A pure vision-based approach to topological SLAM

Lui, Wen Lik Dennis; Jarvis, Ray

doi:10.1109/iros.2010.5651115

Cited by 16 publications

(15 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The topological map of the surrounding environment is used widely for visual odometry system using an omni-directional camera [10][11]19]. Although the omnidirectional camera has a wide total view angle, it is generally mounted in the upward direction.…”

Section: Related Workmentioning

confidence: 99%

Using Visual Feature and Geometric Constraints for Robot Localization

Lee¹,

Lee²,

Eem³

et al. 2015

IJCA

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Using Visual Feature and Geometric Constraints for Robot Localization

Lee¹,

Lee²,

Eem³

et al. 2015

IJCA

View full text Add to dashboard Cite

show abstract

“…The advantage of these approaches is that they provide relatively accurate solutions maintaining low memory requirements and a low computational cost that permits building the map in real time. For example, Lui and Jarvis [18] describe a topological SLAM system using a purely vision-based approach and detects loop-closure using RANSAC [40]. Likewise, Romero and Cazorla [8] describe an approach to match features and its application in case of scene recognition and topological SLAM, maintaining an only topological map of the environment.…”

Section: Topological Slammentioning

confidence: 99%

“…It is possible to find solutions that include the use of odometry, sonars and lasers [5,14,15] or solutions using vision sensors [2,16,17]. On the other hand, when a topological approach to SLAM is used, the position of the robot is represented by means of a list of states and the map is composed of a list of locations and the connectivity relationships between them [18][19][20]. The hybrid methods combine the computational efficiency of a topological map with the precision and detail of metric implementation [11,12,21].…”

Section: Introductionmentioning

confidence: 99%

Appearance‐based approach to hybrid metric‐topological simultaneous localisation and mapping

Fernández

Payá

Reinoso

et al. 2014

IET Intelligent Transport Systems

View full text Add to dashboard Cite

In this study a unified framework to carry out the simultaneous localisation and mapping of a mobile robot combining metric and topological techniques is presented. The robot moves in a real indoor environment and the algorithm makes use of the information provided by an omnidirectional camera mounted on the robot and its internal odometry. The hybrid approach consists in constructing simultaneously two maps of the environment, one metric and other topological with relationships between them which are updated in each step. The robot goes through the environment to build up a map while continuously captures images. To build the topological map the most relevant information from the scenes is extracted using a global appearance descriptor. A new node is added to the map when the appearance between two images is sufficiently different. Also, the authors check if there is a loop closure with a previous node. At the same time, a metrical map of the environment is computed. With this aim, the authors estimate the position of the robot when it captures a new image using a Monte-Carlo algorithm. The authors show how it is possible to obtain a reasonable performance both in time and accuracy in an indoor environment, when the involved parameters are properly tuned.

show abstract

“…The Haar wavelets were experimentally validated to be robust for use in indoor, semi-outdoor and outdoor environments. For more information, please refer to Lui and Jarvis (2010c). The following describes the two proposed frameworks for the place recognition system.…”

Section: Place Recognition Systemmentioning

confidence: 99%

A pure vision-based topological SLAM system

Lui

Jarvis

2012

The International Journal of Robotics Research

View full text Add to dashboard Cite

In this paper, we present a feasible solution to the problem of autonomous navigation in initially unknown environments using a pure vision-based approach. The mobile robot performs range sensing with a unique omnidirectional stereovision system, estimates its motion using visual odometry and detects loop closures via a place recognition system as it performs topological map building and localization concurrently. Owing to the importance of performing loop closing regularly, the mobile robot is equipped with an active loop closure detection and validation system that assists it to return to target loop closing locations, validates ambiguous loop closures and provides it with the ability to overturn the decision of an incorrectly committed loop closure. A refined incremental probabilistic framework for an appearance-based place recognition system is fully described and the final system is validated in multiple experiments conducted in indoor, semioutdoor and outdoor environments. Lastly, the performance of the probabilistic framework is compared with the rank-based framework with additional experiments conducted in the semi-autonomous mode, where the mobile robot, provided with a priori information in the form of a topological map that is built in a separate occasion in an offline manner, is required to reach its target destination.

show abstract

A pure vision-based approach to topological SLAM

Cited by 16 publications

References 22 publications

Using Visual Feature and Geometric Constraints for Robot Localization

Using Visual Feature and Geometric Constraints for Robot Localization

Appearance‐based approach to hybrid metric‐topological simultaneous localisation and mapping

A pure vision-based topological SLAM system

Contact Info

Product

Resources

About