Recursive Path Planning Using Reduced States for Car-like Vehicles on Grid Maps
by
Sangyol Yoon, Sung-Eui Yoon,
Unghui Lee, and David Hyunchul Shim
IEEE Transactions on Intelligent Transportation Systems, 2015
|
|
This figure shows our autonomous vehicle that we have tested our path planning method.
|
Abstract
We present a novel path planning method, K*, for efficiently generating a path
considering the kinematic constraints and shape of a car-like vehicle. Our
method is based on a kinematics-aware node expansion method that also checks
collisions based on the shape of a vehicle. We present two different heuristics
considering the kinematics of the vehicle simultaneously w/ and w/o obstacles.
Especially for complex environments that have a complex
configuration of obstacles and even have narrow passage, we recursively
identify intermediate goals and in-between nodes that pass through the narrow
passage for computing a path to the goal. We have demonstrated benefits of our
method in various simulations and experimental results with an autonomous
vehicle. Furthermore, we have shown that our method is able to efficiently
generate a collision-free path that the vehicle can follow even for complex
environments with narrow passage.
Contents
(PDF)
Sangyol Yoon, Sung-Eui Yoon, Unghui Lee, and David Hyunchul Shim
IEEE Transactions on Intelligent Transportation Systems, 2015
Dept. of Computer Science
KAIST
373-1 Guseong-dong, Yuseong-gu, Daejeon, 305-701
South Korea
sglabkaist dot gmail dot com