公开(公告)号：US20220402504A1

公开(公告)日：2022-12-22

申请号：US17807631

申请日：2022-06-17

Applicant: Aptiv Technologies Limited

Inventor： Jan Siegemund ,  Jittu Kurian ,  Sven Labusch ,  Dominic Spata ,  Adrian Becker ,  Simon Roesler ,  Jens Westerhoff

IPC: B60W40/09 ,  B60W50/12

Abstract: A computer-implemented method for generating ground truth data may include the following steps carried out by computer hardware components: for a plurality of points in time, acquiring sensor data for a respective point in time; and for at least a subset of the plurality of points in time, determining ground truth data of the respective point in time based on the sensor data of at least one present and/or past point of time and at least one future point of time.

公开(公告)号：US20220269921A1

公开(公告)日：2022-08-25

申请号：US17649791

申请日：2022-02-02

Applicant: Aptiv Technologies Limited

Inventor： Igor Kossaczky ,  Sven Labusch ,  Mirko Meuter

IPC: G06N3/04 ,  G06V20/58 ,  G06V10/82 ,  G07C5/08

Abstract: Provided is a method and system for tracking a motion of information in a spatial environment of a vehicle. Sensor-based data regarding the spatial environment is acquired for a plurality of timesteps, the sensor-based data defining the information in spatially resolved cells. For each of the timesteps, the sensor-based data is input into a recurrent neural network, RNN, having one or more internal memory states. For each of the timesteps, the internal states of the RNN are transformed by using a motion map describing a speed and/or a direction of motion of the information of the spatially resolved cells individually. For each of the plurality of timesteps, the transformed internal states are used in a processing of the RNN to track the motion of the information in the environment of the moving vehicle.

公开(公告)号：US20220026568A1

公开(公告)日：2022-01-27

申请号：US17384493

申请日：2021-07-23

Applicant: Aptiv Technologies Limited

Inventor： Mirko Meuter ,  Jittu Kurian ,  Yu Su ,  Jan Siegemund ,  Zhiheng Niu ,  Stephanie Lessmann ,  Saeid Khalili Dehkordi ,  Florian Kästner ,  Igor Kossaczky ,  Sven Labusch ,  Arne Grumpe ,  Markus Schoeler ,  Moritz Luszek ,  Weimeng Zhu ,  Adrian Becker ,  Alessandro Cennamo ,  Kevin Kollek ,  Marco Braun ,  Dominic Spata ,  Simon Roesler

IPC: G01S13/931 ,  G06K9/00 ,  G06K9/62 ,  G01S13/86 ,  G01S7/41 ,  B60W60/00 ,  G06N3/04

Abstract: A computer implemented method for detection of objects in a vicinity of a vehicle comprises the following steps carried out by computer hardware components: acquiring radar data from a radar sensor; determining a plurality of features based on the radar data; providing the plurality of features to a single detection head; and determining a plurality of properties of an object based on an output of the single detection head.

公开(公告)号：US20240061104A1

公开(公告)日：2024-02-22

申请号：US18451657

申请日：2023-08-17

Applicant: Aptiv Technologies Limited

Inventor： Sven Labusch ,  Adrian Becker ,  Igor Kossaczky ,  Arne Grumpe

IPC: G01S13/931 ,  G01S13/89 ,  B60W50/14

CPC classification number: G01S13/931 ,  G01S13/89 ,  B60W50/14 ,  G01S2013/9314 ,  B60W2050/146 ,  B60W2420/52

Abstract: The present disclosure relates to a computer-implemented method, apparatus, computer program, and a vehicle that includes the apparatus for determining one or more features of a surrounding of a vehicle. In aspects, a method includes obtaining sensor data comprising measurement points, the measurement points being arranged in a data space; determining an abstract signal processing space based on a distribution of the measurement points in the data space; mapping the measurement points into the abstract signal processing space; and determining the one or more features in the abstract signal processing space based on an arrangement of the measurement points in the abstract signal processing space.

公开(公告)号：US20230093301A1

公开(公告)日：2023-03-23

申请号：US17932576

申请日：2022-09-15

Applicant: Aptiv Technologies Limited

Inventor： Sven Labusch ,  Marco Braun

IPC: G01S17/86 ,  G01S17/894

Abstract: This disclosure describes systems and techniques for object detection. In aspects, techniques include obtaining 3D data including range data, angle data, and doppler data. The techniques further include processing a deep-learning algorithm on the 3D data to obtain processed 3D data and obtaining processed 2D data from the processed 3D data. The processed 2D data includes range data and angle data.

公开(公告)号：US20220214441A1

公开(公告)日：2022-07-07

申请号：US17646504

申请日：2021-12-30

Applicant: Aptiv Technologies Limited

Inventor： Sven Labusch ,  Igor Kossaczky ,  Mirko Meuter ,  Simon Roesler

IPC: G01S13/536 ,  G01S7/35

Abstract: A computer implemented method for compressing radar data comprises the following steps carried out by computer hardware components: acquiring radar data comprising a plurality of Doppler bins; determining which of the plurality of Doppler bins represent stationary objects; and determining compressed radar data based on the determined Doppler bins which represent stationary objects.