Bayerische Motoren Werke Aktiengesellschaft

Marc Walessa

Oliver Kormann

Albrecht Neff

Florian Oszwald

Thomas Barmeyer

Renaud Debon

Torsten Seyffarth

Markus Hoerwick

Markus Hörwick

A method for the preparation of an obstacle map, wherein the obstacle map comprises cells, includes assigning each of the cells to segments of an environment of the vehicle, and assigning to each of the cells information as to whether the corresponding segment of the environment is occupied by an obstacle. The method also includes preparing an environment map that comprises the cells, and determining a threshold value specification, where the threshold value specification specifies different threshold values for the cells of the environment map. The threshold value specification is determined depending on a trajectory of the vehicle. An obstacle map is then determined on the basis of the environment map and the threshold value specification.

Method for providing obstacle maps for vehicles

An environment map includes cells, each of which is assigned to portions of the environment of a vehicle and each of which is assigned an obstacle probability that represents the probability that the corresponding portion of the environment is occupied by an obstacle. The vehicle has at least two environment sensors, each of which is designed to provide measurement data on the occupancy of a region of the environment by an obstacle, referred to as an obstacle region, in the respective detection region of the sensor. The measurement data describes obstacle regions which extend over multiple portions of the environment, and the detection regions of the environment sensors at most partly overlap. A method for providing the environment map for the vehicle has the following steps: receiving the measurement data from the at least two environment sensors, the measurement data of a first environment sensor identifying an obstacle region; determining occupancy probabilities for the portions of the environment covered by the identified obstacle region of the measurement data of the first environment sensor on the basis of the measurement data of at least one other environment sensor, wherein an occupancy probability for a portion indicates the probability that the corresponding portion of the environment is occupied by an obstacle; and updating the obstacle probability of the environmental map for at least the portions for which the occupancy probability has been determined.

Processing sensor measurements of a vehicle environment with low transverse resolution

A method makes available a map of obstacles in the surroundings for a vehicle. An initial map of the surroundings which is divided into cells, each of which is assigned an occupation probability and an obstacle altitude. A ground altitude for each cell of the initial map is determined on the basis of the altitudes in the initial map by smoothing the altitudes. A corrected altitude of the obstacles for each cell of the map of obstacles is determined on the basis of the ground altitude determined for the corresponding cell of the initial map and the altitude of the obstacles assigned to the corresponding cell of the initial map. A respective occupation probability is determined on the basis of the occupancy probability assigned to the corresponding cell of the initial map. The map of obstacles in the surroundings is made available.

Map of the surroundings for driving areas with random altitude profile

A driver information method is provided, wherein an image of the surrounding area is captured by at least one side camera attached to the motor vehicle. The image contains an image capturing area that lies essentially laterally relative to the motor vehicle. A display unit, which is visible to the driver of a motor vehicle, outputs a screen image that contains a reproduction of the image of the surrounding area, the reproduction being graphically processed, if desired, and being preferably in essence photo-realistic. The output of the screen image is only temporary; and an obstructed view situation, in which an obstructed lateral view of the driver is to be assumed, is detected on the basis of distance signals of at least one environment detection system that is not based on a camera. The output of the screen image is automatically started when an obstructed view situation is detected.

Vehicle driver information method

A method provides an environmental map for a vehicle, wherein the environmental map represents a section of the environment and includes cells which are each assigned to a subsection of the environment of the vehicle. Each cell is assigned occupancy information which is based on the probability of the presence of an object in the subsection assigned to the cell in question. The vehicle has a group of at least two driver assistance systems which are each configured to adopt an active and an inactive state and which, in the active state require occupancy information concerning sections of the environment which at least do not overlap completely. The method determines the driver assistance system(s) which is(are) in the active state; determines the section of the environment that the environmental map is intended to represent, on the basis of the section(s) about which the driver assistance system(s) in the active state require(s) occupancy information. In particular, the section of the environment that the environmental map is intended to represent includes the section(s) about which the driver assistance system or the driver assistance systems in the active state require(s) occupancy information when in the active state.

Provision of an efficient environmental map for a vehicle

For the automatic longitudinal guidance of a motor vehicle having a longitudinally guiding driver assistance system with a stop-and-go function, at least starting from a point-in-time wherein the motor vehicle is stopped, the vehicle apron is continuously monitored for possible obstacles by a monitoring device having a camera which supplies a sequence of individual images of the vehicle apron. For the detection of obstacles in the vehicle apron, characteristic image features are extracted from the individual images and are tracked with respect to time within the sequence of individual images, and an appearance and/or disappearance of one or more characteristic image features taking place in the course of the sequence is determined and evaluated. Additionally or alternatively, a change of a spatial distribution of one or more characteristic image features taking place in the course of the sequence in the respective individual image or in a cutout of the latter is determined and evaluated.

Growing community of inventors

Munich, Germany

Marc Walessa