Corpus ID: 232257936

Particle Filter-based vs. Graph-based: SLAM Acceleration on Low-end FPGAs

@article{Sugiura2021ParticleFV,
  title={Particle Filter-based vs. Graph-based: SLAM Acceleration on Low-end FPGAs},
  author={K. Sugiura and Hiroki Matsutani},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.09523}
}
SLAMallowsa robot to continuouslyperceive the surroundingenvironment and locate itself correctly. However, its high computational complexity limits the practical use of SLAM in resource-constrained computing platforms. We propose a resource-efficient FPGA-based accelerator and apply it to two major SLAM methods: particle filter-based and graphbased SLAM.We compare their performances in terms of the latency, throughput gain, and memory consumption, considering their algorithmic characteristics… Expand

Figures from this paper

References

SHOWING 1-7 OF 7 REFERENCES
eSLAM: An Energy-Efficient Accelerator for Real-Time ORB-SLAM on FPGA Platform*
TLDR
This work proposes an energy-efficient architecture for real-time ORB (Oriented-FAST and Rotated-BRIEF) based visual SLAM system by accelerating the most time-consuming stages of feature extraction and matching on FPGA platform and reforming the original ORB descriptor pattern as a rotational symmetric manner. Expand
Real-time loop closure in 2D LIDAR SLAM
TLDR
This work presents the approach used in the backpack mapping platform which achieves real-time mapping and loop closure at a 5 cm resolution and provides experimental results and comparisons to other well known approaches which show that, in terms of quality, this approach is competitive with established techniques. Expand
Efficient Grid-Based Rao–Blackwellized Particle Filter SLAM With Interparticle Map Sharing
TLDR
The experimental results show that the proposed IPMS RBPF-SLAM outperforms conventional methods in terms of map accuracy versus memory consumption and the proposed method is applied to the real-world datasets and benchmark datasets. Expand
A flexible and scalable SLAM system with full 3D motion estimation
TLDR
A system for fast online learning of occupancy grid maps requiring low computational resources is presented that combines a robust scan matching approach using a LIDAR system with a 3D attitude estimation system based on inertial sensing to achieve reliable localization and mapping capabilities in a variety of challenging environments. Expand
Real-time correlative scan matching
  • E. Olson
  • Computer Science
  • 2009 IEEE International Conference on Robotics and Automation
  • 2009
TLDR
This paper advocates a probabilistically-motivated scan-matching algorithm that produces higher quality and more robust results at the cost of additional computation time, and describes several novel implementations of this approach that achieve real-time performance on modern hardware. Expand
On measuring the accuracy of SLAM algorithms
TLDR
A framework for analyzing the results of a SLAM approach based on a metric for measuring the error of the corrected trajectory is proposed, which overcomes serious shortcomings of approaches using a global reference frame to compute the error. Expand
Olson . Real - Time Correlative Scan Matching
  • Proceedings of the IEEE International Conference on Robotics and Automation ( ICRA )