Development of GPU-accelerated localization system for autonomous mobile robot; Mechanical Engineering, Automation and Control Systems (MEACS)

Bibliographic Details
Parent link:Mechanical Engineering, Automation and Control Systems (MEACS).— 2014.— [4 p.]
Main Author: Rud M. N.
Other Authors: Pantiykchin A. R.
Summary:Title screen
We present a localization system for autonomous mobile robot, that operates in conditions of well - known environment. In our work we use particle - based Monte - Carlo localization. This algorithm has many applications in mobile robotics, but it is computationally expensive. Due to high level of parallelism in this algorithm, we had an opportunity to accelerate its execution on graphical processing unit (GPU) using CUDA - parallel computing architecture from NVIDIA Corporation. We use Microsoft Kinect sensor and robot odometry to perform indoor localization. Developed system was tested on three-wheeled mobile robot. NVIDIA Jetson TK1 board performed all necessary computations.
Режим доступа: по договору с организацией-держателем ресурса
Language:English
Published: 2014
Subjects:
Online Access:http://dx.doi.org/10.1109/MEACS.2014.6986850
Format: Electronic Book Chapter
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=638968

MARC

LEADER 00000nla2a2200000 4500
001 638968
005 20231101134035.0
035 |a (RuTPU)RU\TPU\network\3365 
035 |a RU\TPU\network\3358 
090 |a 638968 
100 |a 20150217a2014 k y0engy50 ba 
101 0 |a eng 
105 |a a z 101zy 
135 |a drcn ---uucaa 
181 0 |a i  
182 0 |a b 
200 1 |a Development of GPU-accelerated localization system for autonomous mobile robot  |f M. N. Rud, A. R. Pantiykchin 
203 |a Text  |c electronic 
300 |a Title screen 
320 |a [References: 5 tit.] 
330 |a We present a localization system for autonomous mobile robot, that operates in conditions of well - known environment. In our work we use particle - based Monte - Carlo localization. This algorithm has many applications in mobile robotics, but it is computationally expensive. Due to high level of parallelism in this algorithm, we had an opportunity to accelerate its execution on graphical processing unit (GPU) using CUDA - parallel computing architecture from NVIDIA Corporation. We use Microsoft Kinect sensor and robot odometry to perform indoor localization. Developed system was tested on three-wheeled mobile robot. NVIDIA Jetson TK1 board performed all necessary computations. 
333 |a Режим доступа: по договору с организацией-держателем ресурса 
463 0 |0 (RuTPU)RU\TPU\network\3200  |t Mechanical Engineering, Automation and Control Systems (MEACS)  |o proceedings of the International Conference, Tomsk, 16-18 October, 2014  |f National Research Tomsk Polytechnic University (TPU) ; Institute of Electrical and Electronics Engineers (IEEE)  |v [4 p.]  |d 2014 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
610 1 |a mobile robot 
610 1 |a Monte-Carlo localization 
610 1 |a GPU acceleration 
610 1 |a CUDA 
610 1 |a Kinect 
610 1 |a NVIDIA Jetson TKl 
610 1 |a мобильные роботы 
610 1 |a локализация 
610 1 |a робототехника 
610 1 |a графические процессоры 
610 1 |a параллельные вычисления 
700 1 |a Rud  |b M. N. 
701 1 |a Pantiykchin  |b A. R. 
801 2 |a RU  |b 63413507  |c 20161226  |g RCR 
856 4 |u http://dx.doi.org/10.1109/MEACS.2014.6986850 
942 |c CF