Visual-Inertial Navigation Algorithm Development Using Photorealistic Camera Simulation in the Loop

By Thomas Sayre-Mccord, Winter Guerra, Amado Antonini, Jasper Arneberg, Austin Brown, Guilherme Venturelli Cavalheiro, Yajun Fang, A. Gorodetsky, Dave McCoy, Sebastian Quilter and 5 more. 2018

30 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Drone Racing: Learning Agile Flight in Dynamic Environments (2018, background): “For the specific case of drone racing, this entails the capability to look for the target (the next gate) and localize relative to this while maintaining visual contact with it [7, 28].”
Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping (2019, methodology): “…accuracy of the metric-semantic reconstruction from Kimera-Semantics, we use a photo-realistic Unity-based simulator provided by MIT Lincoln Lab, that provides sensor streams (in ROS) and ground truth for both the geometry and the semantics of the scene, and has an interface similar to [20], [21].”
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, methodology): “uHumans and uHumans2 are generated using a photorealistic Unity-based simulator provided by MIT Lincoln Laboratory, that provides sensor streams (in ROS) and ground truth for both the geometry and the semantics of the scene, and has an interface similar to (Sayre-McCord et al. 2018; Guerra et al. 20”
Synthetic Data for Deep Learning (2019, methodology): “, using feedback from visual sensors in order to maintain position, stability, and perform maneuvers; here synthetic data has usually been used in the form of hardware-in-the-loop simulators for the developed controllers [348], sometimes augmented with full-scale flight simulators [336] or specially”