Integrated Mission Specification and Task Allocation for Robot Teams - Part 2: Testing and Evaluation
Author(s) -
Patrick Ulam,
Yochiro Endo,
Alan R. Wagner,
Ronald C. Arkin
Publication year - 2006
Publication title -
smartech repository (georgia institute of technology)
Language(s) - English
Resource type - Reports
DOI - 10.21236/ada457295
Subject(s) - task (project management) , robot , computer science , human–computer interaction , software engineering , systems engineering , engineering , artificial intelligence
: This work presents the evaluation of two mission specification and task allocation architectures. These architectures, described in part 1 of this paper, present novel means with which to integrate a case-based reasoning (CBR) mission planner with contract net protocol (CNP) based task allocation. In the first design, the CBR and runtime-CNP architecture, the case-based mission planner generates mission plans that support necessary behaviors for CNP-based task allocation and execution. In the second design, the CBR and premission-CNP architecture, task allocation takes place during mission specification. The results of an empirical evaluation of the CBR and runtime-CNP across three naval scenarios is described. Finally, we briefly describe an earlier usability evaluation of the CBR and premission-CNP architecture using goals, operators, methods, and selection rules modeling.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom