Carnegie Mellon University
Learning to learn from simulation: Using simulations to expedite learning on robots
Abstract: Robot controllers, including locomotion controllers, often consist of expert-designed heuristics. These heuristics can be hard to tune, particularly in higher dimensions. It is typical to use simulation to tune or learn these parameters and test on hardware. However, controllers learned in simulation often don't transfer to hardware due to model mismatch. This necessitates controller [...]
Fun with Fluids
Abstract: Visual simulation of fluids has become an indispensable tool for computer graphics. Many fluid phenomena can be simulated by solving Navier-Stokes equations. In computer graphics, the NS equations are mostly used for simulating smoke, water and fire. However, it is useful for other different purposes. In this talk, we show our usage of [...]
Carnegie Mellon University
Training Strategies for Time Series: Learning for Prediction, Filtering, and Reinforcement Learning
Abstract: Data driven approaches to modeling time-series are important in a variety of applications from market prediction in economics to the simulation of robotic systems. However, traditional supervised machine learning techniques designed for i.i.d. data often perform poorly on these sequential problems. This thesis proposes that time series and sequential prediction, whether for forecasting, filtering, [...]
Panel Discussion: “Robotics, Pittsburgh and the End of Work”
As one of the test sites for Uber’s driverless cars, Pittsburgh is frequently hailed as a city of the future. And indeed, some economists predict that robots will outnumber human workers as early as 2040. At this panel will talk about how we can plan for this seismic change in our economy and way of [...]
Dinner Reception: “Robotics, Pittsburgh and the End of Work”
After the “Robotics, Pittsburgh and the End of Work” talk, head over the lounge outside of the Giant Eagle auditorium, A51 Baker Hall, for a dinner reception from 6-7 pm.
“Love Your Work”
Kathi Weeks is Professor of Women’s Studies at Duke University and writes about the intersection of feminism and labor. In her talk about anti-work politics in the age of “love your work,” Weeks Livingston argues for a Universal Basic Income (UBI) and a future in which we leave the Protestant work ethic behind.
Robotics Institute Faculty Lunch
By Invitation Only - Robotics Institute Faculty Lunch - Please arrive by 11:45AM, talk will begin promptly at 12:00PM.
Carnegie Mellon University
Expressive Real-time Intersection Scheduling
Abstract: Traffic congestion is a major annoyance throughout global metropolitan areas. This talk will present Expressive Real-time Intersection Scheduling (ERIS), a schedule-driven control strategy for adaptive intersection control to reduce traffic congestion. ERIS maintains separate estimates for each lane approaching a traffic intersection allowing it to more accurately estimate the effects of scheduling decisions than [...]