Algoritmus pro automatické doplňovaní jednoduchých trajektorií
Autocompletion algorithm for simple trajectories
Type of document
diplomová prácemaster thesis
Author
Wei Xin Tan
Supervisor
Škoviera Radoslav
Opponent
Černeková Zuzana
Field of study
Kybernetika a robotikaStudy program
Kybernetika a robotikaInstitutions assigning rank
katedra řídicí technikyRights
A university thesis is a work protected by the Copyright Act. Extracts, copies and transcripts of the thesis are allowed for personal use only and at one?s own expense. The use of thesis should be in compliance with the Copyright Act http://www.mkcr.cz/assets/autorske-pravo/01-3982006.pdf and the citation ethics http://knihovny.cvut.cz/vychova/vskp.htmlVysokoškolská závěrečná práce je dílo chráněné autorským zákonem. Je možné pořizovat z něj na své náklady a pro svoji osobní potřebu výpisy, opisy a rozmnoženiny. Jeho využití musí být v souladu s autorským zákonem http://www.mkcr.cz/assets/autorske-pravo/01-3982006.pdf a citační etikou http://knihovny.cvut.cz/vychova/vskp.html
Metadata
Show full item recordAbstract
Motion planning is one of the core problems that is being studied extensively by robotics researchers in the present day. Among the many techniques available, planning via automatic path/trajectory generation is one of the most widely used approaches. This thesis has implemented a system using tools from computer vision, computer graphics and supervised machine learning which can 'autocomplete' a user demonstrated trajectory segment on differently shaped blocks. This means that the final trajectory generated will be based on the shape of the block with the user's demonstration superimposed on it. The aim is for the trajectory to be utilized in planning the motions of an industrial robot. In the process of developing this system, this thesis provides a comprehensive review of the subject fields utilized and covers the basic intuition behind the algorithms used in the system. The final results of this thesis show that it is possible to automatically generate smooth and continuous trajectories that are non-photorealistic using information from a human made trajectory segment. Although the system is functional, it should be considered as a proof of concept rather than as an industrial level implementation. There is much improvement to be made to this thesis' system before it can be considered fit enough to be deployed in an industrial setting. Motion planning is one of the core problems that is being studied extensively by robotics researchers in the present day. Among the many techniques available, planning via automatic path/trajectory generation is one of the most widely used approaches. This thesis has implemented a system using tools from computer vision, computer graphics and supervised machine learning which can 'autocomplete' a user demonstrated trajectory segment on differently shaped blocks. This means that the final trajectory generated will be based on the shape of the block with the user's demonstration superimposed on it. The aim is for the trajectory to be utilized in planning the motions of an industrial robot. In the process of developing this system, this thesis provides a comprehensive review of the subject fields utilized and covers the basic intuition behind the algorithms used in the system. The final results of this thesis show that it is possible to automatically generate smooth and continuous trajectories that are non-photorealistic using information from a human made trajectory segment. Although the system is functional, it should be considered as a proof of concept rather than as an industrial level implementation. There is much improvement to be made to this thesis' system before it can be considered fit enough to be deployed in an industrial setting.
Collections
- Diplomové práce - 13135 [301]