Coherent Scene Understanding with 3D Geometric Reasoning
Event Location: NSH 1305Abstract: When looking at a single 2D image of a scene, humans could effortlessly understand the 3D world behind the scene even though stereo and motion cues are not available. Due to this remarkable human capability, one of the ultimate goals of computer vision is to enable machines to automatically infer the [...]
Experience Graphs: Leveraging Experience in Planning
Event Location: NSH 1305Abstract: Motion planning is a central problem in robotics and is crucial to finding paths to navigate and manipulate safely and efficiently. Ideally, we want planners which find paths quickly and of good quality. Additionally, planners should generate predictable motions, which are safer when operating in the presence of humans. While the [...]
Study on Wheel Grouser Designs for Improving Traverse Performance of Planetary Rovers
Event Location: GHC 2109Bio: Hiroaki Inotsume is a M.S. student in the Robotics Institute, advised by Prof. David Wettergreen. His work focuses on analysis of vehicle-terrain interactions for design, motion planning, and control of planetary rovers. He received his B.E. and M.E. degrees in Aerospace Engineering from Tohoku University in Japan.Abstract: Because of great successes [...]
Improving Face Analysis Using Expression Dynamics
Event Location: NSH 1507Bio: Hamdi Dibeklioglu received the B.Sc. degree from Yeditepe University, Istanbul in 2006 and the M.Sc. degree from Bogaziçi University,Istanbul in 2008. In 2013, he completed his PhD research in the Intelligent Systems Lab Amsterdam, University of Amsterdam. He is currently a post-doctoral researcher in the Pattern Recognition & Bioinformatics Group at [...]
Subdimensional Expansion: An Approach to Computationally Tractable Multirobot Path Planning
Event Location: NSH 1305Abstract: Planning optimal paths for large numbers of robots is computationally expensive. In our research, we developed 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 [...]
Distributed Algorithm Design for Constrained Multi-robot Task Assignment
Event Location: GHC 8102Abstract: The task assignment problem is one of the fundamental combinatorial optimization problems. It has been extensively studied in operation research, management science, computer science and robotics. In multi-robot systems (MRS), there are various applications of task assignment, such as environmental monitoring, disaster response, extraterrestrial exploration, sensing data collection and collaborative autonomous [...]
MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction
Event Location: NSH 1507Bio: Hanbyul Joo is a Ph.D. student at the Robotics Institute, Carnegie Mellon University, supervised by Prof. Yaser Sheikh. Before joining CMU, he worked as a researcher at ETRI, Korea, and received M.S. and B.S. from KAIST, Korea. He focuses on developing large-scale dynamic reconstruction using about 500 synchronized cameras. He is [...]
Predicting Object Dynamics in Scenes
Event Location: NSH 1507Bio: David Fouhey is a Ph.D. student at the Robotics Institute, Carnegie Mellon University, where he is supervised by Abhinav Gupta and Martial Hebert. He holds an A.B. in Computer Science from Middlebury College. His research addresses a variety of scene understanding tasks in computer vision, with a particular interest in inferring [...]
Trinocular Geometry Revisited
Event Location: NSH 1507Abstract: This is a joint work with J. Ponce. When do the visual rays associated with triplets of point correspondences converge, that is, intersect in a common point? Classical models of trinocular geometry based on the fundamental matrices and trifocal tensor associated with the corresponding cameras only provide partial answers to this [...]
Predicting Failures of Vision Systems
Event Location: NSH 1507Abstract: This is a joint work with P. Zhang, J. Wang, A Farhadi, and D. Parikh. Computer vision systems today fail frequently. They also fail abruptly without warning or explanation. Alleviating the former has been the primary focus of the community. In this work, we hope to draw the community’s attention to [...]