Autonomy Artificial Intelligence Robotics (AAIR)

Implementing Robotic Control Algorithms in Open Source and Government Virtual Environments

by Philip Frederick; Mike Del Rose; David Pirozzo; Robert Kania; Bernard Theisen; Stephanie Roth


There are an increasing number of simulation tools either available today or coming online for ground vehicle autonomous behavior modeling. Engineers in TARDECs Ground Vehicle Robotics (GVR) area have dedicated a significant portion of effort over the past four plus years reviewing, implementing and promoting the development these tools. This paper provides an overview of these efforts and discusses the current state of these virtual environments from the perspective of TARDEC robotic researchers, developers, engineers and program managers. We specifically touch on experiences implementing control algorithms in Player/Stage, ANVEL and MODSIM/RIDE. While we take specific measures to avoid comparative analysis we provide our insight into the current strengths and limitations of these systems as it relates to utilization on research efforts, a quick development/integration program (Dismounted Soldier Autonomy Tools) and a JCTD effort (AMAS). We also give an overview of other known autonomy M&S systems and their stated status/attributes as well as discuss what we believe would be necessary for these tools to mature to the point where they can eventually serve to reduce costs associated with autonomous vehicle development and testing.