Passport – a global database for market, industry, and consumer analysis

VILNIUS TECH Library invites you to follow the published new dissertations. The dissertation „Control of Robot Path Using an Artificial Intelligence System by Fusing Sensor Signal“ („Roboto trajektorijos valdymas dirbtinio intelekto sistema suliejant jutiklių signalus“) prepared at VILNIUS TECH by Vygantas Ušinskis. The dissertation was prepared in 2021–2026. Scientific consultant – Prof. Dr  Vytautas Bučinskas. The dissertation was defended at the public meeting of the Dissertation Defence Council of the Scientific Field of Mechanical Engineering in the Aula Doctoralis Meeting Hall of Vilnius Gediminas Technical University at 10 a.m. on 30 April 2026. The dissertation examines the problem of local robot navigation, where sensor data must be processed in real time to assess the environment and generate an adaptive motion trajectory. The research object is a local navigation system with sensor fusion for mobile robots operating in tunnels and confined channels. Navigation is divided into four parts: environment assessment, localisation, path planning, and motion execution. The analysis of localisation technologies enables the selection of an effective sensor set for obstacle detection. Heuristic and artificial intelligence methods allow generating an optimal trajectory that avoids collisions and maintains the goal. The work addresses navigation and obstacle detection in human-inaccessible environments using a cost-efficient combination of active and passive sensors, with experimental validation of the system’s performance. The dissertation consists of an introduction, three main chapters, conclusions, references, and a list of the author’s scientific publications on the topic of the dissertation. The introduction presents the problem, relevance, research objective and tasks, methodology, scientific novelty, practical significance, and defended statements, as well as the author’s publications and the structure of the dissertation. The First Chapter presents a literature review, including an overview and comparison of global and local path-planning methods, localisation technologies and their combinations, and sensor-fusion approaches used in mobile robots. Key factors affecting reliable navigation are identified, forming the basis for the dissertation tasks. The Second Chapter describes the developed research methodology for autonomous tunnel navigation: the operating principles of the red, green and blue (RGB) channel-camera- and laser-based optical obstacle detection system, sensor-fusion techniques, and the application of modified Vector Field Histogram (VFH) and machine-learning-based path-planning methods. The Third Chapter presents the research results: optical system experiments, path-planning simulations, a comparison between machine-learning and modified VFH methods, and the testing of the constructed robot prototype in a laboratory environment. Five research papers have been published on the topic of the dissertation: three in journals indexed in the Web of Science database, and two in conference proceedings. Additionally, five conference presentations related to the dissertation topic have been delivered in Lithuania and abroad. Doctoral dissertation readers can search via VILNIUS TECH Virtual Library.  

We would like to inform you about upcoming changes to the opening hours of the VILNIUS TECH Library: On 30 April (Thursday) Information Centre in the Central Library and reading rooms in faculties will be open until 1.00 p. m. Paid services in the central library will be available until 1.00 p.m. On 1 May (Friday), user services at the Information Centre in the Central Library and reading rooms in faculties will not be provided. Labour Day.*   *Access to the VILNIUS TECH central library (Saulėtekio al. 14) during nighttime, weekends, and public holidays is restricted to individuals with an activated student card or activated VILNIUS TECH card. For any questions, please contact the Central Library via email at biblioteka@vilniustech.lt or by phone at (0 5) 274 4900.