Autonomous overtaking maneuver under complex driving conditions
Loading...
URL
Journal Title
Journal ISSN
Volume Title
Sähkötekniikan korkeakoulu |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
Department
Major/Subject
Mcode
ELEC3055
Degree programme
Language
en
Pages
68+2
Series
Abstract
The thesis tackles the planning and control of autonomous overtaking and subsequent lane-keeping. While existing solutions attempt multi-lane overtaking involving simple and static scenarios, the focus here is on single-lane overtaking which requires minimal intrusion onto the adjacent lane in dynamically changing conditions. The method proposed utilizes a heuristic rule-based strategy to select optimal maneuvers and then uses a combination of safe and reachable sets to iteratively generate intermediate reference targets based on the desired maneuver. A nonlinear model predictive controller then plans dynamically feasible trajectories to these intermediate reference targets that avoid collisions. The proposed method was implemented and tested under 7 different scenarios that cover many complex lane-keeping and overtaking scenarios using the CARLA simulation engine with ROS (Robotic Operating System) framework for inter-component communication with model predictive controller developed using MATLAB. In every tested scenario, the proposed planning and control paradigm was able to select the best course of action (maneuver) and execute the same without collisions with other nearby vehicles.Description
Supervisor
Albayrak, SahinThesis advisor
Görür, Orhan CanAksjonov, Andrei