A Novel Cost Function for Decision-Making Strategies in Automotive Collision Avoidance Systems

Abstract

Nowadays, the automotive advanced driver assistance systems have the ability to detect surrounding objects, predict impending collisions and initiate automatic emergency braking. However, by a late detection of objects at higher speeds, the collision is hardly avoidable by braking only, hence an evasive steering maneuver shall be performed simultaneously to cure this deficiency. This paper presents a novel approach that utilizes a dedicated cost function to make the appropriate maneuver decision in an imminent collision avoidance situation. By taking into account the host vehicle and the collision target motions as well as other moving or stationary objects in the near vicinity, diverse aspects and criteria are analyzed and discussed to evaluate possible maneuver candidates. After that, the cost functions of different maneuvers are calculated by summarizing the results of all the evaluation criteria and aspects. In both simulated and measured critical situations, the cost function is validated and the maneuver with the best (i.e., lowest) cost is selected to avoid the impending collision and the endangerment of any other road users aside.