Road occupancy prediction of traffic participants

Abstract

We predict the road occupancy of traffic participants for collision avoidance systems. The occupancy sets are computed for consecutive time intervals and contain all reachable positions of traffic participants in compliance with a proposed dynamic model. Those sets make it possible to check if planned emergency maneuvers are collision-free in all possible future scenarios. However, no algorithm exists for exactly computing the occupancy when the model forbids unrealistic behavior such as leaving road boundaries or largely exceeding speed limits. For this reason, we provide methods to tightly overapproximate occupancy sets to ensure safe emergency maneuvers. We demonstrate the applicability of the approach by numerical examples, which show that the occupancy computation is not only efficient, but also tight enough to trigger emergency maneuvers almost at the last possible point in time.

Set-Based Prediction of Traffic Participants on Arbitrary Road Networks

“…This paper is an extension to the authors' previous work [3], [51], where it was shown that the occupancy prediction of other traffic participants can be computed in a formal manner. This work significantly extends previous work:…”

Driving strategy selection for cooperative vehicles using maneuver templates

“…We overapproximate the set of solutions Z(t) to facilitate its computation. If we obtain a new model M with constraints C ⊆ C and set Z (t) by relaxing the constraints on model M or by removing constraints C i (z, u) from C, then Z(t) ⊆ Z (t) holds [20]. The overapproximation implies that Z (t) = ∅ ⇒ Z(t) = ∅ holds; therefore, maneuver templates can be discarded despite the overapproximation of Z(t).…”

Fail-safe motion planning of autonomous vehicles

“…To guarantee safety, all possible trajectories of the leading vehicle must be considered. To this end, an overapproximative occupancy set which encloses all possible occupancies is computed [28] for a given time horizon T h2 .…”

“…In [28], a method for computing an overapproximative set which encloses all possible trajectories of the leading vehicle is proposed for a given time horizon T h 2 . To this end, two abstracted models for the leading vehicles are presented: They consider constraints derived from the traffic rules listed in the Vienna Convention on Road Traffic [31] and physical constraints.…”

“…Second, the computation time is low due to the abstracted models used for the vehicle, which makes it suitable for real-time computation. For a more detailed description, the reader is referred to [28].…”