Keyframe-Based Visual-Inertial SLAM using Nonlinear Optimization

Leutenegger, Stefan; Furgale, Paul; Rabaud, Vincent; Chli, Margarita; Konolige, Kurt; Siegwart, Roland

doi:10.15607/rss.2013.ix.037

Cited by 339 publications

(261 citation statements)

References 17 publications

(21 reference statements)

Supporting

Mentioning

261

Contrasting

Order By: Relevance

“…Since the sensor was designed to perform real-time visualinertial SLAM, we applied our framework [5] to an outdoor dataset. In short, the method is inspired by recent advances purely vision-based SLAM that solve a sparse nonlinear least-squares problem.…”

Section: Visual-inertial Motion Estimationmentioning

confidence: 99%

See 1 more Smart Citation

A synchronized visual-inertial sensor system with FPGA pre-processing for accurate real-time SLAM

Nikolic

Rehder

Burri

et al. 2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

230

153

View full text Add to dashboard Cite

Abstract-Robust, accurate pose estimation and mapping at real-time in six dimensions is a primary need of mobile robots, in particular flying Micro Aerial Vehicles (MAVs), which still perform their impressive maneuvers mostly in controlled environments. This work presents a visual-inertial sensor unit aimed at effortless deployment on robots in order to equip them with robust real-time Simultaneous Localization and Mapping (SLAM) capabilities, and to facilitate research on this important topic at a low entry barrier.Up to four cameras are interfaced through a modern ARM-FPGA system, along with an Inertial Measurement Unit (IMU) providing high-quality rate gyro and accelerometer measurements, calibrated and hardware-synchronized with the images. This facilitates a tight fusion of visual and inertial cues that leads to a level of robustness and accuracy which is difficult to achieve with purely visual SLAM systems. In addition to raw data, the sensor head provides FPGA-pre-processed data such as visual keypoints, reducing the computational complexity of SLAM algorithms significantly and enabling employment on resource-constrained platforms.Sensor selection, hardware and firmware design, as well as intrinsic and extrinsic calibration are addressed in this work. Results from a tightly coupled reference visual-inertial SLAM framework demonstrate the capabilities of the presented system.

show abstract

Section: Visual-inertial Motion Estimationmentioning

confidence: 99%

“…The sensor head evolved through the development of several prototypes and was tested in many applications, for instance in a coal fired power plant [4] or on a car [5]. Fig.…”

Section: Introductionmentioning

confidence: 99%

A synchronized visual-inertial sensor system with FPGA pre-processing for accurate real-time SLAM

Nikolic

Rehder

Burri

et al. 2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

230

153

View full text Add to dashboard Cite

show abstract

“…This approach requires a number of reference nodes (anchor nodes or landmarks) deployed at fixed locations as well as one or more mobile nodes (receiver). Another approach is to combine the information provided by Inertial Measurement Unit (IMU) and aiding sensors such as cameras (monocular, stereo and RGB-D) and LiDAR sensors (Leutenegger, 2013;Veth, 2011).…”

Section: Indoor Positioning and Mappingmentioning

confidence: 99%

Towards a Fast, Low-Cost Indoor Mapping and Positioning System For Civil Protection and Emergency Teams

Angelats

Navarro

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Civil protection and emergency teams work usually under very risky conditions that endanger their lives. One of the factors contributing to such risks is the lack of knowledge about their physical environment, especially when working indoors. Mapping and location indoor and outdoor technologies exist; for outdoors, very good levels of precision and accuracy may be obtained using offthe-shelf equipment; on the other side, and although good solutions for indoor environments are available, these require some extra pre-deployed infrastructure in the area to navigate, which is unacceptable in the case of emergency teams. It may be said, then, that no mature indoor + outdoor integrated solution providing the appropriate precision and accuracy for the purposes of emergency teams exist. In this paper, the assessment of a set of currently available sensors (IMUs, RGB-D cameras, GNSS receivers) and algorithms is presented to show that it is already possible to build such a solution relying on them -providing that appropriate (indoor) lightning and texture conditions exist.

show abstract

“…The visual inertial odometry (VIO) literature is vast, including approaches based on filtering [14][15][16][17][18][19], fixed-lag smoothing [20][21][22][23][24], full smoothing [25][26][27][28][29][30][31][32]. The algorithms considered here are related to IMU preintegration models [30][31][32][33].…”

Section: Introductionmentioning

confidence: 99%

Visual-Inertial Odometry on Chip: An Algorithm-and-Hardware Co-design Approach

Zhang

Suleiman

Carlone

et al. 2017

Robotics: Science and Systems XIII

View full text Add to dashboard Cite

Abstract-Autonomous navigation of miniaturized robots (e.g., nano/pico aerial vehicles) is currently a grand challenge for robotics research, due to the need for processing a large amount of sensor data (e.g., camera frames) with limited on-board computational resources. In this paper we focus on the design of a visual-inertial odometry (VIO) system in which the robot estimates its ego-motion (and a landmark-based map) from onboard camera and IMU data. We argue that scaling down VIO to miniaturized platforms (without sacrificing performance) requires a paradigm shift in the design of perception algorithms, and we advocate a co-design approach in which algorithmic and hardware design choices are tightly coupled. Our contribution is four-fold. First, we discuss the VIO co-design problem, in which one tries to attain a desired resource-performance trade-off, by making suitable design choices (in terms of hardware, algorithms, implementation, and parameters). Second, we characterize the design space, by discussing how a relevant set of design choices affects the resource-performance trade-off in VIO. Third, we provide a systematic experiment-driven way to explore the design space, towards a design that meets the desired trade-off. Fourth, we demonstrate the result of the co-design process by providing a VIO implementation on specialized hardware and showing that such implementation has the same accuracy and speed of a desktop implementation, while requiring a fraction of the power.

show abstract

Keyframe-Based Visual-Inertial SLAM using Nonlinear Optimization

Cited by 339 publications

References 17 publications

A synchronized visual-inertial sensor system with FPGA pre-processing for accurate real-time SLAM

A synchronized visual-inertial sensor system with FPGA pre-processing for accurate real-time SLAM

Towards a Fast, Low-Cost Indoor Mapping and Positioning System For Civil Protection and Emergency Teams

Visual-Inertial Odometry on Chip: An Algorithm-and-Hardware Co-design Approach

Contact Info

Product

Resources

About