A new FastSLAM algorithm based on the unscented particle filter

With the development of the artificial intelligence technology, mobile robots have been widely applied to various fields, such as human-computer interaction and self-cruise. Simultaneous localization and mapping is a key to realize the intelligent navigation. Based on the previous research fruits, this paper listed a construction method using lidar, and introduced the SLAM algorithm of the unscented particle filter to make the constructed maps more precise. In this method, the lidar is first used to scan the indoor environment, and then the collected data is adopted to fit the indoor map. Finally, the accurate information is shown in the experimental section.

[1]  Daniel Cremers,et al.  LSD-SLAM: Large-Scale Direct Monocular SLAM , 2014, ECCV.

[2]  Daniel E. Koditschek,et al.  Coordinated Robot Navigation via Hierarchical Clustering , 2015, IEEE Transactions on Robotics.

[3]  Hugh F. Durrant-Whyte,et al.  Mobile robot localization by tracking geometric beacons , 1991, IEEE Trans. Robotics Autom..

[4]  Paul Newman,et al.  Probabilistic Appearance Based Navigation and Loop Closing , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[5]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

[6]  Wolfram Burgard,et al.  Autonomous indoor robot navigation using a sketch interface for drawing maps and routes , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[7]  Ian D. Reid,et al.  Real-Time SLAM Relocalisation , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[8]  Kris Beevers Mapping with limited sensing , 2007 .

[9]  Wesley H. Huang,et al.  Fixed-lag Sampling Strategies for Particle Filtering SLAM , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[11]  Randall Smith,et al.  Estimating Uncertain Spatial Relationships in Robotics , 1987, Autonomous Robot Vehicles.