Standard platform for sensor fusion on advanced driver assistance system using Bayesian Network

In this paper, a new architecture for sensor fusion for advanced driver assistant system (ADAS) is proposed. This architecture is based on Bayesian Network and plays the role of a platform for integrating various sensors such as Lidar, Radar and Vision sensors into sensor fusion systems. This architecture has the following 3 major advantages: (1) It makes structure and signal flow of the complicated fusion systems easy to understand (2) It increases the reusability of the sensor algorithm modules (3) It achieves easy integration of various sensors with different specifications. These advantages are confirmed by vehicle test.