A Review of Visual-Inertial Simultaneous Localization and Mapping from Filtering-Based and Optimization-Based Perspectives

Chen, Chang; Zhu, Hua; Li, Menggang; You, Shaoze

doi:10.3390/robotics7030045

Cited by 90 publications

(59 citation statements)

References 115 publications

(157 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also when a robot is turned on, it does not know its relative position to a previously created map (initial state problem). Other approaches include filter-based 38,39 sliding window estimators and dynamic Bayesian network for recursive state estimation. 13 Despite the fact that visual SLAM-based obstacle detection can in principle be performed using a single camera and IMUs, additional sensor may enhance its effectiveness.…”

Section: Visual Slammentioning

confidence: 99%

“…The environmental map in addition to the kinematic model (describing the motion or dynamics of the robot), together with the spatial coordinate system, and spatial occupancy models are used as input to control the robot when navigating, in particular during path planning and obstacle avoidance. The reader is referred to literature 38,35,[40][41][42][43] for more details on visual SLAM. A survey of visual navigation techniques for mobile robots is presented in Bonin-Font et al 44 The main issues in SLAM problems have also been reviewed in Cadena et al 3 These include coverage, multisession SLAM, computational complexity, and robustness.…”

Section: Visual Slammentioning

confidence: 99%

See 1 more Smart Citation

A review of algorithms and techniques for image-based recognition and inference in mobile robotic systems

Tawiah

2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Autonomous vehicles include driverless, self-driving and robotic cars, and other platforms capable of sensing and interacting with its environment and navigating without human help. On the other hand, semiautonomous vehicles achieve partial realization of autonomy with human intervention, for example, in driver-assisted vehicles. Autonomous vehicles first interact with their surrounding using mounted sensors. Typically, visual sensors are used to acquire images, and computer vision techniques, signal processing, machine learning, and other techniques are applied to acquire, process, and extract information. The control subsystem interprets sensory information to identify appropriate navigation path to its destination and action plan to carry out tasks. Feedbacks are also elicited from the environment to improve upon its behavior. To increase sensing accuracy, autonomous vehicles are equipped with many sensors [light detection and ranging (LiDARs), infrared, sonar, inertial measurement units, etc.], as well as communication subsystem. Autonomous vehicles face several challenges such as unknown environments, blind spots (unseen views), non-line-of-sight scenarios, poor performance of sensors due to weather conditions, sensor errors, false alarms, limited energy, limited computational resources, algorithmic complexity, human–machine communications, size, and weight constraints. To tackle these problems, several algorithmic approaches have been implemented covering design of sensors, processing, control, and navigation. The review seeks to provide up-to-date information on the requirements, algorithms, and main challenges in the use of machine vision–based techniques for navigation and control in autonomous vehicles. An application using land-based vehicle as an Internet of Thing-enabled platform for pedestrian detection and tracking is also presented.

show abstract

Section: Visual Slammentioning

confidence: 99%

Section: Visual Slammentioning

confidence: 99%

A review of algorithms and techniques for image-based recognition and inference in mobile robotic systems

Tawiah

2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…The stereo vision-based VIO/VISLAM is generally divided into two methodologies [10]: filtering-based (e.g., PIRVS [30], S-MSCKF [31] and Trifo-VIO [34]) and optimization-based (e.g., ICE-BA [33] and VINS-Fusion [35]). The comparison in [10], [37] found that the latter has more potential than the former in terms of localization accuracy, while the former has advantages in terms of computing cost. To balance the real-time requirements and accuracy, we propose a feedback mechanism that combines the filtering-based and optimization-based approaches into one VISLAM system.…”

Section: Most Existing Vio/vislam Approaches Focus On Monocularmentioning

confidence: 99%

“…However, the pure vision-based VO/VSLAM methods are sensitive to the challenging scenarios, such as textureless surfaces, motion blur, occlusions and illumination changes [6]- [9]. To address these problems, Visual Inertial Odometry (VIO) or Visual Inertial Simultaneous Localization and Mapping (VISLAM) techniques [10] fuse Inertial Measurement Unit (IMU) data to the VO/VSLAM system and achieve more robustness and higher accuracy even in the above challenging scenarios.…”

