A Bayesian Driver Agent Model for Autonomous Vehicles System Based on Knowledge-Aware and Real-Time Data

Abstract

A key research area in autonomous driving is how to model the driver’s decision-making behavior, due to the fact it is significant for a self-driving vehicles considering their traffic safety and efficiency. However, the uncertain characteristics of vehicle and pedestrian trajectories affect urban roads, which poses severe challenges to the cognitive understanding and decision-making of autonomous vehicle systems in terms of accuracy and robustness. To overcome the abovementioned problems, this paper proposes a Bayesian driver agent (BDA) model which is a vision-based autonomous vehicle system with learning and inference methods inspired by human driver’s cognitive psychology. Different from the end-to-end learning method and traditional rule-based methods, our approach breaks the driving system up into a scene recognition module and a decision inference module. The perception module, which is based on a multi-task learning neural network (CNN), takes a driver’s-view image as its input and predicts the traffic scene’s feature values. The decision module based on dynamic Bayesian network (DBN) then makes an inferred decision using the traffic scene’s feature values. To explore the validity of the Bayesian driver agent model, we performed experiments on a driving simulation platform. The BDA model can extract the scene feature values effectively and predict the probability distribution of the human driver’s decision-making process accurately based on inference. We take the lane changing scenario as an example to verify the model, the intraclass correlation coefficient (ICC) correlation between the BDA model and human driver’s decision process reached 0.984. This work suggests a research in scene perception and autonomous decision-making that may apply to autonomous vehicle system.

An overview of the development of key technologies in autonomous driving technology

“…Li, Lu, Lin, Zhou and Lv introduce a new positioning approach based on the "threshold-constrained line of bearing" (LOB) concept to overcome these challenges [6]. While the existing LOB method faces issues with threshold selection that can vary based on specific data and scenarios, this study proposes a "divide and conquer" strategy built on the LOB technique.…”

Vehicles Detection and Tracking in Advanced & Automated Driving Systems: Limitations and Challenges

“…ADS have also been investigated widely, taking part in car industries to manufacture a car that can drive and take decisions or apply maneuvers on its own with the same efficiency as humans [4] or may be better in avoiding human possible mistake that could happen due to the driver's distraction or fatigue [5]. ADS and ADAS have many common modules that must be fulfilled in order for their functionalities to operate properly, such as road monitoring [6].…”