Neural extended Kalman filter for monocular SLAM in indoor environment

Miljković, Zoran; Vuković, Najdan; Mitić, Marko

doi:10.1177/0954406215586589

Cited by 9 publications

(5 citation statements)

References 22 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several other researchers have worked on various SLAM issues. For example, in [30][31][32], the authors presented a new architecture that applies one monocular SLAM system for the tracking of unconstraint motion of the mobile robot. The improved oriented FAST and rotated BRIEF (ORB) characteristics show the landmarks to design a network feature procedure of detection.…”

Section: Related Workmentioning

confidence: 99%

Simultaneous Localization and Mapping Based on Kalman Filter and Extended Kalman Filter

Ullah

Zhang

et al. 2020

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

For more than two decades, the issue of simultaneous localization and mapping (SLAM) has gained more attention from researchers and remains an influential topic in robotics. Currently, various algorithms of the mobile robot SLAM have been investigated. However, the probability-based mobile robot SLAM algorithm is often used in the unknown environment. In this paper, the authors proposed two main algorithms of localization. First is the linear Kalman Filter (KF) SLAM, which consists of five phases, such as (a) motionless robot with absolute measurement, (b) moving vehicle with absolute measurement, (c) motionless robot with relative measurement, (d) moving vehicle with relative measurement, and (e) moving vehicle with relative measurement while the robot location is not detected. The second localization algorithm is the SLAM with the Extended Kalman Filter (EKF). Finally, the proposed SLAM algorithms are tested by simulations to be efficient and viable. The simulation results show that the presented SLAM approaches can accurately locate the landmark and mobile robot.

show abstract

Section: Related Workmentioning

confidence: 99%

Simultaneous Localization and Mapping Based on Kalman Filter and Extended Kalman Filter

Ullah

Zhang

et al. 2020

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…However, studies like [33] predict absolute state vectors instead of vector increments using NN, which increases model complexity and requires a more extensive training process. Studies from [29,[32][33][34][35][36][37][38][39][40][41][42][43][44][45] adopted vector increments of the sensor observations and predictions during KF prediction, whilst most of the work only works on GNSS/INS navigation during GNSS outages, aiming for improving INS efficiency INS in urban settings and situations [31,38,39,41,42,46].…”

Section: Hybrid Fusion Enhanced By Aimentioning

confidence: 99%

“…The authors in [35,36] did not account for the temporal variations in features that can significantly impact the performance, given that basic neural networks are sensitive to such changes. Kotov et al [37] compared NNEKF-MPL and NNEKF-ELM, demonstrating that NNEKF-MPL performs better when the vehicle exhibits a non-constant systematic error.…”

Section: Hybrid Fusion Enhanced By Aimentioning

confidence: 99%

Integrating GRU with a Kalman Filter to Enhance Visual Inertial Odometry Performance in Complex Environments

Tabassum,

Xu,

Petrunin

et al. 2023

Aerospace

View full text Add to dashboard Cite

To enhance system reliability and mitigate the vulnerabilities of the Global Navigation Satellite Systems (GNSS), it is common to fuse the Inertial Measurement Unit (IMU) and visual sensors with the GNSS receiver in the navigation system design, effectively enabling compensations with absolute positions and reducing data gaps. To address the shortcomings of a traditional Kalman Filter (KF), such as sensor errors, an imperfect non-linear system model, and KF estimation errors, a GRU-aided ESKF architecture is proposed to enhance the positioning performance. This study conducts Failure Mode and Effect Analysis (FMEA) to prioritize and identify the potential faults in the urban environment, facilitating the design of improved fault-tolerant system architecture. The identified primary fault events are data association errors and navigation environment errors during fault conditions of feature mismatch, especially in the presence of multiple failure modes. A hybrid federated navigation system architecture is employed using a Gated Recurrent Unit (GRU) to predict state increments for updating the state vector in the Error Estate Kalman Filter (ESKF) measurement step. The proposed algorithm’s performance is evaluated in a simulation environment in MATLAB under multiple visually degraded conditions. Comparative results provide evidence that the GRU-aided ESKF outperforms standard ESKF and state-of-the-art solutions like VINS-Mono, End-to-End VIO, and Self-Supervised VIO, exhibiting accuracy improvement in complex environments in terms of root mean square errors (RMSEs) and maximum errors.

show abstract

“…[11][12][13] It is efficient and accurate in mobile robot path planning, especially after the central statistical framework of the robot simultaneous localization and mapping technique is introduced by Smith. [14][15][16][17] With the development of the legged robot, the information represented by grid maps is not enough to guide the motion planning. The height and physical characteristics of obstacles have many references 1 State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China 2 Beijing Institute of Control Engineering, Beijing, China in robots traversing terrains.…”

Section: Introductionmentioning

confidence: 99%

“…11–13 It is efficient and accurate in mobile robot path planning, especially after the central statistical framework of the robot simultaneous localization and mapping technique is introduced by Smith. 14–17 With the development of the legged robot, the information represented by grid maps is not enough to guide the motion planning. The height and physical characteristics of obstacles have many references in robots traversing terrains.…”

Section: Introductionmentioning

confidence: 99%

Plane-based grid map: A robot-centric mapping algorithm for wheel-legged rover motion planning in unstructured terrain environments

Zhu

Sun

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

Active suspension rover is gaining more and more attention. Among them, the wheel-legged rover has outstanding performance. In order to fully utilize the rover’s capabilities and improve the autonomy in planetary exploration, this paper addresses a plane-based grid (PBG) mapping method for its motion planning in unstructured terrain environments. First, the kinematics of the TAWL rover and each leg’s dynamic are presented to analyze the physical characteristics. Second, the PBG map is constructed based on the rover’s capabilities. It can be directly used during motion planning. This mapping framework utilizes a sensor model to predict whether the grid is occupied or free. Then, a plane cluster algorithm is proposed to classify grid cells, which incorporates two machine learning algorithms. Thus, the flat areas are clustered from the unstructured terrains. With the PBG map and the motion planning framework, the wheel-legged rover can simplify the motion planning process and better utilize the driving efficiency and the legs’ adaptability. Third, the proposed mapping algorithm is tested on a depth camera. Robotic experiments are carried out, demonstrating our framework which allows the rover to safely combine the wheeled motion with legged motion in autonomous navigation.

show abstract

Neural extended Kalman filter for monocular SLAM in indoor environment

Cited by 9 publications

References 22 publications

Simultaneous Localization and Mapping Based on Kalman Filter and Extended Kalman Filter

Simultaneous Localization and Mapping Based on Kalman Filter and Extended Kalman Filter

Integrating GRU with a Kalman Filter to Enhance Visual Inertial Odometry Performance in Complex Environments

Plane-based grid map: A robot-centric mapping algorithm for wheel-legged rover motion planning in unstructured terrain environments

Contact Info

Product

Resources

About