Using perception cues for context-aware navigation in dynamic outdoor environments

Continued advancements in robot autonomy have allowed the research community to shift from using robots as tools in the field to deploying robot teammates capable of learning, reasoning, and executing tasks. Autonomous navigation is one necessary capability of a robot teammate that must operate in large field environments. In relatively static environments a simple navigation solution such as obstacle avoidance along the shortest path may suffice; however, as robot teammates are deployed to highly dynamic environments with changing mission requirements, additional environment context may be necessary to ensure safe and reliable navigation. Although recent works in urban autonomous driving have advanced the state-of-the-art in context-aware decision making, the spectrum of behaviors deployed for context-switching is more narrowly focused (by defining constraints specific to operation in structured environments) than what might be required for human-agent teaming field missions. As such, establishing a context-aware intelligent system for dynamic, unstructured environments is still an open problem. We discuss our approach to the integration of several context-aware navigation behaviors on a small unmanned ground vehicle (UGV) and a perception stack that provides cues used to transition between these different learned behaviors. Specifically, we integrate socially compliant, terrain-aware, and covert behaviors in an outdoor navigation scenario where the UGV encounters moving pedestrians, different terrains, and weapon threats. We provide a detailed account of the overall system integration, experiment design, component- and system-level analysis, and lessons learned.