Javad Heydari

Papers

Total Citations

H-Index

About

Javad Heydari is a researcher at the forefront of autonomous robotics, specializing in coverage path planning, reinforcement learning, and multi-robot systems. His work addresses the fundamental challenge of enabling robots to autonomously and efficiently cover unknown, dynamic environments—a critical capability for applications ranging from domestic cleaning to industrial inspection and search-and-rescue operations. Heydari’s major contributions include pioneering deep reinforcement learning-based algorithms that allow robots to make intelligent, real-time decisions without relying on pre-mapped environments. Notably, his 2021 paper, "Deep Reinforcement Learning Based Online Area Covering Autonomous Robot," has garnered 9 citations for its novel approach to integrating learning with online map building. Complementing this, his studies on reinforcement learning-based coverage path planning with implicit cellular decomposition (7 citations) and online area covering in unknown dynamic environments (7 citations) have provided robust frameworks for tackling the NP-hard nature of coverage problems. Heydari’s work is distinguished by its practical focus on overcoming the limitations of heuristic methods, offering scalable solutions that adapt to complex room geometries and obstacles. For students and researchers, his research represents a vital bridge between theoretical reinforcement learning and real-world robotic autonomy, pushing the boundaries of how machines perceive and navigate unstructured spaces.