Agents of Exploration and Discovery
Abstract
Autonomous agents have many applications in familiar situations, but they also have great potential to help us understand novel settings. In this paper, we propose a new challenge for the research community: developing embodied systems that not only explore new environments but that also acquire scientific knowledge characterizing them. Illustrative examples include autonomous rovers on planetary surfaces and unmanned vehicles on undersea missions. We review two relevant paradigms: robotic agents that explore unknown areas and computational systems that discover scientific models. In each case, we specify the problem, identify component functions, cite prior work, and note current limitations. Finally, we discuss obstacles the community must overcome before it can develop integrated agents of exploration and discovery.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2021
- Accession Number
- AD1200692
Entities
People
- Brian A. Haugh
- Patrick W. Langley
Organizations
- Institute for Defense Analyses