Maryam Kamgarpour
Papers
8
Total Citations
64
H-Index
4
About
Maryam Kamgarpour is a researcher whose work spans optimal control, safe planning under uncertainty, and multi-robot systems, with a growing focus on reinforcement learning and black-box optimization in safety-critical settings. Her foundational contribution in sequential linear quadratic optimal control introduced an efficient framework for solving nonlinear switched systems, a technically demanding class of problems that has drawn 28 citations and established her as a voice in hybrid dynamical systems. Building on this, Kamgarpour has made significant strides in safe mission planning for autonomous robots operating in stochastic, dynamically uncertain environments — developing scalable methods for multi-robot task allocation that balance mission objectives against probabilistic hazards, work that has collectively accumulated dozens of citations across several related publications. Her research on log barrier methods for safe black-box and non-convex optimization addresses the practical challenge of enforcing safety constraints when system dynamics are unknown, with applications in robotics and manufacturing. More recently, she has ventured into construction robotics, applying reinforcement learning to scaffold-free fabrication of spanning structures. Across her portfolio, Kamgarpour consistently bridges rigorous mathematical control theory with real-world autonomous systems applications, making her work relevant to both theorists and practitioners in robotics and artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1Sequential Linear Quadratic Optimal Control for Nonlinear Switched Systems28 citations · 2017
- 2
- 3Safe Mission Planning under Dynamical Uncertainties7 citations · 2020
- 4
- 5Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning4 citations · 2022
- 6
- 7
- 8Log Barriers for Safe Non-convex Black-box Optimization2 citations · 2019