Aptiv Technologies Ag

Aptiv Technologies Limited

Ido Freeman

Kun Zhao

Mirko Meuter

Jan Siegemund

Klaus Friedrichs

Lutz Roese-Koerner

Arne Grumpe

Peet Cremer

Thomas Kurbiel

Dominic Spata

Christof Petig

Pascal Colling

A method is provided for controlling the movement of a host vehicle. Lane data related to road items are determined from a data source, and object data acquired from objects are determined via a sensor system. The road items and the objects are located in an external environment of the host vehicle. A machine-learning algorithm is fed with the lane data and the object data to generate a set of controlling functions for controlling the movement of the host vehicle by performing the steps of: classifying a predefined set of maneuvers for the host vehicle based on the lane data and the object data, and determining a set of controlling functions related to kinematics of the host vehicle. The movement of the host vehicle is controlled based on the classified maneuvers and the determined controlling functions.

Method and computer system for controlling the movement of a host vehicle

A method is provided for classifying pixels of an image. An image comprising a plurality of pixels is captured by a sensor device. A neural network is used for estimating probability values for each pixel, each probability value indicating the probability for the respective pixel being associated with one of a plurality of predetermined classes. One of the classes is assigned to each pixel of the image based on the respective probability values to create a predicted segmentation map. For training the neural network, a loss function is generated by relating the predicted segmentation map to ground truth labels. Furthermore, an edge detection algorithm is applied to at least one of the predicted segmentation maps and the ground truth labels, wherein the edge detection algorithm predicts boundaries between objects. Generating the loss function is based on a result of the edge detection algorithm.

Method and device for classifying pixels of an image

A computer implemented method for predicting a trajectory of an object comprises the following steps carried out by computer hardware components: acquiring radar data of the object; determining first intermediate data based on the radar data based on a residual backbone using a recurrent component; determining second intermediate data based on the first intermediate data using a feature pyramid; and predicting the trajectory of the object based on the second intermediate data.

Methods and systems for predicting a trajectory of an object

A computer implemented method for determining weights for an attention based trajectory prediction comprises the following steps carried out by computer hardware components: receiving a sequence of a plurality of captures taken by a sensor; determining an unnormalized weight for a first capture of the sequence based on the first capture of the sequence; and determining a normalized weight for the first capture of the sequence based on the unnormalized weight for the first capture of the sequence and a normalized weight for a second capture of the sequence.

Method and system for determining weights for an attention based method for trajectory prediction

A method for classifying a capture taken by a sensor includes receiving a sequence of a plurality of captures taken by a sensor, each of the captures comprising a plurality of elements; generating, per capture, a plurality of raw probability values, each of the raw probability values being linked to a respective one of a plurality of predetermined classes and indicating the probability that the capture or an element of the capture is associated with the respective class; determining, for a respective one of the captures, a plurality of consolidated probability values in dependence of a plurality of base probability values and a plurality of context probability values, wherein the base probability values represent the raw probability values of the respective capture and the context probability values represent the raw probability values of at least one further capture of the sequence other than the respective capture, the context probability values being normalised according to a normalisation rule; and classifying the respective capture or an element thereof on the basis of the consolidated probability values.

Method for classifying a capture taken by a sensor

A device for assigning one of a plurality of predetermined classes to each pixel of an image, the device is configured to receive an image captured by a camera, the image comprising a plurality of pixels; use an encoder convolutional neural network to generate probability values for each pixel, each probability value indicating the probability that the respective pixel is associated with one of the plurality of predetermined classes; generate for each pixel a class prediction value from the probability values, the class prediction value predicting the class of the plurality of predetermined classes the respective pixel is associated with; use an edge detection algorithm to predict boundaries between objects shown in the image, the class prediction values of the pixels being used as input values of the edge detection algorithm; and assign a label of one of the plurality of predetermined classes to each pixel of the image.

Device and a method for assigning labels of a plurality of predetermined classes to pixels of an image

A device for image classification comprising a convolutional neural network configured to generate a plurality of probability values, each probability value being linked to a respective one of a plurality of predetermined classes and indicating the probability that the image or a pixel of the image is associated with the respective class, and the convolutional neural network comprises a plurality of convolutional blocks and each of the convolutional blocks comprises: a first convolutional layer configured to perform a pointwise convolution using a first kernel, a second convolutional layer configured to perform a depthwise convolution using a second kernel, wherein the second kernel has one of a single row and a single column, a third convolutional layer configured to perform a depthwise convolution using a third kernel, wherein the third kernel has a single column if the second kernel has a single row, and the third kernel has a single row if the second kernel has a single column, and a fourth convolutional layer configured to perform a convolution using a fourth kernel.

Growing community of inventors

Düsseldorf, Germany

Ido Freeman