Prilagodba Stanley algoritma za korištenje u okviru ROS navigacijskog paketa

undergraduate thesis

• Title (english): Adjustment of Stanley algorithm for usage within ROS navigation package
• Author: Branko Radoš
• Mentor: Stjepan Bogdan (mentor)
• Committee member: Stjepan Bogdan (predsjednik povjerenstva)
• Committee member: Goran Vasiljević (član povjerenstva)
• Committee member: Juraj Oršulić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Stanlijeva metoda je metoda slijeđenja putanje namijenjena autonomnim
vozilima. Svoju publicitet dobiva pobjedom Stanley automobila na DARPA
Grand Challenge-u 2005. Metoda se ističe svojom jednostavnošću, uz visoku
kvalitetu i pouzdanost slijeđenja. Problem završnog rada opisuje implementaciju
Stanley algoritma za diferencijalna vozila, korišten kao lokalni planer u ROS
navigation paketu. Implementacija je potkrijepljena bezinercijskim modelom u
STDR simulatoru kao i inercijskim u GAZEBO-u. Iscrpnim simulacijama određeni
su parametri koji postižu optimalnu razinu slijeđenja. Na koncu simulacijski
rezultati su ispitani na pioneer P3-DX diferencijalnom vozilu.

Abstract (english)

The Stanley method is an path tracking method for autonomous vehicles. It
was made popular by the Stanley vehicle which won the DARPA Grand Challenge
in 2005. It stands out with its simplicity, yet provides very high accuracy and
reliability. This thesis describes an implementation of the Stanley algorithm for a
diferential drive vehicle, to be used as a "local planner" in the ROS Navigation
Stack. The implementation has been verified by simulation in the simplified
STDR simulator as well as in Gazebo, a 3D simulator which models physical
interactions. Algorithm parameters yielding optimal tracking performance have
been determined by extensive simulations. Finally, the implementation has also
been evaluated on the pioneer P3-DX diferential drive robot.

• Keywords: autonomna navigacija; slijedenje putanje; Stanley algoritam; ROS
• Keywords (english): autonomous navigation; path tracking; stanley algorithm; ROS
• Language: croatian
• URN:NBN: urn:nbn:hr:168:294010
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-19 19:05:06