US 12,352,849 B2
Methods and systems for detection of objects in a vicinity of a vehicle
Mirko Meuter, Erkrath (DE); Jittu Kurian, Wuppertal (DE); Yu Su, Wuppertal (DE); Jan Siegemund, Cologne (DE); Zhiheng Niu, Wuppertal (DE); Stephanie Lessmann, Erkrath (DE); Saeid Khalili Dehkordi, Berlin (DE); Florian Kästner, Bochum (DE); Igor Kossaczky, Wuppertal (DE); Sven Labusch, Cologne (DE); Arne Grumpe, Essen (DE); Markus Schoeler, Wuppertal (DE); Moritz Luszek, Detmold (DE); Weimeng Zhu, Wuppertal (DE); Adrian Becker, Leverkusen (DE); Alessandro Cennamo, Wuppertal (DE); Kevin Kollek, Wuppertal (DE); Marco Braun, Koblenz (DE); Dominic Spata, Witten (DE); and Simon Roesler, Neuss (DE)
Assigned to Aptiv Technologies AG, Schaffhausen (CH)
Filed by Aptiv Technologies AG, Schaffhausen (CH)
Filed on Jul. 23, 2021, as Appl. No. 17/384,493.
Claims priority of application No. 20187674 (EP), filed on Jul. 24, 2020; and application No. 21159039 (EP), filed on Feb. 24, 2021.
Prior Publication US 2022/0026568 A1, Jan. 27, 2022
Int. Cl. G01S 13/931 (2020.01); B60W 60/00 (2020.01); G01S 7/41 (2006.01); G01S 13/86 (2006.01); G06F 18/25 (2023.01); G06N 3/04 (2023.01); G06V 20/58 (2022.01)
CPC G01S 13/931 (2013.01) [B60W 60/001 (2020.02); G01S 7/41 (2013.01); G01S 13/865 (2013.01); G01S 13/867 (2013.01); G06F 18/253 (2023.01); G06N 3/04 (2013.01); G06V 20/58 (2022.01); B60W 2420/403 (2013.01); B60W 2420/408 (2024.01); B60W 2554/404 (2020.02)] 19 Claims
OG exemplary drawing
 
1. A method, comprising:
detecting, using computer hardware components of a vehicle, objects in a vicinity of a vehicle by:
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 that comprises a plurality of sequentially arranged layers, the single detection head being free from layers arranged in parallel;
determining a plurality of properties of each object based on an output of the single detection head;
carrying out, with an ego-motion compensation module, a nearest neighbor interpolation to determine a new position of each object in a current time step and avoiding drift due to an accumulation of positional errors in positions of the objects over time by recording a residual part indicating a positional error of a movement of each object from the current time step;
determining the new position of each object based on a transformation grid from the current time step and a previous residual part for each object from a previous time step;
determining a subsequent position of each object in a subsequent time step based on the recorded residual part for each object; and
detecting the objects based on a regression subnet comprising the ego-motion compensation module; and
controlling, by an autonomous driving system of the vehicle, autonomous driving of the vehicle based on the plurality of properties of each object.