Multi-Representation Processing for Human-Robot Systems
Abstract
The goal of our research is to develop a general robotic agent architecture whose knowledge representations are neither purely probabilistic, and whose representations might change over time (perhaps as a result of learning or deliberative processes). The goal is to improve the performance of a robotic agent, allowing it to simultaneously benefit from the strengths of multiple representations. We are pursuing methodologies that lead to reliable, real-time, practical systems that can be deployed and evaluated on physical robots. When these goals are in conflict with optimality, we prefer satisficing. Further, we are interested in extensible systems, e.g. by learning in situ from a human mentor.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Feb 03, 2017
- Source ID
- N000141712217
Entities
People
- John E. Laird
Organizations
- Board of Regents of the University of Michigan
- Office of Naval Research
- United States Navy