Trajectory generation for lane-change maneuver of autonomous vehicles
Abstract
Lane-change maneuver is one of the most thoroughly investigated automatic driving operations that can be used by an autonomous self-driving vehicle as a primitive for performing more complex operations like merging, entering/exiting highways or overtaking another vehicle. This thesis focuses on two coherent problems that are associated with the trajectory generation for lane-change maneuvers of autonomous vehicles in a highway scenario: (i) an effective velocity estimation of neighboring vehicles under different road scenarios involving linear and curvilinear motion of the vehicles, and (ii) trajectory generation based on the estimated velocities of neighboring vehicles for safe operation of self-driving cars during lane-change maneuvers. We first propose a two-stage, interactive-multiple-model-based estimator to perform multi-target tracking of neighboring vehicles in a lane-changing scenario. The first stage deals with an adaptive window based turn-rate estimation for tracking maneuvering target vehicles using Kalman filter. In the second stage, variable-structure models with updated estimated turn-rate are utilized to perform data association followed by velocity estimation. Based on the estimated velocities of neighboring vehicles, piecewise Bezier-curve-based methods that minimize the safety/collision risk involved and maximize the comfort ride have been developed for the generation of desired trajectory for lane-change maneuvers. The proposed velocity-estimation and trajectory-generation algorithms have been validated experimentally using Pioneer3- DX mobile robots in a simulated lane-change environment as well as validated by computer simulations.
Degree
M.S.E.C.E.
Advisors
Lee, Purdue University.
Subject Area
Computer Engineering|Electrical engineering|Robotics
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.