Shayan Sepahvand

Toronto Metropolitan University, Shahid Beheshti University

Papers

Total Citations

H-Index

About

Shayan Sepahvand is a rising researcher at the intersection of robotics, control systems, and computer vision, with a focus on autonomous aerial and ground robots. His work centers on visual servoing—using visual feedback to control robot motion—and he has pioneered novel approaches that integrate neural networks with traditional control theory. In his 2024 paper, "Robust Image-based Visual Servoing of an Aerial Robot Using Self-organizing Neural Networks" (6 citations), Sepahvand demonstrated how self-organizing neural networks can enhance the robustness of drone control in dynamic environments. Building on this, his 2025 work, "Deep Visual Servoing of an Aerial Robot Using Keypoint Feature Extraction" (4 citations), introduces a deep-learning-based method using CNNs to extract keypoint features from monocular RGB camera data, enabling more precise and adaptive flight control. Earlier, his 2021 study on "Motion control of a caterpillar robot using optimized feedback linearization and sliding mode controllers" (3 citations) showcased his versatility in ground robotics. Though early in his career, Sepahvand’s integration of deep learning with classical control is a promising contribution to autonomous systems, with potential applications in inspection, surveillance, and search-and-rescue operations.