Presenter: Maggie Wigness (DEVCOM Army Research Laboratory)

Abstract: Data-driven AI/ML techniques have advanced significantly to automate skills such as detection, target recognition, and mobility. Yet, there are many applications, including military operation or humanitarian assistance and disaster relief, where it is highly likely that the operating domain will depict some distributional shift from that in which a system was trained. Under these scenarios, the design of AI systems that dynamically adapt or that can be refined quickly, potentially in real-time, becomes critically important to ensure safety and success. I will discuss research on this topic that supports ground vehicle autonomous navigation and teaming, where we introduce new techniques that leverage human-guided ML, multi-modal representation learning, hierarchical learning, and reinforcement learning to support the need for adaptable intelligent systems.

Bio: Maggie Wigness is a Senior Computer Scientist at the U.S. Army Combat Capabilities Development Command (DEVCOM) Army Research Laboratory (ARL) in the Science for Intelligent Systems Division. While at ARL she has led technical innovations and strategically defined the research directions in many ARL collaborative research alliances (CRAs) focused on robotics, autonomy and AI/ML. Maggie’s current autonomy research efforts are in the cross section of computer vision and adaptive, online-learning from human demonstration to support mobility for ground vehicles in off-road and unstructured environments, and multi-agent teaming to support tactical maneuver. She helped enable the advancement of ML-based approaches to support off-road mobility by spearheading some of the initial large-scale off-road benchmark datasets that are used extensively by the greater robotics research community. Maggie earned her PhD in Computer Science from Colorado State University.