Proceedings Article10.1109/IROS.2013.6696328
Segmented DP-SLAM
Renan Maffei,Vitor A. M. Jorge,Mariana Kolberg,Edson Prestes +3 more
- 01 Nov 2013
- pp 31-36
TL;DR: This paper proposes a new submap-based particle filter algorithm called Segmented DP-SLAM, that combines an optimized data structure to store the maps of the particles with a probabilistic map of segments, representing hypothesis of submaps topologies.
read more
Abstract: Simultaneous Localization and Mapping (SLAM) is one of the most difficult tasks in mobile robotics. While the construction of consistent and coherent local solutions is simple, the SLAM remains a critical problem as the distance travelled by the robot increases. To circumvent this limitation, many strategies divide the environment in small regions, and formulate the SLAM problem as a combination of multiple precise submaps. In this paper, we propose a new submap-based particle filter algorithm called Segmented DP-SLAM, that combines an optimized data structure to store the maps of the particles with a probabilistic map of segments, representing hypothesis of submaps topologies. We evaluate our method through experimental results obtained in simulated and real environments.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Fast Monte Carlo Localization using spatial density information
Renan Maffei,Vitor A. M. Jorge,Vitor F. Rey,Mariana Kolberg,Edson Prestes +4 more
- 26 May 2015
TL;DR: This paper proposes an observation model for localization that associates a kernel density estimate (KDE) to each point in the space, independent of orientation, what allows an efficient pre-caching step, and shows that the method is efficient, even working with large sets of particles, and effective.
10
A Study on Improving the Computational Complexity of SLAM for Intelligent Robot Utilizing Smart Phone
Cheol-Won Lee,Heung-Seok Jeon +1 more
TL;DR: A new scheme for enhancing the computational SLAM overhead of intelligent robots by using the idle resource of Smart Phone as a SLAM processor and a new model for incorporating the smart phone with robot is designed.
Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building
Jee Youn Hwang,Zhang-Wei Hong,Eric Chen,Akhilan Boopathy,Pulkit Agrawal,Ila Fiete +5 more
- 01 Jan 2023
TL;DR: FARMap utilizes fragmentation and recall of local maps to efficiently build and navigate large spaces. Local maps are built by clustering space based on surprisal, and high surprisal leads to fragmentation events, where the local map is stored in long-term memory and a new local map is initialized.
References
FastSLAM: a factored solution to the simultaneous localization and mapping problem
Michael Montemerlo,Sebastian Thrun,Daphne Koller,Ben Wegbreit +3 more
- 28 Jul 2002
TL;DR: FastSLAM as discussed by the authors is an algorithm that recursively estimates the full posterior distribution over robot pose and landmark locations, yet scales logarithmically with the number of landmarks in the map.
Fastslam: a factored solution to the simultaneous localization and mapping problem with unknown data association
Michael Montemerlo,William Whittaker,Sebastian Thrun +2 more
- 01 Jan 2003
TL;DR: This paper presents FastSLAM, an algorithm that recursively estimates the full posterior distribution over robot pose and landmark locations, yet scales logarithmically with the number of landmarks in the map.
A Tutorial on Graph-Based SLAM
TL;DR: An introductory description to the graph-based SLAM problem is provided and a state-of-the-art solution that is based on least-squares error minimization and exploits the structure of the SLAM problems during optimization is discussed.
Hierarchical SLAM: real-time accurate mapping of large environments
TL;DR: A close to optimal loop closing method is proposed that, while maintaining independence at the local level, imposes consistency at the global level at a computational cost that is linear with the size of the loop.
An Atlas framework for scalable mapping
Michael Bosse,Paul Newman,John J. Leonard,M. Soika,Wendelin Feiten,Seth Teller +5 more
- 10 Nov 2003
TL;DR: Atlas is described, a hybrid metrical/topological approach to SLAM that achieves efficient mapping of large-scale environments using a graph of coordinate frames that captures the local environment and the current robot pose along with the uncertainties of each.