Indoor Visual Semantic SLAM Improves VIO and RGBD for Narrow Space Navigation

Andrés Solares Jurado, Germán Andrés Di Fonzo, Rafael Pérez, Hriday Bavle, Miguel Fernández-Cortizas, Javier Rodríguez Vázquez, Guillermo Robledo, Pascual Campoy
November, 2021
PDF Cite Source Document

Abstract

A lightweight semantic SLAM approach for aerial robots operating in narrow, GNSS-denied environments. The system combines visual odometry or visual-inertial odometry with high-level object detections from an OAK-D RGB-D sensor.

Type
Conference paper
Publication
12th International Micro Air Vehicle Conference (IMAV), 196–203
Robotics SLAM Computer Vision
Javier Rodríguez Vázquez
Javier Rodríguez Vázquez
Principal Researcher

Principal Researcher in Artificial Intelligence working on generalizable autonomy, embodied AI, adaptive agents, planning, memory, and robot learning.