RGB–D terrain perception and dense mapping for legged robots
This paper addresses the issues of unstructured terrain modeling for the purpose of navigation with legged robots. We present an improved elevation grid concept adopted to the specific requirements of a small legged robot with limited perceptual capabilities. We propose an extension of the elevation...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Sciendo
2016-03-01
|
Series: | International Journal of Applied Mathematics and Computer Science |
Subjects: | |
Online Access: | https://doi.org/10.1515/amcs-2016-0006 |
id |
doaj-a671491be8024ece8bb7e5a3933c7c0f |
---|---|
record_format |
Article |
spelling |
doaj-a671491be8024ece8bb7e5a3933c7c0f2021-09-06T19:39:49ZengSciendoInternational Journal of Applied Mathematics and Computer Science2083-84922016-03-01261819710.1515/amcs-2016-0006amcs-2016-0006RGB–D terrain perception and dense mapping for legged robotsBelter Dominik0Łabecki Przemysław1Fankhauser Péter2Siegwart Roland3Institute of Control and Information Engineering, Poznań University of Technology, ul. Piotrowo 3A, 60-965 Poznań, PolandInstitute of Control and Information Engineering, Poznań University of Technology, ul. Piotrowo 3A, 60-965 Poznań, PolandAutonomous Systems Lab, ETH Zurich, LEE J 201, Leonhardstrasse 21, 8092 Zurich, SwitzerlandAutonomous Systems Lab, ETH Zurich, LEE J 201, Leonhardstrasse 21, 8092 Zurich, SwitzerlandThis paper addresses the issues of unstructured terrain modeling for the purpose of navigation with legged robots. We present an improved elevation grid concept adopted to the specific requirements of a small legged robot with limited perceptual capabilities. We propose an extension of the elevation grid update mechanism by incorporating a formal treatment of the spatial uncertainty. Moreover, this paper presents uncertainty models for a structured light RGB-D sensor and a stereo vision camera used to produce a dense depth map. The model for the uncertainty of the stereo vision camera is based on uncertainty propagation from calibration, through undistortion and rectification algorithms, allowing calculation of the uncertainty of measured 3D point coordinates. The proposed uncertainty models were used for the construction of a terrain elevation map using the Videre Design STOC stereo vision camera and Kinect-like range sensors. We provide experimental verification of the proposed mapping method, and a comparison with another recently published terrain mapping method for walking robots.https://doi.org/10.1515/amcs-2016-0006rgb-d perceptionelevation mappinguncertaintylegged robots |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Belter Dominik Łabecki Przemysław Fankhauser Péter Siegwart Roland |
spellingShingle |
Belter Dominik Łabecki Przemysław Fankhauser Péter Siegwart Roland RGB–D terrain perception and dense mapping for legged robots International Journal of Applied Mathematics and Computer Science rgb-d perception elevation mapping uncertainty legged robots |
author_facet |
Belter Dominik Łabecki Przemysław Fankhauser Péter Siegwart Roland |
author_sort |
Belter Dominik |
title |
RGB–D terrain perception and dense mapping for legged robots |
title_short |
RGB–D terrain perception and dense mapping for legged robots |
title_full |
RGB–D terrain perception and dense mapping for legged robots |
title_fullStr |
RGB–D terrain perception and dense mapping for legged robots |
title_full_unstemmed |
RGB–D terrain perception and dense mapping for legged robots |
title_sort |
rgb–d terrain perception and dense mapping for legged robots |
publisher |
Sciendo |
series |
International Journal of Applied Mathematics and Computer Science |
issn |
2083-8492 |
publishDate |
2016-03-01 |
description |
This paper addresses the issues of unstructured terrain modeling for the purpose of navigation with legged robots. We present an improved elevation grid concept adopted to the specific requirements of a small legged robot with limited perceptual capabilities. We propose an extension of the elevation grid update mechanism by incorporating a formal treatment of the spatial uncertainty. Moreover, this paper presents uncertainty models for a structured light RGB-D sensor and a stereo vision camera used to produce a dense depth map. The model for the uncertainty of the stereo vision camera is based on uncertainty propagation from calibration, through undistortion and rectification algorithms, allowing calculation of the uncertainty of measured 3D point coordinates. The proposed uncertainty models were used for the construction of a terrain elevation map using the Videre Design STOC stereo vision camera and Kinect-like range sensors. We provide experimental verification of the proposed mapping method, and a comparison with another recently published terrain mapping method for walking robots. |
topic |
rgb-d perception elevation mapping uncertainty legged robots |
url |
https://doi.org/10.1515/amcs-2016-0006 |
work_keys_str_mv |
AT belterdominik rgbdterrainperceptionanddensemappingforleggedrobots AT łabeckiprzemysław rgbdterrainperceptionanddensemappingforleggedrobots AT fankhauserpeter rgbdterrainperceptionanddensemappingforleggedrobots AT siegwartroland rgbdterrainperceptionanddensemappingforleggedrobots |
_version_ |
1717770004403847168 |