Recurrent neural network and extended Kalman filter in SLAM problem

Kotov, K. Yu.; Maltsev, Alexandr S.; Sobolev, M. A.

doi:10.3182/20130902-3-cn-3020.00057

Cited by 8 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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. However, the aforementioned NN methods do not take temporal information contained within historical data into training, making those methods insufficient for addressing navigation applications' dynamic and time-dependent characteristics.…”

Section: Hybrid Fusion Enhanced By Aimentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Hybrid Fusion Enhanced By Aimentioning

confidence: 99%

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

show abstract

“…Bar-Shalom et al explored an iterative extend Kalman filter (IEKF) algorithm with the reduced state estimation bias and the increased running time (Bar-Shalom et al , 2004). Kotov et al studied a recurrent neural network (RNN)-based EKF-SLAM method, brought higher estimation accuracy with RNN modeling and compensating the systematic error (Kotov et al , 2013). Pei et al investigated a novel distributed EKF-SLAM system that combines the advantages of EKF-SLAM and distributed SLAM systems and developed a decorrelated distributed EKF to estimate the robot pose and landmarks (Pei et al , 2019).…”

Section: Introductionmentioning

confidence: 99%

A multi-innovation with forgetting factor based EKF-SLAM method for mobile robots

Zhou

Wang

2020

View full text Add to dashboard Cite

Purpose The purpose of this paper is to explore a multi-innovation with forgetting factor-based EKF-SLAM (FMI-EKF-SLAM) algorithm to solve the error increasing problem, caused by the Extended Kalman filtering (EKF) violating the local linear assumption in simultaneous localization and mapping (SLAM) for mobile robots because of strong nonlinearity. Design/methodology/approach A multi-innovation with forgetting factor-based EKF-SLAM (FMI-EKF-SLAM) algorithm is investigated. At each filtering step, the FMI-EKF-SLAM algorithm expands the single innovation at current step to an extended multi-innovation containing current and previous steps and introduces the forgetting factor to reduce the effect of old innovations. Findings The simulation results show that the explored FMI-EKF-SLAM method reduces the state estimation errors, obtains the ideal filtering effect and achieves higher accuracy in positioning and mapping. Originality/value The method proposed in this paper improves the positioning accuracy of SLAM and improves the EKF, so that the EKF has higher accuracy and wider application range.

show abstract

A review of Bayes filters with machine learning techniques and their applications

Kim,

Petrunin,

Shin

2025

Information Fusion

View full text Add to dashboard Cite

Recurrent neural network and extended Kalman filter in SLAM problem

Cited by 8 publications

References 5 publications

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

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

A multi-innovation with forgetting factor based EKF-SLAM method for mobile robots

A review of Bayes filters with machine learning techniques and their applications

Contact Info

Product

Resources

About