Navigacija mobilnog robota u zatvorenim prostorima

master's thesis

• Title (english): Mobile robot navigation in indoor environments
• Author: Marija Piliškić
• Mentor: Stjepan Bogdan (mentor)
• Committee member: Stjepan Bogdan (član povjerenstva)
• Committee member: Tamara Petrović (član povjerenstva)
• Committee member: Goran Vasiljević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-12, Croatia

Abstract

Navigacija autonomnih robota u zatvorenim prostorima se istaknula kao značajno područje u istraživanju u robotici. Cilj je omogućiti robotima da autonomno navigiraju zatvorenim prostorima, precizno se lokaliziraju i efektivno kreiraju i izvršavaju planove kako bi obavili neki zadatak. U ovom radu predtstavit ćemo postojeća rješenja i metode za navigaciju u zatvorenim prostorima. Jedno od takvih rješenja je algoritam teach-and-repeat (eng. nauči i ponovi), koji omogućava robotu da navigira putem kojeg je prethodno izveo ljudski operater, time pojednostavljujući proces navigacije na slijeđenje putanje i izbjegavajući kompleksne probleme procjene terena i planiranja putanje u nestrukturiranim okruženjima. Teach-and-repeat algoritam je implementiran i testiran koristeći lidar kao glavni senzor u novom zatvorenom prostoru. Nadalje, sustav za detekciju dinamičnih prepreka je implementiran i testiran uz sustav.

Abstract (english)

Indoor navigation for autonomous robots has emerged as a significant research area in the field of robotics. The goal of indoor navigation is to enable robots to autonomously traverse indoor spaces, accurately localize themselves, and effectively plan and execute their movements to accomplish specific tasks. In this paper, we will explore existing indoor navigation solutions, one of which is the teach and repeat algorithm that allows the robot to navigate along paths previously taught by a human operator, simplifying the navigation process to path following, and avoiding the complexities of terrain assessment and path planning in unstructured environments. The teach and repeat algorithm will be implemented and tested using a lidar sensor in a new indoor environment. Furthermore, a system for indoor obstacle detection will be implemented and tested with the teach-and-repeat algorithm pipeline.

• Keywords: mobilni roboti; navigacija u zatvorenim prostorima; lidar; pointcloud
• Keywords (english): mobile robots; indoor navigation; lidar; pointcloud segmentation
• Language: english
• URN:NBN: urn:nbn:hr:168:556545
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 10:09:12