Raoul Dinaux

Papers

Total Citations

H-Index

About

Raoul Dinaux is a robotics researcher specializing in autonomous navigation for micro air vehicles (MAVs), with a focus on visual-based obstacle detection and avoidance. His work addresses a critical challenge in aerial robotics: enabling drones to navigate safely in complex, real-world environments where traditional algorithms falter. Dinaux’s most cited paper, "FAITH: Fast Iterative Half-Plane Focus of Expansion Estimation Using Optic Flow" (2021, 13 citations), introduces a novel method for course estimation that leverages optic flow, offering a robust alternative to texture-dependent approaches. This work is foundational for developing autonomous navigation systems that can operate in low-texture or dynamic settings. Complementing this, his 2022 paper, "A Novel Obstacle Detection and Avoidance Dataset for Drones" (9 citations), provides the ODA Dataset—a collection of raw sensor data from real indoor flights using an MAV equipped with forward-facing sensors. This resource is invaluable for benchmarking and advancing obstacle avoidance algorithms. Dinaux’s contributions bridge theory and practice, offering both algorithmic innovations and open datasets that accelerate research in aerial robotics. His work is particularly relevant for students and engineers building resilient, vision-based autonomous drones.