The Robotics Institute
 Search the site
RI | People | Gita Sukthankar

Text only version of this site

Gita Sukthankar
PhD Student

No longer a member of RI.

For more information, see my personal homepage.

Jump to: Research interests | Labs & Groups | Projects | Publications

Research interests

My research is in the area of multi-agent plan recognition; currently I am working on the problem of recognizing tactical plans from spatio-temporal traces of military teams in urban settings. My thesis addresses the novel problem of recovering agent-to-team assignment for team tasks where team composition, the mapping of agents into teams, changes over time. I have also done research on the problem of recognizing human physical behaviors from motion capture traces, improving planning fidelity by modeling the physical capabilities of agents, and developing visualizations for live action gaming.

Past Labs & Groups

Intelligent Software Agents - Here, researchers explore multi-agent planning and scheduling, multi-agent learning, multi-agent negotiation, and decision support for human teams
 

Past Projects

AFOSR PRET: Information Fusion for Command and Control: The Translation of Raw Data To Actionable Knowledge and Decision - We are conducting a multidisciplinary research effort to develop the next generation of information fusion systems.
Agent Storm - Agent Storm is a scenario where agents autonomously coordinate their team-oriented roles and actions while executing a mission.
Agent-based Composition of Behavioral Models - This project focuses on accurately modeling human physical behaviors; these models are used 1) to create computer generated forces (CGFs) that exhibit human-like behavior and 2) to recognize physical behaviors performed by trainees in a MOUT (Military Operations in Urban Terrain) team training simulation.
Aircraft Maintenance - A wearable software system that uses RETSINA agents to assist in the process of documenting and making repairs to aircraft.
IBM ITA: Human-Agent Teamwork Models - We are developing models of human-agent teamwork for implementation in software agent systems.
Reusable Environment for Task Structured Intelligent Network Agents - 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

Recent publications [View all 24 publications]

The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.
For updates and comments, please see these instructions.
This page maintained by robotwebmaster@ri.cmu.edu