Section: Introductionmentioning

confidence: 99%

A Novel Feedback Mechanism-Based Stereo Visual-Inertial SLAM

Bai

Gao²,

Lin³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Simultaneous Localization and Mapping (SLAM) combining visual and inertial measurements has achieved significant attention in the community of Robotics and Computer Vision. However, it is still a challenge to balance real-time requirements and accuracy. Therefore, this paper proposes a feedback mechanism for stereo Visual-Inertial SLAM (VISLAM) to provide accurate and real-time motion estimation and map reconstruction. The key idea of the feedback mechanism is that the frontend and backend in the VISLAM system can promote each other. The results of the backend optimization are fed back to the Kalman Filter (KF)-based frontend to reduce the motion estimate error caused by the well-known linearization of the KF estimator. Conversely, this more accurate motion estimate of the frontend can accelerate the backend optimization since it provides a more accurate initial state for the backend. In addition, we design a relocalization and continued SLAM framework with the feedback mechanism for the application of autonomous robot navigation or continuing SLAM. We evaluated the performance of the proposed VISLAM system through experiments on public EuRoC dataset and real-world environments. The experimental results demonstrate that our system is a promising VISLAM system compared with other state-of-the-art VISLAM systems in terms of both computing cost and accuracy. INDEX TERMS Kalman filter, nonlinear optimization, visual and inertial sensor fusion, visual-inertial simultaneous localization and mapping.

show abstract

“…VINS-mono is a typical framework of VI-SLAM that fuses the camera and IMU data. VINS-mono is a realtime and standout optimization-based SLAM system that supports bias-correction, automatic estimator initialization, online extrinsic calibration, and loop detection [37].…”

Section: Introductionmentioning

confidence: 99%

A Continuous Positioning Algorithm Based on RTK and VI-SLAM With Smartphones

et al. 2020

View full text Add to dashboard Cite

The navigation technology has developed rapidly and immensely over the past few decades. Among the multiple navigation technologies, the representative and promising techniques are Real-time Kinematic (RTK) technique and Simultaneous Localization and Mapping (SLAM). RTK can provide realtime positioning results with high accuracy, while SLAM can not only locate the user but also construct a map of the new ambient. The first smartphone, the Xiaomi MI 8, equipped with the dual-frequency Global Navigation Satellite System (GNSS), hit the market in May 2018, providing valid carrier-phase measurements for RTK owe to the developer option of "Force full GNSS measurements." Nevertheless, RTK underperforms in urban areas as the buildings and trees can block the satellite signals. RTK cannot even provide positioning results when the GNSS outage happens. However, SLAM can effectively make up the drawbacks of RTK as it utilizes no more information than the images. SLAM can also be combined with the Inertial Measurement Unit (IMU) called Visual-Inertial SLAM (VI-SLAM,) with the improvement of accuracy and robustness. Therefore, our study mainly aims to confirm the feasibility of continuous positioning based on RTK and VI-SLAM with the Xiaomi MI 8. An application is developed to execute the functions, including logging images, measurements of IMU, and GPS measurements in Receiver INdependent EXchange (RINEX) format with the Xiaomi MI 8. The performances of RTK with and without the assistance of VI-SLAM are assessed respectively in the urban area. The experimental results demonstrate that the combination of RTK and VI-SLAM based on smartphones can effectively provide continuous positioning results. We believe our application will facilitate research and development in relation to positioning algorithms. Readers have access to this application at https://github.com/Nronaldo/CIGRLogger.

show abstract

A Review of Visual-Inertial Simultaneous Localization and Mapping from Filtering-Based and Optimization-Based Perspectives

Cited by 90 publications

References 115 publications

A review of algorithms and techniques for image-based recognition and inference in mobile robotic systems

A review of algorithms and techniques for image-based recognition and inference in mobile robotic systems

A Novel Feedback Mechanism-Based Stereo Visual-Inertial SLAM

A Continuous Positioning Algorithm Based on RTK and VI-SLAM With Smartphones

Contact Info

Product

Resources

About