magistrsko delo magistrskega študijskega programa II. stopnje Strojništvo
Abstract
Za avtonomno navigacijo mora mobilni robot imeti dostop do karte prostora, ki vsebuje podatek o ovirah v okolici. Gradnja karte, v našem primeru, deluje na osnovi globinske kamere D435 ter kamere za sledenje T265, ki ju povežemo skupaj z algoritmom za hkratno lokalizacijo in kartiranje Rtabmap. Magistrsko delo obravnava razvoj robotskega sistema, ki prejema podatke o odometriji izključno iz sledilne kamere, torej brez uporabe podatkov iz enkoderjev na kolesih. Dodatno pomoč pri kartiranju ponuja funkcionalnost zaznavanja in vizualizacije Aruco oznak, ki znižujejo napako pri lokalizaciji. Razviti sistem deluje pri dobri osvetlitvi, vendar ima težave pri zaznavanju objektov v zahtevnejših svetlobnih pogojih temnejših prostorov, ter ob prisotnosti umazanije in madežev na kamerah.
Keywords
magistrske naloge;robotika;lokalizacija;kartiranje;globinske kamere;sledilne kamere;ROS;Rtabmap;
Data
Language: |
Slovenian |
Year of publishing: |
2021 |
Typology: |
2.09 - Master's Thesis |
Organization: |
UL FS - Faculty of Mechanical Engineering |
Publisher: |
[T. Simičak Hafner] |
UDC: |
007.52:004.93(043.2) |
COBISS: |
84920067
|
Views: |
209 |
Downloads: |
32 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
English |
Secondary title: |
3D simultaneous localisation and mapping on a mobile robot based on a depth camera |
Secondary abstract: |
Autonomous navigation on a mobile robot requires access to a map of the environment, which contains data about the obstacles in said environment. In our work, building a map works on the basis of a depth camera and tracking camera, which feed their data into a simultaneous localisation and mapping algorithm called Rtabmap. This work addresses the development of the robotic system, which receives all of its odometry data exclusively from the tracking camera, meaning it does not use the wheel encoders. Additional functionality and ease of use is provided by the detection and visualization of Aruco tags, which lower the localisation error. The developed system works well in good lighting conditions but fails to perform well in more difficult lighting conditions suck as dark rooms, as well as in the presence of stains and filth on the camera lenses, as it has trouble detecting various objects under such conditions. |
Secondary keywords: |
master thesis;robotics;localisation;mapping;depth cameras;tracking cameras;ROS;Rtabmap; |
Type (COBISS): |
Master's thesis/paper |
Study programme: |
0 |
Embargo end date (OpenAIRE): |
1970-01-01 |
Thesis comment: |
Univ. Ljubljana, Fak. za strojništvo |
Pages: |
XXII, 59 str. |
ID: |
13790049 |