Jarad Cannon

University of New Hampshire at Manchester, University of New Hampshire

Papers

Total Citations

H-Index

About

Jarad Cannon is a researcher focused on advancing robot motion planning in dynamic, unpredictable environments. His work centers on developing real-time heuristic search algorithms that enable robots to navigate safely and efficiently when obstacles are moving and computational resources are limited. Cannon’s key contributions address a fundamental challenge: ensuring that motion planning decisions are made under strict real-time constraints without sacrificing robustness. His most-cited paper, “Real-Time Motion Planning with Dynamic Obstacles” (2021, 13 citations), proposes methods that allow robots to select high-speed actions while guaranteeing real-time performance—a critical capability for applications like autonomous driving, warehouse robotics, and search-and-rescue. Earlier foundational work, including his 2011 thesis and a 2014 conference paper, laid the groundwork by exploring heuristic search techniques for dynamic environments. Cannon’s research has been shaped by collaboration with Wheeler Ruml and Kevin Rose, reflecting a strong tradition of teamwork in algorithm development. With a total of 18 citations across his key publications, Cannon’s contributions are steadily gaining recognition in the robotics and AI communities, offering practical solutions for real-world autonomous systems.