Predicting the Performance of Cooperative Simultaneous Localization and Mapping (C-SLAM)
International Journal of Robotics Research
Simultaneous Localization, Mapping and Moving Object Tracking
International Journal of Robotics Research
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part I
A probabilistic language based on sampling functions
ACM Transactions on Programming Languages and Systems (TOPLAS)
Model based vehicle detection and tracking for autonomous urban driving
Autonomous Robots
Journal of Intelligent and Robotic Systems
Stereo vision specific models for particle filter-based SLAM
Robotics and Autonomous Systems
A 3-Component Inverse Depth Parameterization for Particle Filter SLAM
Proceedings of the 31st DAGM Symposium on Pattern Recognition
Probabilistic mobile manipulation in dynamic environments, with application to opening doors
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Recognizing places using spectrally clustered local matches
Robotics and Autonomous Systems
Real-time hierarchical outdoor SLAM based on stereovision and GPS fusion
IEEE Transactions on Intelligent Transportation Systems
LSH-RANSAC: an incremental scheme for scalable localization
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Real-time hierarchical GPS aided visual SLAM on urban environments
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Improved inverse-depth parameterization for monocular simultaneous localization and mapping
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Simultaneous localization and mapping: A feature-based probabilistic approach
International Journal of Applied Mathematics and Computer Science - Special Section: Robot Control Theory Cezary Zielinski
PSO-FastSLAM: an improved FastSLAM framework using particle swarm optimization
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Observability-based Rules for Designing Consistent EKF SLAM Estimators
International Journal of Robotics Research
Solving the online SLAM problem with an omnidirectional vision system
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Real-time hierarchical stereo Visual SLAM in large-scale environments
Robotics and Autonomous Systems
FISST-SLAM: Finite Set Statistical Approach to Simultaneous Localization and Mapping
International Journal of Robotics Research
Optimal Filtering for Non-parametric Observation Models: Applications to Localization and SLAM
International Journal of Robotics Research
Testing image segmentation for topological SLAM with omnidirectional images
MICAI'10 Proceedings of the 9th Mexican international conference on Advances in artificial intelligence: Part I
Integrated PSO and line based representation approach for SLAM
Proceedings of the 2011 ACM Symposium on Applied Computing
Smoothing-based submap merging in large area SLAM
SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
Linear-time robot localization and pose tracking using matching signatures
Robotics and Autonomous Systems
Cooperative multi-robot map merging using Fast-SLAM
RoboCup 2009
Laser and Radar Based Robotic Perception
Foundations and Trends in Robotics
Progress toward multi-robot reconnaissance and the MAGIC 2010 competition
Journal of Field Robotics
Inference on networks of mixtures for robust robot mapping
International Journal of Robotics Research
Hi-index | 0.00 |
Simultaneous Localization and Mapping (SLAM) is an essential capability for mobile robots exploring unknown environments. The Extended Kalman Filter (EKF) has served as the de-facto approach to SLAM for the last fifteen years. However, EKF-based SLAM algorithms suffer from two well-known shortcomings that complicate their application to large, real-world environments: quadratic complexity and sensitivity to failures in data association. I will present an alternative approach to SLAM that specifically addresses these two areas. This approach, called FastSLAM, factors the full SLAM posterior exactly into a product of a robot path posterior, and N landmark posteriors conditioned on the robot path estimate. This factored posterior can be approximated efficiently using a particle filter. The time required to incorporate an observation into FastSLAM scales logarithmically with the number of landmarks in the map. In addition to sampling over robot paths, FastSLAM can sample over potential data associations. Sampling over data associations enables FastSLAM to be used in environments with highly ambiguous landmark identities. This dissertation will describe the FastSLAM algorithm given both known and unknown data association. The performance of FastSLAM will be compared against the EKF on simulated and real-world data sets. Results will show that FastSLAM can produce accurate maps in extremely large environments, and in environments with substantial data association ambiguity. Finally, a convergence proof for FastSLAM in linear-Gaussian worlds will be presented.