Autonomous, Vision‐based Flight and Live Dense 3D Mapping with a Quadrotor Micro Aerial Vehicle

By Matthias Faessler, Flavio Fontana, Christian Forster, Elias Mueggler, Matia Pizzoli, Davide Scaramuzza. 2016

241 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, 3D Vision & Pose, Robotics & Control

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 Computer Vision and Pattern Recognition

In 3D Vision & Pose

In Robotics & Control

Citations in the corpus

A General Framework for Uncertainty Estimation in Deep Learning (2019, methodology): “As proposed by previous work [37], we add to the linear and angular acceleration of the nominal model ṗ, ω̇ two compensations elin, eang .”
Deep Drone Racing: Learning Agile Flight in Dynamic Environments (2018, background): “Ground truth for this baseline is generated by the low-level controller in [6] while the drone is tracking the global reference trajectory under the assumption of accurate state estimation.”
Toward low-flying autonomous MAV trail navigation using deep neural networks for environmental awareness (2017, methodology): “[9] apply the SVO algorithm [10] to a downward-facing camera and IMU to build a map of the environment, which is then used for planning.”
A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots (2016, methodology): “Center, right: the standalone quadrotor with SVO and onboard processing [34].”
Crazyswarm: A large nano-quadcopter swarm (2017, methodology): “While vision-based methods are both accurate and decentralized [12], the required cameras and computers necessitate a much larger vehicle.”
A Benchmark Comparison of Monocular Visual-Inertial Odometry Algorithms for Flying Robots (2018, methodology): “The pose estimated from the vision-only SVO is provided to MSF as the output of a generic pose sensor, where it is then fused with the IMU data, as proposed in [7].”
Visual-Inertial Navigation Algorithm Development Using Photorealistic Camera Simulation in the Loop (2018, methodology): “A few custom platforms have also been built, typically augmented with an off-the-shelf autopilot board [7], [8].”
The current state and future outlook of rescue robotics (2019, background): “The rise of vision‐based flying robots has enabled many new applications for aerial platforms, which are no longer restricted to near‐hover flight in open outdoor areas to maintain global positioning system (GPS) control (Faessler et al., 2016).”