Situation assessment algorithm for a collision prevention assistant

Abstract

In this paper, we present the concept of a collision prevention assistant, a system that we believe can significantly contribute to road safety. We propose a new situation assessment algorithm which is tailored to the action of braking and that further accounts for the nonlinearities that arise when vehicles cut out or come to a standstill. The effect of sensor uncertainty on the.performance of the proposed algorithm is modelled using a Markov chain and analyzed by means of a Monte Carlo simulation on a typical traffic situation.

Certainty and Critical Speed for Decision Making in Tests of Pedestrian Automatic Emergency Braking Systems

“…In [16], the authors used the idea of the Required Deceleration (RD) to stop the car in the measured distance of the pedestrian position, and used a first order braking model of the system response obtained from tests. Several concepts assessing the risk in terms of Time-to-X were presented in [17] and [18]. Time to Braking (TTB) was the remaining time until an emergency braking at maximum deceleration must be applied in order to avoid a crash by braking; the authors considered a constant deceleration in braking action.…”

Driving situation analysis in automotive environment

“…This property "too near" can be calculated from the vehicle positions and their current derivation(s) in time. A classic attribute is the Time-To-Collision (TTC) or some recent approach like the Time-To-Break (TTB) [5]. Hence, here the association to the set for the center section has not only the distance as a parameter but also additional information like the velocities and accelerations of the ego vehicle and the other participant.…”

“…As mentioned in [5] efficient collision prevention relies on knowledge about the environment and other traffic participants. So not only tracking of obstacles is the challenge but also obtaining detailed information about the current traffic scenario including the actions of the own vehicle (in the following referred to as ego vehicle) and the interactions with other traffic participants.…”

Human Behavior Based Predictive Brake Assistance

“…either critical, requiring system intervention, or non-critical). We also assume the prior, P (C), is uniform, thereby simplifying (1) to P (CBs, Bd, O) = kP (Bs, Bdc, O) (5) where k is a scale factor derived from the denominator in (I) and P (C). Combining this with (2), we can see that we need to learn the probabilities P (B5 C, 0) and P (Bd C, 0).…”

“…Hillenbrand et. al [5] demonstrate a system that takes into account the driver's braking action by classifying braking into either normal braking or emergency braking. No predictive or direct information beyond that obtained from the vehicle is used.…”