US 12,066,832 B2
Method and apparatus with complex-valued attention network
Hyunwoong Cho, Seoul (KR); Woosuk Kim, Hwaseong-si (KR); and Jong-Sok Kim, Hwaseong-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Dec. 30, 2020, as Appl. No. 17/138,411.
Claims priority of application No. 10-2020-0071459 (KR), filed on Jun. 12, 2020.
Prior Publication US 2021/0389777 A1, Dec. 16, 2021
Int. Cl. G05D 1/00 (2006.01); B60W 10/04 (2006.01); B60W 10/20 (2006.01)
CPC G05D 1/0257 (2013.01) [B60W 10/04 (2013.01); B60W 10/20 (2013.01); B60W 2420/408 (2024.01); B60W 2710/20 (2013.01); B60W 2720/10 (2013.01); B60W 2720/106 (2013.01); B60W 2720/12 (2013.01); B60W 2720/125 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A processor-implemented method of performing an operation using a complex-valued attention network, the method comprising:
extracting a complex-valued attention weight from complex-valued input data using one or more convolution operations;
normalizing a magnitude of the complex-valued attention weight while preserving a phase of the complex-valued attention weight;
determining complex-valued attention data by applying the normalized complex- valued attention weight to the complex-valued input data using an element-wise multiplication such that dimensions of the complex-valued attention data correspond to dimensions of the complex-valued input data;
determining ego-motion information of a vehicle from the complex-valued attention data based on an ego-motion estimation model; and
controlling any one or any combination of a velocity, an acceleration, and steering of the vehicle based on the ego-motion information.