On Unsupervised Learning based Multi-Goal Path Planning for Visiting 3D Regions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00328622" target="_blank" >RIV/68407700:21230/18:00328622 - isvavai.cz</a>

Výsledek na webu

<a href="https://dl.acm.org/citation.cfm?id=3297099" target="_blank" >https://dl.acm.org/citation.cfm?id=3297099</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3297097.3297099" target="_blank" >10.1145/3297097.3297099</a>

Jazyk výsledku

angličtina

Název v původním jazyce

On Unsupervised Learning based Multi-Goal Path Planning for Visiting 3D Regions

Popis výsledku v původním jazyce

In this paper, we report on our early results on deploying unsupervised learning technique for solving a multi-goal path planning problem to determine a shortest path to visit a given set of 3D regions. The addressed problem is motivated by data collection missions in which a robotic vehicle is requested to visit a set of locations to perform particular measurements. Instead of precise visitation of the specified locations, it is allowed to take the measurements at the respective distance from the locations, and thus save the travel cost by exploiting non-zero sensing radius of the vehicle. In particular, the problem is formulated as a 3D variant of the Close-Enough Traveling Salesman Problem (CETSP), and the proposed approach is based on the recently introduced technique called the Growing Self-Organizing Array (GSOA). The GSOA is a neural network for routing problems that is accompanied with unsupervised learning procedure to determine a solution of the TSP-like problems in a finite number of learning epochs. Based on the reported results, the proposed GSOA-based approach provides competitive or better results than existing combinatorial heuristics based on the so-called Steiner zones, while the computational requirements are significantly lower.

Název v anglickém jazyce

On Unsupervised Learning based Multi-Goal Path Planning for Visiting 3D Regions

Popis výsledku anglicky

In this paper, we report on our early results on deploying unsupervised learning technique for solving a multi-goal path planning problem to determine a shortest path to visit a given set of 3D regions. The addressed problem is motivated by data collection missions in which a robotic vehicle is requested to visit a set of locations to perform particular measurements. Instead of precise visitation of the specified locations, it is allowed to take the measurements at the respective distance from the locations, and thus save the travel cost by exploiting non-zero sensing radius of the vehicle. In particular, the problem is formulated as a 3D variant of the Close-Enough Traveling Salesman Problem (CETSP), and the proposed approach is based on the recently introduced technique called the Growing Self-Organizing Array (GSOA). The GSOA is a neural network for routing problems that is accompanied with unsupervised learning procedure to determine a solution of the TSP-like problems in a finite number of learning epochs. Based on the reported results, the proposed GSOA-based approach provides competitive or better results than existing combinatorial heuristics based on the so-called Steiner zones, while the computational requirements are significantly lower.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA16-24206S" target="_blank" >GA16-24206S: Metody informatického plánování cest pro neholonomní mobilní roboty v úlohách monitorování a dohledu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 2018 International Conference on Robotics and Artificial Intelligence

ISBN

978-1-4503-6584-0

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

45-50

Název nakladatele

ACM

Místo vydání

New York

Místo konání akce

Guangzhou

Datum konání akce

17. 11. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—