Abstract
This paper presents the depth image based locomotion strategy selection framework for a hybrid mobile robot. Terrain recognizer is a major component of a supervisory controller which classifies depth images into terrain types in real-time and selects different locomotion mode sub-controllers. In order to design the terrain recognizer, a database consisting of five terrain types (uneven, level ground, stair up, stair down and not traversable) is generated. Confidence based filtering is applied to enhance depth image data. The accuracy of the terrain classification for the testing database in five class terrain recognition problem is 96.71%. Real-world experiments conducted in mixed terrain environment evaluate both locomotion and terrain recognition capabilities of the robot in real-time. Experimental results show that a consumer depth camera might serve as an effective instrument for terrain recognition and thus locomotion strategy selection for hybrid robots with multiple locomotion modes.
| Original language | English |
|---|---|
| Title of host publication | IEEE International Symposium on Industrial Electronics |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1532-1537 |
| Number of pages | 6 |
| ISBN (Print) | 9781479923991 |
| DOIs | |
| Publication status | Published - 2014 |
| Event | 2014 IEEE 23rd International Symposium on Industrial Electronics, ISIE 2014 - Istanbul, Turkey Duration: Jun 1 2014 → Jun 4 2014 |
Other
| Other | 2014 IEEE 23rd International Symposium on Industrial Electronics, ISIE 2014 |
|---|---|
| Country | Turkey |
| City | Istanbul |
| Period | 6/1/14 → 6/4/14 |
Fingerprint
Keywords
- depth image filtering
- quadruped robot
- RGB-Depth camera
- supervisory control
- terrain recognition
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Control and Systems Engineering
Cite this
Depth image based terrain recognition for supervisory control of a hybrid quadruped. / Saudabayev, Artur; Kungozhin, Farabi; Nurseitov, Damir; Varol, Huseyin Atakan.
IEEE International Symposium on Industrial Electronics. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1532-1537 6864842.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Depth image based terrain recognition for supervisory control of a hybrid quadruped
AU - Saudabayev, Artur
AU - Kungozhin, Farabi
AU - Nurseitov, Damir
AU - Varol, Huseyin Atakan
PY - 2014
Y1 - 2014
N2 - This paper presents the depth image based locomotion strategy selection framework for a hybrid mobile robot. Terrain recognizer is a major component of a supervisory controller which classifies depth images into terrain types in real-time and selects different locomotion mode sub-controllers. In order to design the terrain recognizer, a database consisting of five terrain types (uneven, level ground, stair up, stair down and not traversable) is generated. Confidence based filtering is applied to enhance depth image data. The accuracy of the terrain classification for the testing database in five class terrain recognition problem is 96.71%. Real-world experiments conducted in mixed terrain environment evaluate both locomotion and terrain recognition capabilities of the robot in real-time. Experimental results show that a consumer depth camera might serve as an effective instrument for terrain recognition and thus locomotion strategy selection for hybrid robots with multiple locomotion modes.
AB - This paper presents the depth image based locomotion strategy selection framework for a hybrid mobile robot. Terrain recognizer is a major component of a supervisory controller which classifies depth images into terrain types in real-time and selects different locomotion mode sub-controllers. In order to design the terrain recognizer, a database consisting of five terrain types (uneven, level ground, stair up, stair down and not traversable) is generated. Confidence based filtering is applied to enhance depth image data. The accuracy of the terrain classification for the testing database in five class terrain recognition problem is 96.71%. Real-world experiments conducted in mixed terrain environment evaluate both locomotion and terrain recognition capabilities of the robot in real-time. Experimental results show that a consumer depth camera might serve as an effective instrument for terrain recognition and thus locomotion strategy selection for hybrid robots with multiple locomotion modes.
KW - depth image filtering
KW - quadruped robot
KW - RGB-Depth camera
KW - supervisory control
KW - terrain recognition
UR - http://www.scopus.com/inward/record.url?scp=84907379128&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84907379128&partnerID=8YFLogxK
U2 - 10.1109/ISIE.2014.6864842
DO - 10.1109/ISIE.2014.6864842
M3 - Conference contribution
SN - 9781479923991
SP - 1532
EP - 1537
BT - IEEE International Symposium on Industrial Electronics
PB - Institute of Electrical and Electronics Engineers Inc.
ER -