Fuzzy logic steering control of autonomous vehicles inside roundabouts

• This paper shows a real experiment with autonomous vehicles in urban roundabouts.
• A parametric curve generation in used in the path planning, which in divided in three stages: entrance, inside and exit of the roundabout.
• Lane changes experiments show that the controller proposed (based on fuzzy logic) is stable.
• The range of speed used in the experiment is between 8 km/h and 24 km/h. The system was designed for 20 km/h max.
• The real situation experiments show that our proposal is valid for urban scenarios.

The expansion of roads and the development of new road infrastructures have increased in recent years, linked to the population growing in large cities. In the last two decades, roundabouts have largely replaced traditional intersections in many countries. They have the advantage of allowing drivers continuous flow when traffic is clear, without the usual delay caused by traffic lights. Although roundabouts with and without traffic-signal control have been widely used and considered in the literature, driverless control on roundabouts has not been studied in depth yet. The behavior of autonomous vehicles in roundabouts can be divided into three stages: entrance, inside, and exit. The first and last may be handled as an extension of intersections. However, autonomous driving on the roundabout requires special attention. In this paper, the design and implementation of a fuzzy logic system for the steering control of autonomous vehicles inside the roundabout is proposed. Cascade architecture for lateral control and parametric trajectory generation are used. Fuzzy control has proved to be easy to define using expert knowledge. Experiments with a real prototype have been carried out, taking into account different speed profiles and lane change maneuvers inside the roundabout, with very satisfactory results.

Figure optionsDownload as PowerPoint slide