Biološki inspirirano kretanje mobilnog robota temeljeno na evolucijskom algoritmu

master's thesis

• Title (english): Biologically inspired movement of a mobile robot based on an evolutionary algorithm
• Author: Bartol Ugrinić
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2024-05-17, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

U ovom diplomskom radu je navedena primjena evolucijskog algoritma u svrhu traženja
optimalnog hoda četveronožnog robota. Naveden je postupak korištenja 3D CAD STL modela
robota u URDF strukturi i korištenje URDF formata u Pybullet simulaciji. Objašnjene su
osnove evolucijskih algoritama i primijenjen evolucijski algoritam u Python kodu. Izvedena je
simulacija hoda i primjer rezultata evolucijskog algoritma, te njegova usporedba s ručno
programiranim hodom robota. Na kraju su navedeni problemi Pybullet simulatora i
evolucijskog algoritma koji su susretnuti tokom pisanja ovog rada i moguće nadogradnje, kako
simulatora tako i evolucijskog algoritma.

Abstract (english)

In this graduate thesis, the application of the evolutionary algorithms for the purpose of
searching for the optimal gait of a four-legged robot is stated. The procedure for using the 3D
CAD STL model of the robot in the URDF structure and the use of the URDF format in the
Pybullet simulator are listed. The basics of evolutionary algorithms and the applied
evolutionary algorithm in Python code are explained. A simulation of the gait and an example
of the result of the evolutionary algorithm was performed, and its comparison with the manually
programmed gait of the robot. At the end the problems of the Pybullet simulator and the
evolutionary algorithm that were encountered during the writing of this thesis and the possible
upgrade of both the simulator and the evolutionary algorithm are listed.

• Keywords: Python; Pybullet; fizički simulator; URDF; evolucijski algoritam; robotski hod
• Keywords (english): Python; Pybullet; physics simulator; URDF; evolutionary algorithm; robot gait
• Language: croatian
• URN:NBN: urn:nbn:hr:235:583263
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-05-14 18:24:17