Max Robotics — Global Service Robot Directory + US Certification

About

Benjamin Gravell’s research lies at the intersection of robust control, stochastic optimization, and autonomous robotics, with a particular focus on ensuring safety and performance under uncertainty. His major contributions include pioneering work on risk-averse motion planning for nonlinear robotic systems, where he developed the Risk-Averse Nonlinear Steering RRT* (RANS-RRT*) algorithm—a planner that explicitly accounts for state estimation and control uncertainties through nonlinear programming and statistical approximations. Gravell also advanced the theoretical foundations of learning-based control by extending policy iteration to linear quadratic games with stochastic parameters, bridging adversarial training and domain randomization with classical control theory. His work on integrated perception and control for nonlinear robots has been recognized for addressing critical gaps in robust autonomy, tackling non-Gaussian uncertainties often ignored in practice. With over 69 citations across his most-cited papers, Gravell’s research has directly influenced safe robot navigation in uncertain environments. Additionally, his concurrent goal assignment and collision-free trajectory generation methods for multi-aerial robot systems have practical implications for swarm robotics and logistics. Gravell’s contributions are essential reading for researchers seeking to merge learning, control, and planning for reliable autonomous systems.