Title :
A new reinforcement learning vehicle control architecture for vision-based road following
Author :
Oh, Se-young ; Lee, Jeong-Hoon ; Choi, Doo-Hyun
Author_Institution :
Dept. of Electr. Eng., Pohang Univ. of Sci. & Technol., South Korea
fDate :
5/1/2000 12:00:00 AM
Abstract :
A new dynamic control architecture based on reinforcement learning (RL) has been developed and applied to the problem of high-speed road following of high-curvature roads. Through RL, the control system indirectly learns the vehicle-road interaction dynamics, knowledge which is essential to stay on the road in high-speed road tracking. First, computer simulation has been carried out in order to test stability and performance of the proposed RL controller before actual use. The proposed controller exhibited a good road tracking performance, especially on high-curvature roads. Then, the actual autonomous driving experiments successfully verified the control performance on campus roads in which there were shadows from the trees, noisy and/or broken lane markings, different road curvatures, and also different times of the day reflecting a range of lighting conditions. The proposed three-stage image processing algorithm and the use of all six strips of edges have been capable of handling most of the uncertainties arising from the nonideal road conditions
Keywords :
computer vision; learning (artificial intelligence); neural nets; road traffic; road vehicles; traffic control; traffic engineering computing; autonomous driving experiments; broken lane markings; campus roads; computer simulation; control system; different road curvatures; high-curvature roads; high-speed road following; high-speed road tracking; lighting conditions; neural nets; nonideal road conditions; reinforcement learning vehicle control architecture; shadows; three-stage image processing algorithm; vehicle-road interaction dynamics; vision-based road following; Computer architecture; Computer simulation; Control systems; Image processing; Learning; Lighting control; Roads; Stability; Testing; Vehicle dynamics;
Journal_Title :
Vehicular Technology, IEEE Transactions on