6-Dof EKF SLAM with Global Planar Features in Artificial Environments
Symposium on System Integration (SII)(2020)
Abstract
This paper presents online SLAM for self-localization of mobile robots in artificial environments. This proposed method exploits global planar features as landmarks in extended Kalman filter (EKF). The main purpose of using global planer features is reducing accumulative error of the estimation. Planes are extracted from point cloud of 3-D LiDAR as normals. These normals are projected onto “depth-Gaussian sphere” Those points from each plane are concentrated in one place on the sphere since planes has many normals which are almost same directions. These concentrations of points are deemed as planar features. The state vector of EKF has states of both a robot and landmarks. Prediction steps compute integration of angular velocity from gyroscope and linear velocity from wheel encoders, respectively. Observation steps update the states by associating observed planes and landmark planes. Area of landmark planes are also expanded with every association. Observed planes which are not associated with any landmarks become new landmarks, and the state vector is augmented. Similar landmarks are merged as necessary. To avoid mismatching between observations and landmarks, candidates for the association are selected by some conditions. To evaluate the proposed method, an experiment with an actual robot was performed. It shows the method suppresses accumulative error of self-localization by using the landmarks.
MoreTranslated text
Key words
6-DoF EKF SLAM,global planar features,artificial environments,online SLAM,mobile robot self-localization,extended Kalman filter,point cloud,depth-Gaussian sphere,EKF state vector,observed planes,landmark planes,accumulative error reduction,global planer feature extraction,3D LiDAR,angular velocity integration,gyroscope,inear velocity,wheel encoders,accumulative error suppression
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example

Generate MRT to find the research sequence of this paper
Related Papers
2022 IEEE/SICE International Symposium on System Integration (SII) 2022
被引用1
JOURNAL OF SENSORS 2023
被引用1
DNN Based Camera Attitude Estimation Using Aggregated Information from Camera and Depth Images
2023 IEEE/SICE INTERNATIONAL SYMPOSIUM ON SYSTEM INTEGRATION, SII 2023
被引用0
Design and Implementation of Intelligent Visual Sweep Robot Based on Basra Development Board
Journal of Hunan Institute of Engineering(Natural Science Edition) 2023
被引用0
A Visual SLAM with Tightly-Coupled Integration of Multi-Object Tracking for Production Workshop
IEEE INTERNET OF THINGS JOURNAL 2024
被引用0
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
GPU is busy, summary generation fails
Rerequest