RNIN-VIO: Robust Neural Inertial Navigation Aided Visual-Inertial Odometry in Challenging Scenes

Chen, Danpeng; Wang, Nan; Xu, Runsen; Xie, Weijian; Bao, Hujun

doi:10.1109/ismar52148.2021.00043

Cited by 31 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method significantly reduces yaw and position drift, and can output 6DoF poses at IMU frame rate. RNIN [19] designs a network structure combining ResNet and LSTM, where the ResNet module is used to learn the hidden state of human motion. In addition, LSTM is used to fuse the current hidden state with the previous hidden state to produce the best current motion state.…”

Section: Deep Learning Based Methodsmentioning

confidence: 99%

“…In order to get rid of the dependence on attitude information of smartphone API and obtain more accurate attitude information, in this paper, a novel deep learning based pedestrian indoor neural inertial network (dilated convolution network (DCN)-long short-term memory (LSTM)) is designed to estimate attitude, which does not rely on external information. Further, inspired by TLIO [18] and RNIN [19], we fuse estimated attitude with 3D relative displacements and the corresponding covariances from a ResNet34-based network by a invariant extended Kalman filter (IEKF) framework to obtain accurate global and local position estimation. The main contributions of this paper are as follows:…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural inertial navigation system on pedestrian

Huang

Gao

Liu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

The recent research shows that data-driven inertia navigation technology can significantly alleviate the drift error of Micro-Electro-Mechanical System Inertial Measurement Unit (MEMS-IMU) in pedestrian localization. However, most existing methods must rely on attitude information provided by external procedure (such as smartphone API), which violates the original intention of full autonomy of inertial navigation, and attitude information is also inaccurate. To address the problem, we propose a pedestrian indoor neural inertial navigation system that does not rely on external information and is only based on low-cost MEMS-IMU. First, a deep learning based neural inertial network was designed to estimate attitude. Then, in order to obtain position estimation with both global and local accuracy, an Invariant Extended Kalman Filter (IEKF) framework was proposed, where 3D displacement and its uncertainty regressed by a deep residual network are utilized to update IEKF. Extensive experimental results on a public dataset and a self-collected dataset show that the proposed method provides accurate attitude estimation and outperforms state-of-the-art methods in position estimation, demonstrating the superiority of our method in reliability and accuracy.

show abstract

Section: Deep Learning Based Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Neural inertial navigation system on pedestrian

Huang

Gao

Liu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…In order to fit the compensation force and fuse it into the EKF framework reasonably, a MSE loss function is replaced by a Negative log-likelihood (NLL) loss [20] after the former loss stabilizes and converges:…”

Section: Kinematic and Dynamic Network Designmentioning

confidence: 99%

DIDO: Deep Inertial Quadrotor Dynamical Odometry

Zhang¹,

Jiang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this work, we propose an interoceptive-only state estimation system for a quadrotor with deep neural network processing, where the quadrotor dynamics is considered as a perceptive supplement of the inertial kinematics. To improve the precision of multi-sensor fusion, we train cascaded networks on real-world quadrotor flight data to learn IMU kinematic properties, quadrotor dynamic characteristics, and motion states of the quadrotor along with their uncertainty information, respectively. This encoded information empowers us to address the issues of IMU bias stability, dynamic constraints, and multi-sensor calibration during sensor fusion. The above multi-source information is fused into a two-stage Extended Kalman Filter (EKF) framework for better estimation. Experiments have demonstrated the advantages of our proposed work over several conventional and learning-based methods.

show abstract

“…In order to further improve the performance of VIO, some newly VIO systems like [1] use pre-built high-precision maps to improve accuracy greatly. And some others like RNIN-VIO [7] take advantage of the neural network of IMU navigation to improve robustness.…”

Section: Vio and Slammentioning

confidence: 99%

RLP‐VIO: Robust and lightweight plane‐based visual‐inertial odometry for augmented reality

Zhou

Yang

et al. 2022

Computer Animation & Virtual

View full text Add to dashboard Cite

We propose RLP-VIO-a robust and lightweight monocular visual-inertial odometry system using multiplane priors. With planes extracted from the point cloud, visual-inertial-plane PnP uses the plane information for fast localization. Depth estimation is susceptible to degenerated motion, so the planes are expanded in a reprojection consensus-based way robust to depth errors.For sensor fusion, our sliding-window optimization uses a novel structureless plane-distance error cost, which prevents the fill-in effect that poisons the BA problem's sparsity and permits the use of a smaller sliding window while maintaining good accuracy. The total computational cost is further reduced with our modified marginalization strategy. To further improve the tracking robustness, the landmark depths are constrained using the planes during degenerated motion. The whole system is parallelized with a three-stage pipeline. Under controlled environments, this parallelization runs deterministically and produces consistent results. The resulting VIO system is tested on widely used datasets and compared with several state-of-the-art systems. Our system achieves competitive accuracy and works robustly even on long and challenging sequences.To demonstrate the effectiveness of the proposed system, we also show the AR application running on mobile devices in real-time.

show abstract

RNIN-VIO: Robust Neural Inertial Navigation Aided Visual-Inertial Odometry in Challenging Scenes

Cited by 31 publications

References 26 publications

Neural inertial navigation system on pedestrian

Neural inertial navigation system on pedestrian

DIDO: Deep Inertial Quadrotor Dynamical Odometry

RLP‐VIO: Robust and lightweight plane‐based visual‐inertial odometry for augmented reality

Contact Info

Product

Resources

About