Simultaneous localization and mapping with unknown data association using FastSLAM

By Michael Montemerlo, Sebastian Thrun. IEEE International Conference on Robotics and Automation, 2003

534 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/609fd34f0ba7a75e7ce6d9ca16f883f8d30ef14b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

On behalf of: Multimedia Archives (2012, unknown): “One may argue that in these ambiguous cases, particlefilter-based SLAM (Murphy, 1999; Doucet et al., 2000; Hahnel et al., 2003; Montemerlo and Thrun, 2003; Grisetti et al., 2007b) is the ideal solution as it theoretically can handle arbitrarily shaped distributions.”
Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters (2007, background): “[7], [40] for approaching the SLAM problem with landmark maps.”
Incremental smoothing and mapping (2008, background): “It can also be achieved in the context of particle-based representations [69, 98, 108, 38], where each particle carries its own correspondences, typically based on a per-particle maximum likelihood assignment or random sampling.”
Simultaneous Localization and Mapping with Sparse Extended Information Filters (2004, methodology): “We begin our exposition with experiments using a real-world benchmark data set, which has commonly used to evaluate SLAM algorithms (Guivant and Nebot 2001; Montemerlo et al. 2003; Neira, Tardós, and Castellanos 2003).”
Learning to Predict Independent of Span (2015, background): “In real-world problems, for instance in robotics, it is not uncommon to extract millions of features from the sensory inputs at each step (e.g., Montemerlo and Thrun 2003), where each step lasts only a fraction of a second.”
FastSLAM: a factored solution to the simultaneous localization and mapping problem (2002, background): “This section extends the FastSLAM algorithm to domains in which the mapping between observations and landmarks is not known [41].”
Improving Grid-based SLAM with Rao-Blackwellized Particle Filters by Adaptive Proposals and Selective Resampling (2005, background): “[14, 13] for approaching the SLAM problem with landmark maps.”
An efficient fastSLAM algorithm for generating maps of large-scale cyclic environments from raw laser range measurements (2003, background): “Montemerlo et al. [ 14 ], [15] extended this idea to efficient landmark-based SLAM using Gaussian representations to and were the first to successfully realize it on real robots.”
FastSLAM 2.0: an improved particle filtering algorithm for simultaneous localization and mapping that provably converges (2003, background): “FastSLAM has been extended to SLAM with unknown data associations [14].”
DAvinCi: A cloud computing framework for service robots (2010, unknown): “FastSLAM] which use particle filters for state estimation (feature sets in maps) have conditional independence among the different particle paths [12], [13], [14] and the map features.”
Robotic Tactile Perception of Object Properties: A Review (2017, result): “This compliant motion problem is also compared with the data association [158], i.”
Scale Drift-Aware Large Scale Monocular SLAM (2010, result): “The difference to FastSLAM is that the partially initialised features x new:j are not used for state estimation immediately.”