Carnegie Mellon University
Advanced Search   
  Look in
       Title     Description
       Inactive Projects
Current Projects, Grouped by Subject
Artificial Intelligence
Autonomous Navigation System (ANS)
The NREC is leading the development of perception and path planning within the Autonomous Navigation System program for the Future Combat System.
Forecasting the Anterior Cruciate Ligament Rupture Patterns
Use of machine learning techniques to predict the injury pattern of the Anterior Cruciate Ligament (ACL) using non-invasive methods.
Formal Verification of Autonomous Systems
We are developing tools and techniques to support formal verification of autonomous systems.

Hot Flash Detection
Machine learning algorithms to detect hot flashes in women using physiological measures.
Human-Robot Interaction
The human-robot interaction project explores aspects of social interaction between people and robots, in particular how robots should be designed to provide people with appropriate interactions.
Indoor People Localization
Tracking multiple people in indoor environments with the connectivity of Bluetooth devices.
Informedia Digital Video Library
Informedia Digital Video Library - Informedia is pioneering new approaches for automated video and audio indexing, navigation, visualization, summarization search, and retrieval and embedding them in systems for use in education, health care, defense intelligence and understanding of human activity.
Language for Advertisement and Request for Knowledge Sharing (LARKS)
A common agent capability description language (ACDL) for matching service-requesting software agents with service-providing software agents.
Learning Locomotion
Robust planning and control of the quadruped robot "Little Dog" to traverse rough terrain (DARPA sponsored).
Mars Autonomy
Long-distance marsrover navigation with minimal human intervention.
A middle agent that facilitates conections among agents that provide services and agents that request services.
Supply chain management
Modeling by Videotape (MBV)
Factorization method of solving the structure-from-motion problem
Multimodal Diaries
Summarization of daily activity from multimodal data (audio, video, body sensors and computer monitoring)
Navigation Among Movable Obstacles (NAMO)
Autonomous motion planning and control for robots working in reconfigurable environments.
PerceptOR (NRECPerceptOR)
NREC designed, developed and tested an innovative autonomous perception and navigation system for the DARPA PerceptOR program.
Planning for Manipulation
Developing algorithms for autonomous manipulation.
A project aimed at developing methods for automating negotiation among agents and implementing effective machine learning techniques.
Project LISTEN's Reading Tutor
Project LISTEN's Reading Tutor listens to children read aloud.
Reusable Environment for Task Structured Intelligent Network Agents (RETSINA)
An architecture for developing distributed intelligent software agents that cooperate asynchronously to perform goal-directed information retrieval and information integration in support of a varie
Robotic Soccer (RoboSoccer)
The RoboSoccer project develops collaboration among multiple autonomous agents.
Robust Autonomy

Social Robots
We are developing robots with personality.
Spatio-Temporal Facial Expression Segmentation
A two-step approach temporally segment facial gestures from video sequences. It can register the rigid and non-rigid motion of the face.
Very Rough Terrain Nonholonomic Trajectory Generation and Motion Planning for Rovers
We are developing rough terrain trajectory generation algorithms for local path planning and optimal regional motion planning methods using a constrained search space.
The WARREN system is a multi-agent application that is designed to help users monitor and manage their financial portfolio.
A personal agent for World-Wide Web browsing that enhances searches and learns user interests.
Weld Sequence Planning
Many manufacturing processes require considerable setup time and offer a large potential for schedule compression. For example, Pratt&Miller Inc. constructed a military spec HMMWV welded spaceframe with best-practice methods, this took 89 billable hours — cutting square tubes, preparing them for welding, and then performing the final welding tasks to build the structure. On analysis, we discovered that the time actually spent on constructive processes was only 3% (slightly over two hours) of that total. Thus 97% of the overall time can potentially be eliminated. We built a system to exploit this opportunity that includes a welding robot, an augmented reality projection system and a laser displacement sensor. To test the system, we fabricated a custom variant of a HMMWV welded spaced frame where pre-process tasks were automated: BOM acquisition, component preparation, sequence planning, weld parameter optimization, fixture planning, workpiece localization and finally automated work assignments were delegated to a robot and a person. In the end, we were able to make the custom welded product nearly 9x faster than was previously possible. This achievement also translates economically to the bottom line because the cost of raw materials was only 6% of the total costs. This talk will highlight the technical achievements that made this possible.