| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Napovedovanje in izogibanje kolizij z replaniranjem trajektorij v realnem času za kolaborativnega robota : magistrsko delo
Authors:ID Picej, Andrej (Author)
ID Gotlih, Karl (Mentor) More about this mentor... New window
ID Hace, Aleš (Mentor) More about this mentor... New window
ID Pučko, Rok (Comentor)
Files:.pdf MAG_Picej_Andrej_2020.pdf (7,38 MB)
MD5: C290BDAA69F73D91E480C32FC0F3DF2D
PID: 20.500.12556/dkum/5e96e48b-75d3-4afe-ba1d-afbd7ddbd7b1
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FS - Faculty of Mechanical Engineering
Abstract:V magistrskem delu je predstavljena metoda napovedovanja in izogibanja kolizij robotskega mehanizma z replaniranjem trajektorij v realnem času. Z zasnovano metodo želimo izboljšati varnost in časovno učinkovitost kolaborativnih robotskih aplikacij. Predstavljene so tehnologije, ki so potrebne za zaznavo okolja, replaniranja poti in trajektorije, napovedovanja kolizij in vodenja robota. Pri zaznavanju kolizij je uporabljeno orodje GPU-Voxels, za namene planiranja robotskih poti pa je uporabljena knjižnica OMPL. Prikazani so eksperimentalni rezultati algoritmov planiranja in izogibanje robotskega mehanizma statičnim in dinamičnim oviram. Predstavljene so primerjave sistema z metodo brez replaniranja, ki kolizije preprečuje z ustavljanjem robota, ter uporabnost sistema pri kolaborativnih aplikacijah.
Keywords:3D kamera, kolizije, robot, kolaborativna aplikacija, varnost, algoritem načrtovanja poti, voksli, trajektorija
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[A. Picej]
Year of publishing:2020
Number of pages:XII, 104 f.
PID:20.500.12556/DKUM-75685 New window
UDC:519.216:007.52(043.2)
COBISS.SI-ID:23102742 New window
NUK URN:URN:SI:UM:DK:BFNLUTCA
Publication date in DKUM:31.01.2020
Views:1737
Downloads:254
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FS
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:15.01.2020

Secondary language

Language:English
Title:Collision prediction and avoidance with real-time trajectory replanning for a collaborative robot
Abstract:The master's thesis describes a method for collision prediction and collision avoidance of a robot with real-time trajectory replanning. Designed method improves safety and time efficiency of collaborative robot applications. Overview of different technologies necessary for depth and environment sensing, path and trajectory replanning, collision prediction and robot controlling is given. GPU-Voxels software is used for collision detection and OMPL software library is used for purposes of robot path planning. Experimental results for different planning algorithms with various static and dynamic obstacles are shown. Comparison between created method and method without path replanning is made. The method is tested on a real collaborative application to evaluate its performance and versatility.
Keywords:3D camera, collisions, robot, collaborative application, safety, path planning algorithm, voxels, trajectory


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica