Yoshitaka Fukuda

About

Yoshitaka Fukuda is a robotics researcher whose work centers on autonomous mobile robot perception, with a particular focus on LIDAR-based target classification. His key contributions lie in developing sensor fusion algorithms that combine LIDAR range data with reflection intensity to improve object identification in real-world, unstructured environments. In his most cited work, "Target object classification based on a fusion of LIDAR range and intensity data" (2014, 6 citations), Fukuda introduced a novel identification algorithm tailored for the Tsukuba Challenge 2013, a competitive autonomous navigation task. The challenge required robots to reliably detect a specific standing signboard while traversing a prescribed course—a deceptively difficult problem in outdoor settings. Fukuda’s approach leveraged the fusion of geometric and reflectance properties to achieve robust classification under varying conditions. His follow-up paper, "LIDAR based target object classification by using reflection intensity" (2014, 2 citations), further refined this method. Though his citation counts are modest, Fukuda’s work is notable for its practical, competition-driven innovation, directly addressing the gap between laboratory perception systems and the demands of field robotics. His research remains relevant for engineers developing cost-effective, real-time object recognition for autonomous vehicles and service robots.

Research Focus

Key Achievements

Top Papers

1. 1
   Target object classification based on a fusion of LIDAR range and intensity data

   6 citations · 2014
2. 2
   LIDAR based target object classification by using reflection intensity

   2 citations · 2014

Key Collaborators

Contact & Links