Title | ||
---|---|---|
A new reinforcement learning vehicle control architecture for vision-based road following |
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 |
Year | DOI | Venue |
---|---|---|
2000 | 10.1109/25.845116 | IEEE T. Vehicular Technology |
Keywords | Field | DocType |
nonideal road conditions,control system,vehicle-road interaction dynamics,neural networks,road vehicles,reinforcement learning,reinforcement learning vehicle control architecture,broken lane markings,learning (artificial intelligence),traffic engineering computing,autonomous driving experiments,shadows,vehicle dynamics.,index terms—lateral control,traffic control,three-stage image processing algorithm,high-speed road following,vision-based road following,computer vision,road following,high-speed road tracking,road traffic,lighting conditions,computer simulation,campus roads,neural nets,high-curvature roads,different road curvatures,vehicle dynamics,stability,control systems,indexing terms,computer architecture,artificial intelligence,neural network,learning artificial intelligence,image processing,testing | Control theory,Architecture,Simulation,Computer science,Image processing,STRIPS,Vehicle dynamics,Control system,Artificial neural network,Reinforcement learning | Journal |
Volume | Issue | ISSN |
49 | 3 | 0018-9545 |
Citations | PageRank | References |
20 | 1.41 | 13 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Se-Young Oh | 1 | 442 | 63.23 |
Jeong-Hoon Lee | 2 | 291 | 16.06 |
Doo-Hyun Choi | 3 | 65 | 12.25 |