Mathew Monfort

University of Illinois Chicago, Massachusetts Institute of Technology

Papers

Total Citations

H-Index

About

Mathew Monfort is a leading researcher in robotics and human-robot interaction, specializing in intent prediction, trajectory forecasting, and inverse optimal control. His work addresses the critical challenge of enabling robots to not only recognize current human actions but also infer future intentions and behaviors, a key step toward seamless human-robot collaboration. Monfort’s most cited paper, “Intent Prediction and Trajectory Forecasting via Predictive Inverse Linear-Quadratic Regulation” (2015, 44 citations), introduces a framework that leverages depth camera data to predict human motion and goals, significantly improving robot anticipation in dynamic environments. He further advances teleoperation systems in “Goal-predictive robotic teleoperation from noisy sensors” (2017, 20 citations), tackling the practical limitations of low-cost depth cameras and sensor calibration to enhance intuitive control. In “Graph-based inverse optimal control for robot manipulation” (2015, 18 citations), Monfort extends inverse optimal control to complex manipulation tasks, learning cost functions from demonstrations even when optimal control is only approximate. His cumulative impact—over 80 citations across these works—underscores his contributions to making robots more adaptive and responsive. Monfort’s research is vital for students and engineers developing assistive robotics, autonomous systems, and human-aware AI.