US 12,111,386 B2
Methods and systems for predicting a trajectory of an object
Dominic Spata, Witten (DE); Arne Grumpe, Essen (DE); Mirko Meuter, Erkrath (DE); and Ido Freeman, Düsseldorf (DE)
Assigned to Aptiv Technologies AG, Schaffhausen (CH)
Filed by Aptiv Technologies AG, Schaffhausen (CH)
Filed on Jul. 23, 2021, as Appl. No. 17/384,449.
Claims priority of application No. 20187694 (EP), filed on Jul. 24, 2020; and application No. 21186073 (EP), filed on Jul. 16, 2021.
Prior Publication US 2022/0026556 A1, Jan. 27, 2022
Int. Cl. G01S 13/58 (2006.01); G01S 13/06 (2006.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01)
CPC G01S 13/58 (2013.01) [G01S 13/06 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01)] 23 Claims
OG exemplary drawing
 
1. A method comprising:
acquiring, by computer hardware components, a plurality of frames of radar data of an object;
via a convolutional neural network, performing temporal fusion of features of the plurality of frames of radar data, wherein the convolutional neural network comprises a residual backbone, a feature pyramid and a regression head;
determining, using a recurrent component, first intermediate data based on the plurality of frames of radar data and the residual backbone;
determining, using the feature pyramid, second intermediate data based on the first intermediate data, wherein the second intermediate data comprises a plurality of features;
determining via the regression head a plurality of coefficients to time-continuous polynomial functions based on the plurality of features; and
predicting, based on the plurality of coefficients, a trajectory of the object.