Matthew D. Schmill

Papers

Total Citations

118

H-Index

About

Matthew D. Schmill is a pioneering researcher in developmental robotics and autonomous learning systems, with a focus on enabling mobile robots to build internal models of their environments through direct experience. His work centers on three interconnected challenges: clustering sensorimotor experiences in ways that align with human judgment, learning planning operators in partially observable real-world settings, and identifying which contextual features are relevant to the effects of a robot’s actions. Schmill’s most influential contribution, “A Method for Clustering the Experiences of a Mobile Robot that Accords with Human Judgments” (2000), has garnered 75 citations and demonstrates how robots can autonomously segment their continuous experience into meaningful, human-comprehensible categories—a critical step toward truly autonomous agency. His follow-up work on learning planning operators (32 citations) and context-sensitive action effects (11 citations) further advances the theory that robots must develop their own understanding of action outcomes through exploration, rather than relying on pre-programmed models. Schmill’s research bridges machine learning, cognitive science, and robotics, offering foundational insights for building adaptive, self-improving autonomous systems.