Abstract
This paper addresses the problem of Simultaneous Localization and Mapping (SLAM) for the case of very small, resource-limited robots which have poor odometry and can typically only carry a single monocular camera. We propose a modification to the standard SLAM algorithm in which the assumption that the robots can obtain metric distance/bearing information to landmarks is relaxed. Instead, the robot registers a distinctive sensor "signature", based on its current location, which is used to match robot positions. In our formulation of this non-linear estimation problem, we infer implicit position measurements from an image recognition algorithm. The Iterated form of the Extended Kalman Filter (IEKF) is employed to process all measurements.
| Original language | English (US) |
|---|---|
| Pages | 194-199 |
| Number of pages | 6 |
| State | Published - Dec 26 2003 |
| Event | 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems - Las Vegas, NV, United States Duration: Oct 27 2003 → Oct 31 2003 |
Other
| Other | 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems |
|---|---|
| Country | United States |
| City | Las Vegas, NV |
| Period | 10/27/03 → 10/31/03 |
Fingerprint
Cite this
Appearance-Based Minimalistic Metric Slam. / Rybski, Paul E.; Roumeliotis, Stergios I.; Gini, Maria; Papanikolopoulos, Nikolaos.
2003. 194-199 Paper presented at 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems, Las Vegas, NV, United States.Research output: Contribution to conference › Paper
}
TY - CONF
T1 - Appearance-Based Minimalistic Metric Slam
AU - Rybski, Paul E.
AU - Roumeliotis, Stergios I.
AU - Gini, Maria
AU - Papanikolopoulos, Nikolaos
PY - 2003/12/26
Y1 - 2003/12/26
N2 - This paper addresses the problem of Simultaneous Localization and Mapping (SLAM) for the case of very small, resource-limited robots which have poor odometry and can typically only carry a single monocular camera. We propose a modification to the standard SLAM algorithm in which the assumption that the robots can obtain metric distance/bearing information to landmarks is relaxed. Instead, the robot registers a distinctive sensor "signature", based on its current location, which is used to match robot positions. In our formulation of this non-linear estimation problem, we infer implicit position measurements from an image recognition algorithm. The Iterated form of the Extended Kalman Filter (IEKF) is employed to process all measurements.
AB - This paper addresses the problem of Simultaneous Localization and Mapping (SLAM) for the case of very small, resource-limited robots which have poor odometry and can typically only carry a single monocular camera. We propose a modification to the standard SLAM algorithm in which the assumption that the robots can obtain metric distance/bearing information to landmarks is relaxed. Instead, the robot registers a distinctive sensor "signature", based on its current location, which is used to match robot positions. In our formulation of this non-linear estimation problem, we infer implicit position measurements from an image recognition algorithm. The Iterated form of the Extended Kalman Filter (IEKF) is employed to process all measurements.
UR - http://www.scopus.com/inward/record.url?scp=0346149800&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0346149800&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:0346149800
SP - 194
EP - 199
ER -