer engineering and mechanical engineering from the University of Rochester in 2004. His research interests span artificial intelligence, robotics, and human-robot interaction with a research focus on improving the optimality, efficiency, and fidelity of models for decision making in complex and unstructured environments with applications to robot motion planning, natural language understanding, and human-robot teaming. Howard was a member of the flight software team for the Mars Science Laboratory, the motion planning lead for the JPL/Caltech DARPA Autonomous Robotic Manipulation team, and a member of Tartan Racing, winner of the 2007 DARPA Urban Challenge. Howard has earned Best Paper Awards at RSS (2016) and IEEE SMC (2017), two NASA Group Achievement Awards (2012, 2014), was a finalist for the ICRA Best Manipulation Paper Award (2012) and was selected for the NASA Early Career Faculty Award (2019). Howard's research at the University of Rochester has been supported by National Science Foundation, Army Research Office, Army Research Laboratory, Department of Defense Congressionally Directed Medical Research Program, National Aeronautics and Space Administration, and the New York State Center of Excellence in Data Science.
Host: Stefanos Nikolaidis
Webcast: https://usc.zoom.us/webinar/register/WN_Rf6FW9NNSIWBkuNs9P5EcQLocation: Online Zoom Webinar
WebCast Link: https://usc.zoom.us/webinar/register/WN_Rf6FW9NNSIWBkuNs9P5EcQ
Audiences: Everyone Is Invited
Contact: Computer Science Department
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
PhD Defense - Danyong Zhao
Tue, Oct 12, 2021 @ 04:00 PM - 06:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD candidate: Dangyong Zhao
Committee:
Jernej Barbic (Chair)
C.-C. Jay Kuo
Yong Chen
Date and Time: 10/12 at 4pm
Acquisition of Human Tissue Elasticity Properties Using Pressure Sensors
Abstract:
Physically based simulation of the human body in three dimensions is important in many applications in computer graphics, animation, virtual reality, virtual commerce, ergonomics and virtual medicine. Finite Element Method (FEM) is a robust and reliable approach to simulate deformable dynamics of three-dimensional elastic structures. However, for quality simulation that matches the behavior of real human tissues, FEM needs accurate material properties that correctly model real relationships between the strains and stresses in the human tissue. This thesis presents methods to capture such nonlinear materials for the human musculo-skeletal tissue (skin, fat, muscles) in vivo, through carefully designed poking experiments, force meters, lasers and ultrasound measuring devices. From our experiments, we obtain ground-truth relationships between the contact force and skin deformation. We then fit material models that best approximate the acquired real-world data.
First, we design a measuring device that can simultaneously capture the skin contact force and the skin deformation, consisting of a force meter and a laser distance measuring device. We design sliding and pivoting joints to rigidly attach the force meter to the laser device, so that diverse human body locations (arm, hand, belly, etc.) can be measured ergonomically and reliably. We also use an ultrasound device to capture the depth of the human subcutaneous fat at different locations; enabling us to generate a 3d model of the fat layer, and optionally also the muscle layer, of the human body.
Second, we propose a novel approach to equivalently convert 3D FEM simulations into 2D simulation, suitable for our material capture. This method permits us to greatly speed up our material optimizations, without losing any accuracy. We validated this approach by comparing the simulation result from 2D equations and the 3D traditional equations. We propose to use natural cubic splines to parameterize the three separable scalar elastic energy density functions based on the Valanis-Landel material model. Based on our novel 2D simulation method and the spline-based non-linear isotropic material, we present an efficient method to compute the gradient of the objective function for optimization and use the conjugate gradient optimization method to optimize the material.
Lastly, we use our acquired materials to design the geometric shape of rigid supporting surfaces to maximize the ergonomics of physically based contact between the surface and a deformable human. We model the soft deformable human using a layer of FEM deformable tissue surrounding a rigid core, with measured realistic elastic material properties, and large-deformation nonlinear analysis using our material capturing and optimizing method. We define a novel cost function to measure the ergonomics of contact between the human and the supporting surface. We give a stable and computationally efficient contact model that is differentiable with respect to the supporting surface shape. This makes it possible to optimize our ergonomic cost function using gradient-based optimizers. We 3D-print the optimized shoe sole, measure contact pressure using pressure sensors, and demonstrate that the real unoptimized and optimized pressure distributions qualitatively match those predicted by our simulation.
WebCast Link: https://usc.zoom.us/j/94230145329
Audiences: Everyone Is Invited
Contact: Lizsl De Leon
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.