Automated Creation of Topological Maps in Unknown Environments Using a Swarm of Resource-Constrained Robots

Ramaithitima, Rattanachai; Whitzer, Michael; Bhattacharya, Subhrajit; Kumar, Vijay

doi:10.1109/lra.2016.2523600

Cited by 29 publications

(21 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The construction of topological maps is combined with metric maps [16], [17] or not [2]. Generalized Voronoi diagram [18] and spectral clustering [19] are the two main methods [20] to construct the topological map. In [21], spectral clustering and extended Voronoi diagrams are used to construct the topological map from the metric map.…”

Section: Related Work a Topological Mapmentioning

confidence: 99%

TSM: Topological Scene Map for Representation in Indoor Environment Understanding

et al. 2020

View full text Add to dashboard Cite

In the field of robotics, it is crucial to obtain a comprehensive semantic understanding of a scene for many applications. Based on the behavioral topological map and scene graph, we propose to employ a semantic map named Topological Scene Map (TSM) for representation in indoor environment understanding. The behavioral topological map we constructed expresses the spatial connection relations and semantically describes the navigation behavior between adjacent topological nodes. The scene graph promotes the TSM to record the objects that appear in the scene and the relations between objects. The addition of spatial and semantic relations makes the expression of the scene more specific, which improves the robot's abilities of scene understanding and human-robotic interaction. In this paper, we design a method for topological map construction and apply a novel approach to generate a scene graph from RGB-D data. The semantic representation of the environment generated in the experiments verifies that the TSM construction framework models the scene efficiently and the TSM is conducive to the realization of humanrobotic interaction.

show abstract

Section: Related Work a Topological Mapmentioning

confidence: 99%

TSM: Topological Scene Map for Representation in Indoor Environment Understanding

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Other works have proposed systems for augmented reality for robots that present a structure very similar to ARK [14], [15], [16], [17], [18], [19], [20]. In all these works, the robots' locations are tracked through overhead cameras connected to a base control station which then delivers virtual environment information to the robots.…”

Section: Related Workmentioning

confidence: 99%

ARK: Augmented Reality for Kilobots

Reina

Cope

Nikolaidis³

et al. 2017

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Abstract-Working with large swarms of robots has challenges in calibration, sensing, tracking, and control due to the associated scalability and time requirements. Kilobots solve this through their ease of maintenance and programming, and are widely used in several research laboratories worldwide where their low cost enables large-scale swarms studies. However, the small, inexpensive nature of the Kilobots limits their range of capabilities as they are only equipped with a single sensor. In some studies, this limitation can be a source of motivation and inspiration, while in others it is an impediment. As such, we designed, implemented, and tested a novel system to communicate personalised location-and-state-based information to each robot, and receive information on each robots' state. In this way, the Kilobots can sense additional information from a virtual environment in real-time; for example, a value on a gradient, a direction towards a reference point or a pheromone trail. The Augmented Reality for Kilobots (ARK) system implements this in flexible base control software which allows users to define varying virtual environments within a single experiment using integrated overhead tracking and control. We showcase the different functionalities of the system through three demos involving hundreds of Kilobots. The ARK provides Kilobots with additional and unique capabilities through an open-source tool which can be implemented with inexpensive, off-the-shelf hardware.

show abstract

“…En los mismos, se puede aplicar el concepto de fronteras de exploración tanto a 2D (Yamauchi, 1997), como a 3D (Zhu, Ding, Lin, & Wu, 2015), donde se obtienen buenos resultados y el problema pasa a ser el de elegir la mejor frontera a visitar. Estos mapas, por sus características, rápidamente ocupan gran cantidad de memoria, y no son fácilmente aplicables a sistemas embebidos, en particular aquellos con las restricciones de vuelo para MAVs (Ramaithitima, Whitzer, Bhattacharya, & Kumar, 2016).…”

Section: Introductionunclassified

Consideraciones de implementación para algoritmos de exploración robótica en plataformas de procesamiento limitado

Nievas

Araguás²,

Paz³

2020

AJEA

View full text Add to dashboard Cite

El proceso de exploración de un ambiente no estructurado presenta numerosas dificultades a la hora de implementar soluciones en plataformas con capacidades de procesamiento limitado. En el presente trabajo se mencionan las técnicas de exploración comúnmente utilizadas y consideraciones para su implementación en sistemas de hardware limitado. Se analizan problemas encontrados con mapas topológicos, en particular aquellos en forma de árbol durante la exploración. También se exponen resultados obtenidos con la plataforma Jetson Nano para procesar una nube de puntos generada mediante la cámara Intel Realsense D435. Se explican detalles a tener en cuenta con la velocidad de memoria de la misma.

show abstract

Automated Creation of Topological Maps in Unknown Environments Using a Swarm of Resource-Constrained Robots

Cited by 29 publications

References 11 publications

TSM: Topological Scene Map for Representation in Indoor Environment Understanding

TSM: Topological Scene Map for Representation in Indoor Environment Understanding

ARK: Augmented Reality for Kilobots

Consideraciones de implementación para algoritmos de exploración robótica en plataformas de procesamiento limitado

Contact Info

Product

Resources

About