Emmanuel Antonio

Papers

Total Citations

H-Index

About

Emmanuel Antonio’s research centers on motion planning for nonholonomic and kinodynamic robotic systems, with a focus on achieving optimality under complex constraints. His major contributions include advancing sampling-based planners like RRT* and SST, particularly by analyzing local planners for dynamical systems to ensure asymptotic global optimality with compound cost functionals. In his most cited work (2021, 15 citations), he formally characterized length-optimal trajectories under nonholonomic metrics, demonstrating how local planners can be reused for diverse cost functions—a key insight for efficient, real-time planning. Another notable study (2021, 4 citations) examined the SST planner’s efficiency in generating time-optimal trajectories for differential drive robots under second-order dynamics and obstacles, highlighting the role of extremal control inputs. Antonio’s work bridges theoretical rigor and practical robotics, offering formal guarantees for planners that must balance speed, energy, or safety. His research is especially valuable for autonomous vehicles, mobile manipulation, and any system where dynamics and obstacles demand near-optimal, real-time solutions. By tackling the reuse of planning components and the integration of nonholonomic constraints, Antonio is shaping more intelligent, adaptable motion planning for next-generation robots.