Evaluating risk at road intersections by detecting conflicting intentions

Abstract

Abstract-This paper proposes a novel approach to risk assessment at road intersections. Unlike most approaches in the literature, it does not rely on trajectory prediction. Instead, dangerous situations are identified by comparing what drivers intend to do with what they are expected to do. Driver intentions and expectations are estimated from the joint motion of the vehicles, taking into account the layout of the intersection and the traffic rules at the intersection. The proposed approach was evaluated in simulation with two vehicles involved in typical collision scenarios. An analysis of the collision prediction horizon allows to characterize the efficiency of the approach in different situations, as well as the potential of different strategies to avoid an accident after a dangerous situation is detected.

Probabilistic decision making for collision avoidance systems: Postponing decisions

“…In this section we describe one possible implementation which builds on our previous work on risk assessment [12].…”

Adaptive tactical behaviour planner for autonomous ground vehicle

“…In this study the behaviour prediction is interaction based, and the behaviour of other actors is predicted based on temporal evolution of behaviour through the use of Dynamic Bayesian Network (DBN). This approach is using similar concepts used by Lefèvre et al [89] however considers the Traffic rules case as a separate exclusive node. The graphical representation of the DBN framework is shown in the Fig 8 Fig.8.…”

A multi-objective evolutionary algorithm for the tuning of fuzzy rule bases for uncoordinated intersections in autonomous driving

“…Statistical studies about the causes of accidents at intersections have shown that 90% of them are due to driver error [23]. The most common ones are perception failures (e.g.…”