Challenges and Opportunities for Resilient Collective Intelligence in Subterranean Environments

Abstract: Resilient intelligent systems adapt, introspect, and evolve to changing robot and environment models and application objectives. Collective resilient intelligence exploits learned models from multiple systems (robot or human) to yield more efficient strategies than single systems. Subterranean environments present unique challenges and considerations to developing robust, real-time navigation, control and autonomy for robotic systems due to the complexity of some domains (e.g., caves) and the repetitive nature of others (e.g., mines).

The goal of this workshop is to discuss the challenges and opportunities of operating in subterranean environments such as mines and caves to achieve safe and stable autonomy of single- and multi-robot systems by exploiting online learning and adaptation within the feedback loop. The workshop brings together experts to present recent advancements in the areas of perception, planning, control, and learning and provide rich discussion for the implications of these methods for safe, autonomous operations in challenging subterranean environments. Academic and industry researchers studying the topical areas of active perception, human-robot interaction, and multi-robot coordination will discuss the fundamental challenges and opportunities that arise in the pursuit of resilient collective intelligence in these domains.

The workshop will consist of topical presentations and a panel discussion by a cross-disciplinary group of experts with the goal of highlighting the challenges that arise when applying techniques from online learning and adaptation (at the levels of planning, perception, and control) in highly variable and unstructured subterranean environments such as mines and caves. Discussions will explore the performance implications of operating in these domains and identify areas for future work to enable more effective and resilient collective operations. A poster session will highlight recent research advancements.