Semantic Component Analysis
Event Location: NSH 1507Abstract: We propose a novel formulation for component analysis that allows for rich instance-level constraints that encourage semantic interpretability of the learned components. Even with simple features and intuitive spatial consistency priors, our method produces accurate, semantically-meaningful image segmentations both with and without supervision.
Webly supervised learning of convolutional networks
Event Location: NSH 1507Bio: I am a PhD student at Language Technology Institute, Carnegie Mellon University, from fall 2012. I am working with Prof. Abhinav Gupta on joint learning with language and vision and life-long learning. I am also working with Prof. Tom Mitchell in CMU. Recently, I just finished my internship in MSR with [...]
Unsupervised Visual Representation Learning by Context Prediction
Event Location: NSH 1507Bio: I'm a sixth year PhD Student in the Machine Learning Department at CMU, working with Alyosha Efros and Abhinav Gupta. I graduated from CMU in 2010 with a B.S. in computer science and cognitive science, with a minor in neural computation, completing an undergraduate thesis with Tai Sing Lee. I'm interested [...]
Panoptic Studio: A Massively Multiview System for Social Motion Capture
Event Location: NSH 1507Bio: I am a Ph.D. student in the Robotics Institute at Carnegie Mellon University, under the supervision of Yaser Sheikh. During summer 2015, I interned at Disney Research Zurich where I worked with Thabo Beeler and Derek Bradley. Before joining CMU, I spent three years as a researcher at ETRI, a government-funded [...]
Performing Self-Scheduled Services in the Spare Time of a Mobile Autonomous Service Robot
Event Location: NSH 3305Abstract: Mobile autonomous service robots perform services requested by users at specific times. The goal of this thesis is to explore how a service robot can make use of the spare time between user requests. We propose the robot performs self-scheduled services for which it receives reward from the users. Our proposed [...]
Agricultural Robotics and the Chilean Challenges
Event Location: GHC 2109Bio: Fernando Auat Cheein received the Doctorate degree in 2009 and the Master of Science degree in 2005, both in San Juan, Argentina. Since 2013 he is a Professor with Federico Santa María Technical University (UTFSM), in Valparaíso, Chile, after doing his post doc research stay in agricultural robotics also in Argentina [...]
Orchard Characterization and its importance in Crop Management
Event Location: GHC 2109Bio: Fernando Auat Cheein received the Doctorate degree in 2009 and the Master of Science degree in 2005, both in San Juan, Argentina. Since 2013 he is a Professor with Federico Santa María Technical University (UTFSM), in Valparaíso, Chile, after doing his post doc research stay in agricultural robotics also in Argentina [...]
Subdimensional Expansion: A Framework for Computationally Tractable Multirobot Path Planning
Event Location: NSH 1507Abstract: Planning optimal paths for large numbers of robots is computationally expensive. In this thesis, we present a new framework for multirobot path planning called subdimensional expansion, which initially plans for each robot individually, and then coordinates motion among the robots as needed. More specifically, subdimensional expansion initially creates a one-dimensional search [...]
Reducing Localization Error for Planetary Rovers with Absolute Bearing by Continuously Tracking the Sun
Event Location: NSH 1507Bio: Curtis Boirum is a M.S. student in the Robotics Institute advised by William “Red” Whittaker. He received an M.S. and B.S. in Mechanical Engineering from Bradley University in Peoria, IL in 2011 and 2009, respectively. He also received a B.S. in Physical Science from Eureka College in Eureka, IL in 2010. [...]