Matthew Ejakov

Papers

Total Citations

H-Index

About

Matthew Ejakov is a robotics researcher specializing in safe motion planning and real-time obstacle avoidance for autonomous systems. His work bridges the gap between theoretical guarantees and practical deployment, focusing on algorithms that ensure robots can navigate unstructured environments without harming humans or damaging objects. Ejakov’s most cited paper, "Conformalized Reachable Sets for Obstacle Avoidance with Spheres" (2025), introduces a novel framework that combines conformal prediction with reachability analysis to generate provably safe, computationally efficient motion plans. This approach allows robots to adapt to sudden environmental changes while maintaining rigorous safety constraints—a critical advancement for applications in autonomous driving, warehouse logistics, and human-robot collaboration. With 3 citations in its first year, the work is gaining traction for its innovative use of statistical guarantees in motion planning. Ejakov’s research addresses a fundamental tension in robotics: the need for both real-time responsiveness and formal safety assurances. By developing algorithms that scale to complex, dynamic settings, he is helping to make autonomous robots more reliable and deployable in real-world scenarios where safety is paramount.