C-SAM: Multi-Robot SLAM using square root information smoothing

Andersson, Lars; Nygårds, Jonas

doi:10.1109/robot.2008.4543634

Cited by 60 publications

(44 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This "map compression problem" has been explored from a novel perspective of dictionary-based map compression in our studies [1]- [3]. Applications of a map compressor range from memory-intensive large-size map building [4]- [6] to lightweight information sharing in a robotic sensor network [7]- [9]. Another line of applications is Kolmogorov complexity, as a universal similarity measure (e.g.…”

Section: Introductionmentioning

confidence: 99%

Dictionary-Based Map Compression for Sparse Feature Maps

Kanji

Tomomi

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYObtaining a compact representation of a large-size feature map built by mapper robots is a critical issue in recent mobile robotics. This "map compression" problem is explored from a novel perspective of dictionary-based data compression techniques in the paper. The primary contribution of the paper is the proposal of the dictionary-based map compression approach. A map compression system is presented by employing RANSAC map matching and sparse coding as building blocks. The effectiveness levels of the proposed techniques is investigated in terms of map compression ratio, compression speed, the retrieval performance of compressed/decompressed maps, as well as applications to the Kolmogorov complexity.

show abstract

Section: Introductionmentioning

confidence: 99%

Dictionary-Based Map Compression for Sparse Feature Maps

Kanji

Tomomi

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…The approach combines inter-robot constraints, which arise when one robot encounters another robot, or two robots observe the same part of the environment, with conventional single robot pose graphs in a manner that maintains computational efficiency and preserves consistency, using the concept of "base nodes" [2]. This provides advances over previous work, such as Howard [3] and Andersson [4] in several ways. Our approach deals with uncertainty in inter-robot constraints, and handles multiple encounters between robots.…”

Section: Introductionmentioning

confidence: 99%

“…In the literature on smoothing and mapping (SAM) approaches, two works stand out as most relevant to this paper, Tectonic SAM [2] and C-SAM [4]. Firstly, Ni et al [2] developed Tectonic SAM, a large-scale mapping approach based on submap decomposition.…”

Section: Introductionmentioning

confidence: 99%

“…Also, in contrast to Tectonic SAM we do not make any approximations related to the separator, but rather perform one large incremental optimization over all pose graphs. Secondly, Andersson et al [4] developed a multi-robot version of SAM called C-SAM. The C-SAM algorithm has some similarities with our approach, but several crucial differences: (a) the focus of C-SAM is on the alignment and merging of multiple feature-based landmark maps [21], whereas our approach is based on pose graph representations and (b) C-SAM is a batch algorithm, whereas our algorithm is recursive.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiple relative pose graphs for robust cooperative mapping

Kim

Kaess

Fletcher

et al. 2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-This paper describes a new algorithm for cooperative and persistent simultaneous localization and mapping (SLAM) using multiple robots. Recent pose graph representations have proven very successful for single robot mapping and localization. Among these methods, incremental smoothing and mapping (iSAM) gives an exact incremental solution to the SLAM problem by solving a full nonlinear optimization problem in real-time. In this paper, we present a novel extension to iSAM to facilitate online multi-robot mapping based on multiple pose graphs. Our main contribution is a relative formulation of the relationship between multiple pose graphs that avoids the initialization problem and leads to an efficient solution when compared to a completely global formulation. The relative pose graphs are optimized together to provide a globally consistent multi-robot solution. Efficient access to covariances at any time for relative parameters is provided through iSAM, facilitating data association and loop closing. The performance of the technique is illustrated on various data sets including a publicly available multi-robot data set. Further evaluation is performed in a collaborative helicopter and ground robot experiment.

show abstract

“…With recent progress in SLAM researches, it has become possible for a robot to obtain and use large-size maps that are incrementally built by other mapper robots [4]. For instance, such an online information sharing network has attracted much interest in recent years, in the context of networked robots, sensor networks as well as robot GIS.…”

Section: Introductionmentioning

confidence: 99%

LSH-RANSAC: Incremental Matching of Large-Size Maps

Kanji

Saeki

Minami

et al. 2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper presents a novel approach for robot localization using landmark maps. With recent progress in SLAM researches, it has become crucial for a robot to obtain and use large-size maps that are incrementally built by other mapper robots. Our localization approach successfully works with such incremental and large-size maps. In literature, RANSAC map-matching has been a promising approach for large-size maps. We extend the RANSAC map-matching so as to deal with incremental maps. We combine the incremental RANSAC with an incremental LSH database and develop a hybrid of the position-based and the appearancebased approaches. A series of experiments using radish dataset show promising results.

show abstract

C-SAM: Multi-Robot SLAM using square root information smoothing

Cited by 60 publications

References 11 publications

Dictionary-Based Map Compression for Sparse Feature Maps

Dictionary-Based Map Compression for Sparse Feature Maps

Multiple relative pose graphs for robust cooperative mapping

LSH-RANSAC: Incremental Matching of Large-Size Maps

Contact Info

Product

Resources

About