Human-in-the-Loop Distributed Simulation and Validation of Strategic Autonomous Algorithms
Christopher W. Lum, Matthew Rowland, Rolf T. Rysdyk · 2008
The goal of most current Unmanned Air Vehicle (UAV) research is to develop algorithms which allow a single agent or possibly a team of agents to operate completely autonomously without human interaction. Most of these autonomous algorithms operate at a high, strategic level and assume that low level tasks such as state stabilization and signal tracking have already been realized. The di‐culty in verifying and validating strategic algorithms in an actual ∞ight test is that implementing these algorithms require the development of many other lower-level subsystems which are not directly related to the strategic algorithms. This paper presents both an architecture and hardware implementation of a ground based, distributed testing environment that is used in the Autonomous Flight System Laboratory to test strategic level algorithms in an e‐cient manner. This system allows human interaction at very speciflc points to avoid developing a fully autonomous system, but still preserves the function and contributions of the strategic algorithm. This architecture and ground based testing facility greatly reduces development time and allows algorithms to be tested with little approximations before implementing them on a fully autonomous system.