Learn More
We report on empirical results in extreme extraction. It is extreme in that (1) from receipt of the ontology specifying the target concepts and relations, development is limited to one week and that (2) relatively little training data is assumed. We are able to surpass human recall and achieve an F1 of 0.51 on a question-answering task with less than 50(More)
Robot Urban Search and Rescue is a new task in robotics that is challenging not only robot hardware, but also human-robot interfaces. It is a real-world challenge in an unstruc-tured environment that requires cooperation between a remote robot and a human operator. The study of human-robot interfaces is still in its infancy, and most of the urban search &(More)
Ambulance crashes are a significant risk to prehospital care providers, the patients they are carrying, persons in other vehicles, and pedestrians. No uniform national transportation or medical database captures all ambulance crashes in the United States. A website captures many significant ambulance crashes by collecting reports in the popular media (the(More)
Rune, the Robot-User Nexus, is the culmination of two years of software development work for the Swarthmore Robotics Team. The two goals of this ongoing project are to create a robust and extensible software architecture for mobile robots, and to create an intuitive, flexible, and extensible interface for mobile robot teleoperation. This report describes a(More)
Provenance research has generally focused on issues with data collection and organization. Most approaches represent stored provenance data as a directed acyclic graph (DAG), where objects such as files and processes are nodes in the graph and directed edges specify ancestry relationships between them. While there has been some work addressing logical(More)
  • 1