Affiliations: [a] Department of Aerospace and Mechanical Engineering, University of Southern California, Los Angeles, CA, USA | [b] Intelligent Systems Division, National Institute of Standards and Technology, Gaithersburg, MD, USA | [c] Department of Mechanical Engineering, Catholic University of America, Washington, DC, USA
Correspondence:
[*]
Corresponding author: Zeid Kootbally, Department of Aerospa- ce and Mechanical Engineering, University of Southern California, Los Angeles, CA, USA. E-mail: [email protected].
Abstract: For the most part, robots perform best in highly structured environments, where objects are in well-known, predictable locations. Another way to describe this is that robots are not considered agile. But, in order for them to be useful to small manufacturers and to also allow larger manufacturers to offer more automated customization of high volume parts, they need to be. In this paper, we describe various technologies that are being developed at the National Institute of Standards and Technology (NIST) in conjunction with outside organizations, such as IEEE, which can be used to enhance the agility of manufacturing robot systems. We validate these technologies using two industrially-relevant use cases. The first deals with task failure identification and recovery and the second deals with robot dynamic retasking. These use cases were successfully performed using a formal knowledge representation, a graph database, a perception system, a high-level and low-level planning system, as well as an overall architecture which brought all of the components together.
