Vision based MAV navigation in unknown and unstructured environments

By Michael Blösch, Stephan Weiss, Davide Scaramuzza, Roland Yves Siegwart. IEEE International Conference on Robotics and Automation, 2010

505 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/715cc8506d44f3328c0319ce1b5357406ecac90f

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

Citations in the corpus

Autonomous landing of a VTOL UAV on a moving platform using image-based visual servoing (2012, background): “Common isolated vision tasks include target tracking ([5] and [6]) and simultaneous localization and mapping (SLAM, [7]).”
Vision-based autonomous mapping and exploration using a quadrotor MAV (2012, background): “Markerless computer vision control based on a single downward-looking camera with wide-angle lens has been demonstrated for landing, takeoff, and hovering and small-scale mapping in [1], [5].”
PIXHAWK: A system for autonomous flight using onboard computer vision (2011, background): “The work of [2] et al.”
Differential flatness based control of a rotorcraft for aggressive maneuvers (2011, background): “INTRODUCTION Simple rotorcraft are becoming increasingly utilized for aerial robotics research [15], [8], [16], [1], [7], [3].”
Vision-based control of a quadrotor for perching on lines (2014, methodology): “Advanced processing power and progress in visual odometry algorithms facilitated the GPS-free vision based navigation of MAVs [4].”
PIXHAWK: A micro aerial vehicle design for autonomous flight using onboard computer vision (2012, methodology): “This allows them to run a modified version of the visual SLAM of [4] on-board with a frame rate of 10Hz.”
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning (2018, background): “Traditional navigation methods typically perform planning on a given map of the environment or build a map as the exploration proceeds [26, 40, 21, 24, 9, 4].”
Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods (2019, background): “• Vision-and-Language Navigation is one such task which can be seen as a transition from standard vision based navigation using only visual input (Sinopoli et al., 2001; Blösch et al., 2010) or natural language instruction based navigation (MacMahon et al.”
Benchmarking Classic and Learned Navigation in Complex 3D Environments (2019, background): “Classic navigation pipelines have been deployed on a variety of robotic platforms, including wheeled [41], legged [20], and aerial [4].”
Camera-based navigation of a low-cost quadrocopter (2012, unknown): “Two videos demonstrating the robustness of our approach, its ability to eliminate drift effectively and to estimate the absolute scale of the map are available online: http://youtu.be/tZxlDly7lno http://youtu.be/eznMokFQmpc”
Learning high-speed flight in the wild (2021, background): “Some works tackle only perception and build high-quality maps from imperfect measurements [5–9], whereas others focus on planning without considering perception errors [10–13].”
Graph-Based Classification of Omnidirectional Images (2017, background): “Omnidirectional cameras are very attractive for various applications in robotics [1, 2] and computer vision [3, 4] thanks to their wide viewing angle.”
SVO: Fast semi-direct monocular visual odometry (2014, methodology): “Most monocular VO algorithms for MAVs [1], [2], [7] rely on PTAM [16].”
Visual-Inertial Navigation Algorithm Development Using Photorealistic Camera Simulation in the Loop (2018, methodology): “Early implementations [6], [26], [27] focused on extending the full SLAM system of Klein and Murray (PTAM) [28] to work on aerial vehicles.”
Vision based navigation for micro helicopters (2012, background): “Whereas state-of-the-art uses off-board processing and/or artificial landmarks for vision based micro helicopter pose control, we showed such control on-board, in real-time and in a previously unknown environment (Bloesch et al. (2010)).”
Toward a Fully Autonomous UAV: Research Platform for Indoor and Outdoor Urban Search and Rescue (2012, background): “Current approaches, which try to tackle this kind of challenge, use a laser scanner [5] or monocular vision [9].”
Visual Odometry and Mapping for Autonomous Flight Using an RGB-D Camera (2011, background): “For smaller MAVs operating in indoor environments, a number of researchers have used monocular camera sensors to control MAVs [36, 2, 5, 8].”
Onboard IMU and monocular vision based control for MAVs in unknown in- and outdoor environments (2011, background): “to the best of our knowledge, the first vision based solution for completely autonomous flights in unknown and GPS denied environments [2].”
A survey of quadrotor Unmanned Aerial Vehicles (2012, methodology): “Monocular systems (single camera) use a single downward facing onboard camera as in [13].”