Abstract
With the evolution of various advanced driver
assistance system (ADAS) platforms, the design
of autonomous driving system is becoming more
complex and safety-critical. The autonomous
driving system simultaneously activates multiple
ADAS functions; and thus it is essential to coordinate various ADAS functions. This paper proposes a randomized adversarial imitation learning
(RAIL) method that imitates the coordination of autonomous vehicle equipped with advanced sensors.
The RAIL policies are trained through derivativefree optimization for the decision maker that coordinates the proper ADAS functions, e.g., smart
cruise control and lane keeping system. Especially,
the proposed method is also able to deal with the
LIDAR data and makes decisions in complex multilane highways and multi-agent environments