UAV-Aided High-Accuracy Relative Localization of Ground Vehicles

2018 ◽  
Author(s):  
Yuanpeng Liu ◽  
Yuan Shen
Keyword(s):  
High Accuracy ◽  
Ground Vehicles ◽  
Relative Localization

scholarly journals COORDINATED USE OF VISUAL ODOMETRY AND LANDMARKS FOR NAVIGATION OF MOBILE GROUND VEHICLES

2021 ◽  
Vol XLIV-2/W1-2021 ◽  
pp. 201-205
Author(s):  
S. M. Sokolov ◽  
N. D. Beklemishev ◽  
A. A. Boguslavsky
Keyword(s):  
Vision System ◽  
High Accuracy ◽  
Information Support ◽  
Navigation Systems ◽  
Ground Vehicles ◽  
Visual Data ◽  
Visual Channel ◽  
Navigation Problem ◽  
Forward Looking

Abstract. The paper considers two directions in the use of visual data for information support of purposeful movements of ground vehicles. This is optical odometry and navigation by landmarks in the environment. Optical odometry builds the trajectory of movement of the vehicle based on the determination of displacements based on selective visual data from different fields of view. The choice and indication of landmarks at the described stage of research remains with the operator. The vision system (VS) monitors the specified landmarks and determines the position of the vehicle relative to them. The experiments used such fields of view as monocular forward looking, panoramic (fisheye type) and forward looking stereo system. When combining the data of the visual channel with each other and with the data of other navigation systems, the specificity of visual sensors is taken into account – a significant effect of the reliability and accuracy of the results from the observation conditions. Experimental verification of the VS layout showed the achievability of high accuracy in solving the navigation problem using the visual channel. All the components of the described process of organizing purposeful movements based on the use of the visual channel continue to be improved.

Online Terrain Classification for Mobile Robots

2005 ◽  
Author(s):  
Edmond M. DuPont ◽  
Rodney G. Roberts ◽  
Majura F. Selekwa ◽  
Carl A. Moore ◽  
Emmanual G. Collins
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Autonomous Vehicles ◽  
Probabilistic Neural Network ◽  
Detection Algorithm ◽  
High Accuracy ◽  
Vibration Frequencies ◽  
Terrain Classification ◽  
Ground Vehicles ◽  
Human Driver

Today’s autonomous vehicles operate in an increasingly general set of circumstances. In particular, unmanned ground vehicles (UGV’s) must be able to travel on whatever terrain the mission offers, including sand, mud, or even snow. These terrains can affect the performance and controllability of the vehicle. Like a human driver who feels his vehicle’s response to the terrain and takes appropriate steps to compensate, a UGV that can autonomously perceive its terrain can also make necessary changes to its control strategy. This article focuses on the development and application of a terrain detection algorithm based on terrain induced vehicle vibration. The dominant vibration frequencies are extracted and used by a probabilistic neural network to identify the terrain. Experimental results based on iRobot’s ATRV Jr (Fig. 1) demonstrate that the algorithm is able to identify with high accuracy multi-differentiated terrains broadly classified as sand, grass, asphalt, and gravel.

scholarly journals DeepLabV3+/Efficientnet Hybrid Network-Based Scene Area Judgment for the Mars Unmanned Vehicle System

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 8136
Author(s):  
Shuang Hu ◽  
Jin Liu ◽  
Zhiwei Kang
Keyword(s):  
High Accuracy ◽  
Experimental Results ◽  
Hybrid Network ◽  
Ground Vehicles ◽  
Mars Exploration ◽  
Unmanned Vehicle ◽  
Vehicle System ◽  
Safe Area ◽  
Feature Information ◽  
Exploration Mission

Due to the complexity and danger of Mars’s environment, traditional Mars unmanned ground vehicles cannot efficiently perform Mars exploration missions. To solve this problem, the DeepLabV3+/Efficientnet hybrid network is proposed and applied to the scene area judgment for the Mars unmanned vehicle system. Firstly, DeepLabV3+ is used to extract the feature information of the Mars image due to its high accuracy. Then, the feature information is used as the input for Efficientnet, and the categories of scene areas are obtained, including safe area, report area, and dangerous area. Finally, according to three categories, the Mars unmanned vehicle system performs three operations: pass, report, and send. Experimental results show the effectiveness of the DeepLabV3+/Efficientnet hybrid network in the scene area judgment. Compared with the Efficientnet network, the accuracy of the DeepLabV3+/Efficientnet hybrid network is improved by approximately 18% and reaches 99.84%, which ensures the safety of the exploration mission for the Mars unmanned vehicle system.

A New 1,000 kV Electron Microscope

1967 ◽  
Vol 25 ◽  
pp. 260-261
Author(s):  
M. Nishigaki ◽  
S. Katagiri ◽  
H. Kimura ◽  
B. Tadano
Keyword(s):  
Electron Microscope ◽  
High Voltage ◽  
Basic Research ◽  
Chromatic Aberration ◽  
High Accuracy ◽  
Biological Specimen ◽  
Voltage Electron ◽  
High Voltage Electron Microscope ◽  
High Voltage Electron

The high voltage electron microscope has many advantageous features in comparison with the ordinary electron microscope. They are a higher penetrating efficiency of the electron, low chromatic aberration, high accuracy of the selected area diffraction and so on. Thus, the high voltage electron microscope becomes an indispensable instrument for the metallurgical, polymer and biological specimen studies. The application of the instrument involves today not only basic research but routine survey in the various fields. Particularly for the latter purpose, the performance, maintenance and reliability of the microscope should be same as those of commercial ones. The authors completed a 500 kV electron microscope in 1964 and a 1,000 kV one in 1966 taking these points into consideration. The construction of our 1,000 kV electron microscope is described below.

Application Of BIM-Technology In The Restoration Of Buildings

2020 ◽  
pp. 42-48
Keyword(s):  
Chinese Communist Party ◽  
Laser Scanning ◽  
High Accuracy ◽  
Information Environment ◽  
Information Modeling ◽  
Structural Scheme ◽  
Traditional Design ◽  
Information Interaction ◽  
Heritage Buildings ◽  
Effective Organization

The paper describes the main trends in the development of BIM technologies in the field of restoration and reconstruction of historical and cultural heritage buildings. The practical part of the paper presents the experience in using information modeling technologies when restoring the building, where the VI Congress of the Chinese Communist Party in Moscow took place. The use of laser scanning technologies made it possible to reproduce with high accuracy in the information model the original appearance of the building using Autodesk RevitR software. It is shown, how the use of information modeling technologies affects the duration of restoration process, taking into account the calculation of the structural scheme and bearing structures of the building, ensuring the identity of the decoration and the effective organization of electromechanical installation. Operating in a single BIM information environment makes it possible to continuously obtain reliable information on the project, which provides more effective information interaction and communication of participants compared to using traditional design methods.

Sign in / Sign up

Export Citation Format

Share Document