A hybrid self-adaptive particle filter through KLD-sampling and SAMCL

Li, Audeliano W.; Bastos, Guilherme Sousa

doi:10.1109/icar.2017.8023503

Cited by 7 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the limitation of this algorithm is that the range sensors of the robot should be placed uniformly on it, and this constraint is eliminated in Yilmaz and Temeltas (2019). The adaptive MCL and self-adaptive MCL are combined in Li and Bastos (2017) to reach a faster algorithm.…”

Section: Related Workmentioning

confidence: 99%

Integration of affine ICP into the precise localization problem of smart-AGVs: Procedures, enhancements and challenges

Yïlmaz

Temeltaş

2020

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

The localization problem in robotics has been widely studied both for indoor and outdoor applications, but is still open for improvements. In indoor environments, GPS-based methods are not preferred due to reflections, and the pose of the robot is determined according to the measurements taken around with its sensors. One of them is iterative closest point (ICP)-based localization method. ICP is a point set registration method, the essence of which is to iteratively compute the transformation between two point sets. However, it is also utilized to solve the localization problem thanks to its high precision in registration. Precise localization is important for applications that require highly accurate pose estimation, such as for smart-AGVs to be used in smart factories to reach a station at industrial standards. Traditional ICP finds transformation in terms of a rotation and translation, and thus can be directly applied to the localization problem. On the other hand, the affine variant of ICP is not adapted to solve the localization problem. In this study, the necessary arrangements to make affine ICP suitable for precise localization are given as a procedure such that the transformation between point sets is found by affine ICP, the resulting transformation is projected to rotation plane by polar decomposition and then the pose is estimated. The enhancements achieved with the usage of affine ICP in precise localization problems are demonstrated in simulation by comparing localization performance of affine ICP with that of traditional ICP. For this purpose, in a factory environment, a scenario where a smart-AGV approaching the target autonomously to carry out an operation has been prepared. The performances of the algorithms have been evaluated for five different docking stations with 30 separate experiments. Moreover, the challenges related to the affine ICP-based fine localization, in particular about finding projection of affine transformation to rotation plane, are highlighted in this study.

show abstract

Section: Related Workmentioning

confidence: 99%

Integration of affine ICP into the precise localization problem of smart-AGVs: Procedures, enhancements and challenges

Yïlmaz

Temeltaş

2020

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…In order to solve the problem wherein the sampling size becomes large depending on the space size, a PF has been developed to optimize the distribution and size of samples. The most representative approaches are the localization methods based on particle swarm optimization (PSO) and the Kullback‐Leibler divergence (KLD) .…”

Section: Related Workmentioning

confidence: 99%

Hierarchical sampling optimization of particle filter for global robot localization in pervasive network environment

Lee

Myung

2019

ETRI Journal

View full text Add to dashboard Cite

This paper presents a hierarchical framework for managing the sampling distribution of a particle filter (PF) that estimates the global positions of mobile robots in a large‐scale area. The key concept is to gradually improve the accuracy of the global localization by fusing sensor information with different characteristics. The sensor observations are the received signal strength indications (RSSIs) of Wi‐Fi devices as network facilities and the range of a laser scanner. First, the RSSI data used for determining certain global areas within which the robot is located are represented as RSSI bins. In addition, the results of the RSSI bins contain the uncertainty of localization, which is utilized for calculating the optimal sampling size of the PF to cover the regions of the RSSI bins. The range data are then used to estimate the precise position of the robot in the regions of the RSSI bins using the core process of the PF. The experimental results demonstrate superior performance compared with other approaches in terms of the success rate of the global localization and the amount of computation for managing the optimal sampling size.

show abstract

“…The adaptive particle filter with KL-sampling proposed by Dieter [43] limits the estimation error through adaptive changes of sample size, but it may bring high computational cost [44,45]. Torma et al [46] proposed a particle filter based on an adaptive adjustment of likelihood distribution, whereas the weight variance of particles has a great influence on the sample size [47].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Sample-Size Unscented Particle Filter with Partitioned Sampling for Three-Dimensional High-Maneuvering Target Tracking

Deng

Chen

2019

Applied Sciences

View full text Add to dashboard Cite

High-maneuvering target tracking is a focused application area in radar positioning and military defense systems, especially in three-dimensional space. However, using a traditional motion model and techniques expanded from general two-dimensional maneuvering target tracking may be inaccurate and impractical in some mission-critical systems. This paper proposes an adaptive sample-size unscented particle filter with partitioned sampling (PS-AUPF), which is used to track a three-dimensional, high-maneuvering target, combined with the CS-jerk model. In PS-AUPF, the partitioned sampling is introduced to improve the resampling and predicting process by decomposing motion space. At the same time, the adaptive sample size strategy is used to adjust the sample size adaptively in the tracking process, according to the initial parameters and the estimated state variance of each time step. Finally, the effectiveness of this method is validated by simulations, in which the sample size of each algorithm is set to the minimum required for the optimal accuracy, thus ensuring the reliability of the tracking results. The results have shown that the proposed PS-AUPF, with higher accuracy and lower computational complexity, performs better than other existing tracking methods in three-dimensional high-maneuvering target tracking scenarios.

show abstract

A hybrid self-adaptive particle filter through KLD-sampling and SAMCL

Cited by 7 publications

References 8 publications

Integration of affine ICP into the precise localization problem of smart-AGVs: Procedures, enhancements and challenges

Integration of affine ICP into the precise localization problem of smart-AGVs: Procedures, enhancements and challenges

Hierarchical sampling optimization of particle filter for global robot localization in pervasive network environment

Adaptive Sample-Size Unscented Particle Filter with Partitioned Sampling for Three-Dimensional High-Maneuvering Target Tracking

Contact Info

Product

Resources

About