Real-time monocular dense mapping on aerial robots using visual-inertial fusion

Yang, Zhenfei; Gao, Fei; Shen, Shaojie

doi:10.1109/icra.2017.7989529

Cited by 60 publications

(34 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because our proposed method directly operates on point clouds raw data without map maintenance, the proposed motion planning is naturally plug‐in‐and‐use on many other platforms, which produce point clouds. In fact, we have already applied our previous method from F. Gao and Shen () to a vision‐based quadrotor (Yang et al, ) and ground vehicle (C. Shen, Zhang, Li, Gao, & Shen, ) in various types of applications. In the future, we are going to implement our proposed method, which is an advance on our previous method, on other platforms and applications.…”

Section: Discussionmentioning

confidence: 99%

“…A point cloud, which is an underlying representation of the environment, does not need a discretization of the configuration space or complicated maintenance. It is essentially an unordered set of three-dimensional (3D) raw data, which can be obtained by many sensors, such as by camera in Yang, Gao, and Shen (2017) and by light detection and ranging (LiDAR) in Zhang and Singh (2018). The choice of planning directly on point clouds bypasses the costly map building and maintenance process and achieves the best adaptivity to different sensors in different environments, which is one of the critical requirements for search-and-rescue missions in hazardous scenes.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Flying on point clouds: Online trajectory generation and autonomous navigation for quadrotors in cluttered environments

Gao

et al. 2018

Journal of Field Robotics

Self Cite

136

View full text Add to dashboard Cite

Micro aerial vehicles (MAVs), especially quadrotors, have been widely used in field applications, such as disaster response, field surveillance, and search‐and‐rescue. For accomplishing such missions in challenging environments, the capability of navigating with full autonomy while avoiding unexpected obstacles is the most crucial requirement. In this paper, we present a framework for online generating safe and dynamically feasible trajectories directly on the point cloud, which is the lowest‐level representation of range measurements and is applicable to different sensor types. We develop a quadrotor platform equipped with a three‐dimensional (3D) light detection and ranging (LiDAR) and an inertial measurement unit (IMU) for simultaneously estimating states of the vehicle and building point cloud maps of the environment. Based on the incrementally registered point clouds, we online generate and refine a flight corridor, which represents the free space that the trajectory of the quadrotor should lie in. We represent the trajectory as piecewise Bézier curves by using the Bernstein polynomial basis and formulate the trajectory generation problem as a convex program. By using Bézier curves, we can constrain the position and kinodynamics of the trajectory entirely within the flight corridor and given physical limits. The proposed approach is implemented to run onboard in real‐time and is integrated into an autonomous quadrotor platform. We demonstrate fully autonomous quadrotor flights in unknown, complex environments to validate the proposed method.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Flying on point clouds: Online trajectory generation and autonomous navigation for quadrotors in cluttered environments

Gao

et al. 2018

Journal of Field Robotics

Self Cite

136

View full text Add to dashboard Cite

show abstract

“…This reconstruction is the backbone for safe and efficient navigation around obstacles. The method used in this work in the continuation of our preliminary results . We use temporal cost aggregation from multiple images from the monocular to eliminate baseline limitation.…”

Section: Monocular Dense Mappingmentioning

confidence: 99%

“…In our previous work, the keyframe was selected by the VINS framework automatically. However, there exist two limitations: …”

Section: Monocular Dense Mappingmentioning

confidence: 99%

See 1 more Smart Citation

Autonomous aerial navigation using monocular visual‐inertial fusion

Lin

Gao

Qin

et al. 2017

Journal of Field Robotics

Self Cite

198

166

View full text Add to dashboard Cite

Autonomous micro aerial vehicles (MAVs) have cost and mobility benefits, making them ideal robotic platforms for applications including aerial photography, surveillance, and search and rescue. As the platform scales down, MAVs become more capable of operating in confined environments, but it also introduces significant size and payload constraints. A monocular visual-inertial navigation system (VINS), consisting only of an inertial measurement unit (IMU) and a camera, becomes the most suitable sensor suite in this case, thanks to its light weight and small footprint.In fact, it is the minimum sensor suite allowing autonomous flight with sufficient environmental awareness. In this paper, we show that it is possible to achieve reliable online autonomous navigation using monocular VINS. Our system is built on a customized quadrotor testbed equipped with a fisheye camera, a low-cost IMU, and heterogeneous onboard computing resources. The backbone of our system is a highly accurate optimization-based monocular visual-inertial state estimator with online initialization and self-extrinsic calibration. An onboard GPU-based monocular dense mapping module that conditions on the estimated pose provides wide-angle situational awareness. Finally, an online trajectory planner that operates directly on the incrementally built threedimensional map guarantees safe navigation through cluttered environments. Extensive experimental results are provided to validate individual system modules as well as the overall performance in both indoor and outdoor environments.

show abstract

A marker-based method for visual-inertial initialization

An,

Fan,

Dong

2024

Intell. Mar. Technol. Syst.

View full text Add to dashboard Cite

Accurate and robust initialization is significant for visual-inertial simultaneous localization and mapping (VI-SLAM). Existing methods solve VI-SLAM initialization based on visual information. However inertial measurement unit (IMU) parameter estimation performed underwater is subject to two major limitations. First, IMU preintegration error accumulates over time, resulting in reduced accuracy. Second, it is difficult for robots to achieve sufficient movement underwater, which affects the reliability of initialization results. For a better balance between the efficiency and accuracy of VI-SLAM initialization, this study proposes a VI-SLAM initialization method using a designed marker calibration device. First, we utilize both marker points and ORB feature points for a fast and robust visual trajectory estimation with real motion scale, and we estimate the gravity direction using the marker calibration device. Second, the IMU trajectory is aligned with the trajectory, and the IMU parameters are solved using the initial gravity direction. Experiments verify the effectiveness of our developed method for improving the accuracy and efficiency of the VI-SLAM initialization. The code is available at https://gitee.com/litseaak/mmorb.

show abstract

Real-time monocular dense mapping on aerial robots using visual-inertial fusion

Cited by 60 publications

References 22 publications

Flying on point clouds: Online trajectory generation and autonomous navigation for quadrotors in cluttered environments

Flying on point clouds: Online trajectory generation and autonomous navigation for quadrotors in cluttered environments

Autonomous aerial navigation using monocular visual‐inertial fusion

A marker-based method for visual-inertial initialization

Contact Info

Product

Resources

About