A robust and modular multi-sensor fusion approach applied to MAV navigation

By Simon Lynen, Markus Achtelik, Stephan Weiss, Margarita Chli, Roland Yves Siegwart. 2013

565 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence

How researchers see this paper

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

In Aerospace Engineering

In Artificial Intelligence

Citations in the corpus

Survey on Computer Vision for UAVs: Current Developments and Trends (2017, methodology): “In this work a monocular approach uses only an onboard smartphone processor for semi direct visual odometry [54], multi sensor fusion [56] and a modified version of Regularized Modular Depth Estimation (REMODE) [57].”
Vision-based autonomous quadrotor landing on a moving platform (2017, methodology): “Pose estimates are computed at 40Hz and fused with measurements coming from an Inertial Measurement Unit (IMU) using an Extended Kalman Filter [21] at 200Hz.”
VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator (2017, methodology): “The simplest way to deal with visual and inertial measurements is loosely coupled sensor fusion [9], [10], where the IMU is treated as an independent module to assist the visual structure.”
A General Optimization-based Framework for Local Odometry Estimation with Multiple Sensors (2019, methodology): “A high-rate inertial sensor is used for state propagation and visual measurements are used for the update in [9, 16].”
Keyframe-based visual–inertial odometry using nonlinear optimization (2015, methodology): “Subsequently, a variety of filtering based approaches have been published based on EKFs (Kim and Sukkarieh, 2007; Mourikis and Roumeliotis, 2007; Li and Mourikis, 2012a; Weiss et al., 2012; Lynen et al., 2013), Iterated EKFs (IEKFs) (Strelow and Singh, 2004, 2003) and Unscented Kalman Filters (UKFs)”
A Benchmark Comparison of Monocular Visual-Inertial Odometry Algorithms for Flying Robots (2018, methodology): “A good compromise between these two extremes is ROVIO, which can provide better accuracy than SVO+MSF and much lower resource utilization than VINSMono.”
A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors (2019, methodology): “Also, the proposed system outperforms MSF [18].”
Receding Horizon "Next-Best-View" Planner for 3D Exploration (2016, methodology): “A point cloud of the environment is constructed from the stereo image for the environment mapping, while a visual–inertial odometry algorithm is used for pose estimation [28], [29].”
A survey on vision-based UAV navigation (2018, unknown): “Lynen et al. (2013) presented a general purpose multi-sensor fusion extended Kalman filter (MSF-EKF) that can handle different types of delayed measurement signals from multiple sensors, and provides a more accurate attitude estimation for UAV control and navigation.”
Visual-Inertial Navigation: A Concise Review (2019, background): “Speciﬁcally, the loosely-coupled fusion, in either ﬁltering or optimization-based estimation, processes the visual and inertial measurements separately to infer their own motion constraints and then fuse these constraints (e.g., [27, 87, 88, 89, 90, 91]).”
LINS: A Lidar-Inertial State Estimator for Robust and Efficient Navigation (2019, unknown): “, [11], [12]).”
Advanced closed loop visual navigation for micro aerial vehicles (2014, background): “Tightly coupled as well as loosely coupled approaches (see Section 3.3), fusing information from the IMU with optical flow to obtain a metric velocity, have been presented by Weiss et al. (2012b); Omari and Ducard (2013); Lynen et al. (2013b).”
Aggressive quadrotor flight through narrow gaps with onboard sensing and computing using active vision (2016, methodology): “Finally, we fuse the obtained pose with IMU measurements to provide a full state estimate using the multi-sensor fusion framework of [15].”
Robust state estimation for Micro Aerial Vehicles based on system dynamics (2015, methodology): “Based on earlier work by Lynen et al. [3], the indirect EKF formulation proposed in Roumeliotis et al. [15] was used and extended with the new aerodynamic model developed in IIA.”
GVINS: Tightly Coupled GNSS–Visual–Inertial Fusion for Smooth and Consistent State Estimation (2021, unknown): “In terms of loosely-coupled manner, [7] [8] describe state estimation systems which fuse GNSS solution with visual and inertial data under the EKF framework.”