Bayesian, maneuver-based, long-term trajectory prediction and criticality assessment for driver assistance systems

Abstract

We propose a Bayesian trajectory prediction and criticality assessment system that allows to reason about imminent collisions of a vehicle several seconds in advance. We first infer a distribution of high-level, abstract driving maneuvers such as lane changes, turns, road followings, etc. of all vehicles within the driving scene by modeling the domain in a Bayesian network with both causal and diagnostic evidences. This is followed by maneuver-based, long-term trajectory predictions, which themselves contain random components due to the immanent uncertainty of how drivers execute specific maneuvers. Taking all uncertain predictions of all maneuvers of every vehicle into account, the probability of the ego vehicle colliding at least once within a time span is evaluated via Monte-Carlo simulations and given as a function of the prediction horizon. This serves as the basis for calculating a novel criticality measure, the Time-To-Critical-Collision-Probability (TTCCP) - a generalization of the common Time-To-Collision (TTC) in arbitrary, uncertain, multi-object driving environments and valid for longer prediction horizons. The system is applicable from highly-structured to completely non-structured environments and additionally allows the prediction of vehicles not behaving according to a specific maneuver class.