VGTU talpykla >
Doktorantūros skyrius / Department for Doctoral Studies >
Technologijos mokslų daktaro disertacijos ir jų santraukos >
Please use this identifier to cite or link to this item:
|Title: ||Autonomous robot navigation by multi-criteria decision-making methods|
|Other Titles: ||Autonominė roboto navigacija taikant daugiakriterinius sprendimų priėmimo metodus|
|Authors: ||Semėnas, Rokas|
|Issue Date: ||9-May-2022|
|Publisher: ||Vilniaus Gedimino technikos universitetas|
|Citation: ||Semėnas, R. 2022. Autonomous robot navigation by multi-criteria decision-making methods: doctoral dissertation. Vilnius: Vilniaus Gedimino technikos universitetas, 136 p.|
|Abstract: ||Search and rescue (SAR) missions in disaster sites are complex operations with the top priority of the first responders to find as many survivors as possible within a limited time window. In these missions, autonomous robots can assist the responder teams by providing essential information about the SAR environments without putting human resources in danger. Thus, a robot’s ability to efficiently explore and navigate an unknown environment is the main requirement for an autonomous search and rescue robot. Currently, a common approach to this problem is to incrementally increase the robot’s knowledge about the exploration space by directing it to the regions which border currently unexplored areas, called frontiers. However, deciding on where to move next when multiple candidates are present introduces an additional layer of complexity as the robot must make real-time decisions with limited and possibly inaccurate information. Also, imprecise robot movements and imperfect input data characteristics provided by robot sensors can impact the candidate assessment process and, therefore, should be addressed while designing autonomous search and rescue robots.
The dissertation consists of an introduction, three main chapters, general conclusions, and a list of references. The first chapter performs a literature review on autonomous navigation and environment exploration strategies and formulates the dissertation’s objectives. In the second chapter, a novel adaptive approach that implements the fuzzy logic controller is proposed for the autonomous navigation and environment exploration process. Also, two novel extensions are developed for the state-of-the-art WASPAS multi-criteria decision-making method and applied to determine the most suitable frontier considering the current robot state and the discovered environment information. These extensions are modelled under the interval-valued neutrosophic and m-generalised q-neutrosophic environments and referred to as WASPAS-IVNS and WASPAS-mGqNS.
The third chapter evaluates the proposed autonomous navigation strategies and presents the results. The case study results highlight how the proposed approach could be applied to minimise the probability to damage the robot while maximising the size of the area searched by the robot. By addressing the estimated inaccuracies in the input data characteristics, the proposed decision-making framework provides additional reliability when comparing and ranking candidate frontiers. The obtained results also indicate the increased efficiency when comparing the proposed adaptive candidate assessment strategies to the standard candidate assessment-based strategies.|
|Description: ||Doctoral dissertation|
|Appears in Collections:||Technologijos mokslų daktaro disertacijos ir jų santraukos|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.