TACTICAL CONTROL OF AUTONOMOUS, VIRTUAL VEHICLES

摘要

Driving simulators are complex systems with growing importance in studies of driver behaviour and road and vehicle performances. In order to be convincing, a driving simulator must supply the conductor with the sensation of immersion in a typical environment of public ways. These typical environments are composed by a large amount of different vehicles, each one with its own unique behaviour and all of them interacting and competing. The development and implementation of so many different traffic elements is a complex problem. Each vehicle must be able to understand the environment traffic situation, to make decisions based on its knowledge about the road network and to react instantaneously to any unpredictable traffic event. This paper presents a behavior model used to drive autonomous vehicles in a realistic driving simulator. It can implement strictly autonomous vehicles, completely controlled elements, or mixed solutions with externally imposed medium time goals and short time autonomy. It can be configured to implement several different driving behaviors in order to simulate the diversity that can be found in real traffic with human drivers.