Max Robotics — Global Service Robot Directory + US Certification

About

Jesse Butterfield’s research lies at the intersection of robotics, machine learning, and multi-agent systems, with a focus on enabling robots to learn from human demonstration and coordinate autonomously. In his most-cited work (41 citations), he tackled the challenge of learning control policies from human teleoperation data, introducing a multi-valued function regressor for time-series data that addresses the inherent ambiguity of mapping perception to action—a critical step toward more intuitive human-robot interaction. Butterfield also made significant contributions to multi-robot coordination, proposing Markov random fields as a unifying probabilistic framework for distributed action selection (9 citations) and developing methods for autonomous biconnected network formation (14 citations) to ensure robust communication among robot teams. His work on modeling theory of mind with Markov random fields (34 citations) further demonstrates his innovative approach to capturing social cognition in artificial systems. Additionally, his research on player positioning in the Four-Legged League (5 citations) highlights his practical contributions to robotic soccer. With a career spanning foundational theory and applied robotics, Butterfield’s work has shaped how robots learn from humans and collaborate in dynamic environments.