PhD Thesis Defense
Abhinav Shrivastava
Carnegie Mellon University

Discovering and Leveraging Visual Structure for Large-scale Recognition

GHC 8102

Abstract: Our visual world is extraordinarily varied and complex, but despite its richness, the space of visual data may not be that astronomically large. We live in a well-structured, predictable world, where cars almost always drive on roads, sky is always above the ground, and so on. As humans, the ability to learn this structure [...]

PhD Thesis Defense
Venkatraman Narayanan
Carnegie Mellon University

Deliberative Perception

Newell-Simon Hall 3305

Abstract: A recurrent and elementary robot perception task is to identify and localize objects of interest in the physical world. In many real-world situations such as in automated warehouses and assembly lines, this task entails localizing specific object instances with known 3D models. Most modern-day methods for the 3D multi-object localization task employ scene-to-model feature [...]

PhD Thesis Defense
Robotics Institute,
Carnegie Mellon University

Compact Generative Models of Point Cloud Data for 3D Perception

Newell-Simon Hall 3305

Abstract: One of the most fundamental tasks for any robotics application is the ability to adequately assimilate and respond to incoming sensor data. In the case of 3D range sensing, modern-day sensors generate massive quantities of point cloud data that strain available computational resources. Dealing with large quantities of unevenly sampled 3D point data is [...]

PhD Thesis Defense
Robotics Institute,
Carnegie Mellon University

Mathematical Models of Adaptation in Human-Robot Collaboration

Newell Simon Hall 1507

Abstract: While much work in human-robot interaction has focused on leader- follower teamwork models, the recent advancement of robotic systems that have access to vast amounts of information suggests the need for robots that take into account the quality of the human decision making and actively guide people towards better ways of doing their task. [...]

PhD Thesis Proposal
Robotics Institute,
Carnegie Mellon University

Learning to learn from simulation: Using simulations to expedite learning on robots

GHC 8102

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 [...]

PhD Thesis Defense
Robotics Institute,
Carnegie Mellon University

Training Strategies for Time Series: Learning for Prediction, Filtering, and Reinforcement Learning

Newell-Simon Hall 3305

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, [...]

PhD Speaking Qualifier
Robotics Institute,
Carnegie Mellon University

Expressive Real-time Intersection Scheduling

Newell Simon Hall 1507

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 [...]