Aptiv Technologies Limited

Aptiv Technologies Ag

Dominik Sasin

Pawel Markiewicz

Jakub Porebski

Dariusz Borkowski

Mariusz Lichon

An illustrative example method of mapping a physical environment using an occupancy grid containing a set of cells associated with respective occupancy probabilities includes measuring a potential position of an object, using a sensor and identifying a segment representing a distribution interval of probable values associated with respective probability values relating to the measured potential position. The segment extends according to only one of two dimensions of the coordinate system of the sensor and penetrates a subset of potentially occupied cells. The method includes evaluating a probability of occupancy of each potentially occupied cell by determining the features of a segment portion included in the potentially occupied cell, and determining the probability of occupancy of the potentially occupied cell as a function of the determined segment portion using the probability density function.

Method and system for mapping a physical environment using an occupancy grid

When two target objects cannot see each other and at least one of them is a moving object following lanes, the warning system identifies the couples of two predicted trajectories having at least one point in common or an inter-trajectory distance less than a distance threshold (d), among all possible couples of two predicted trajectories for the two respective target objects, then calculates a probability of collision for each identified couple of trajectories, by determining a predicted collision time and calculating probability distribution functions for the positions of the two target objects at said predicted collision time, and checks whether or not the probability of collision calculated for at least one of the identified couples of trajectories is more than a collision probability threshold in order to trigger an alert towards at least one of the two target objects.

Warning system for a host automotive vehicle

A method for identifying objects in a traffic space by means of a sensor system arranged at or in a host vehicle comprises the steps of determining the positions of a plurality of object surface spots detected by the sensor system in a vehicle coordinate system, assigning the determined positions of object surface spots to at least one detection group by means of a clustering algorithm, wherein the clustering algorithm uses clustering regions defining threshold distances, and identifying at least one object by determining that positions of object surface spots belonging to the same detection group form part of a single object. The determined positions of object surface spots are transformed in a transformation process and the clustering algorithm is applied to the transformed positions of object surface spots. The transformation process includes a directional scaling step that renders the clustering regions non-circular in the vehicle coordinate system.

Growing community of inventors

Cracow, Poland

Dominik Sasin