An evaluation of 2D SLAM techniques available in Robot Operating System

2015 IEEE/SICE International Symposium on System Integration (SII)

Santos

Alvito

et al. 2015

Self Cite

SocialRobot is a collaborative European project, which focuses on providing a practical and interactive robotic solution to improve the quality of life of elderly people. Having this in mind, a state of the art mobile robot platform has been integrated with virtual social care technology to meet the elderly individual needs and requirements, following a human centered approach. In this paper, we make an overview of SocialRobot, addressing mainly the integration of the platform and the architecture developed for the project, as well as the existing robot services, the human-robot interactive scenarios prepared, and results extracted from experimental tests with the mobile robot platform.

Section: Service Provision and Robot Capabilitiesmentioning

confidence: 99%

SocialRobot: An interactive mobile robot for elderly home care

2015 IEEE/SICE International Symposium on System Integration (SII)

Santos

Alvito

et al. 2015

Self Cite

“…In order to adopt this metric, the best fit alignment between the ground truth and the map obtained was computed using intensity-based image registration tools. In [26], the metric is described in detail and more results are presented. The numeric results are shown in Table 1.…”

Section: Evaluation Of Slam Algorithms In Rosmentioning

confidence: 99%

“…So, the logical choice is to use GMapping as the base algorithm for this work, which combines both scan matching and odometry in order to minimize the number of particles and improve the accuracy of the estimated pose. More details about the SLAM evaluation conducted can be found in [26].…”

Section: Evaluation Of Slam Algorithms In Rosmentioning

confidence: 99%

A Sensor Fusion Layer to Cope with Reduced Visibility in SLAM

Santos

Couceiro

et al. 2015

J Intell Robot Syst

Self Cite

Mapping and navigating with mobile robots in scenarios with reduced visibility, e.g. due to smoke, dust, or fog, is still a big challenge nowadays. In spite of the tremendous advance on Simultaneous Localization and Mapping (SLAM) techniques for the past decade, most of current algorithms fail in those environments because they usually rely on optical sensors providing dense range data, e.g. laser range finders, stereo vision, LIDARs, RGB-D, etc., whose measurement process is highly disturbed by particles of smoke, dust, or steam. This article addresses the problem of performing SLAM under reduced visibility conditions by proposing a sensor fusion layer which takes advantage from complementary characteristics between a laser range finder (LRF) and an array of sonars. This sensor fusion layer is ultimately used with a state-of-the-art SLAM technique to be resilient in scenarios where visibility cannot be assumed at all times. Special attention is given to mapping using commercial off-the-shelf (COTS) sensors, namely arrays of sonars which, being usually available in robotic platforms, raise technical issues that were investigated in the course of this work. Two sensor fusion methods, a heuristic method and a fuzzy logic-based method, are presented and discussed, corresponding to different stages of the research work conducted. The experimental validation of both methods with two different mobile robot platforms in smoky indoor scenarios showed that they provide a robust solution, using only COTS sensors, for adequately coping with reduced visibility in the SLAM process, thus decreasing significantly its impact in the mapping and localization results obtained.

“…2 Secondly, it is well-established with recognized performance as proven by recent works, e.g. [14]. Finally, the nature of the algorithm is particularly suitable for parallelization, given that each particle is computed independently and there is no data flow between them.…”

Section: Multithreaded Rbpf Slammentioning

confidence: 99%

Speeding up rao-blackwellized particle filter SLAM with a multithreaded architecture

Gouveia

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

Marques

2014

Self Cite

In this work we explore multiprocessor computer architectures to propose an effective method for solving the Simultaneous Localization and Mapping Problem. The proposed method makes use of multithreading to parallelize a Rao-Blackwellized Particle Filter approach. By applying the method in common computers found in robots, it is shown that a significant gain in efficiency can be obtained. Furthermore, the parallel method enables us to raise the number of particles up to values that would not be possible in a single threaded solution, thus gaining in localization precision and map accuracy. In order to analyze SLAM results, frequently used datasets by the robotics community were used, and a benchmarking metric was applied.