US 12,117,839 B2
Deep learning-based autonomous vehicle control device, system including the same, and method thereof
Byung Yong You, Suwon-si (KR)
Assigned to HYUNDAI MOTOR COMPANY, Seoul (KR); and KIA MOTORS CORPORATION, Seoul (KR)
Filed by HYUNDAI MOTOR COMPANY, Seoul (KR); and KIA MOTORS CORPORATION, Seoul (KR)
Filed on Oct. 19, 2020, as Appl. No. 17/073,808.
Application 17/073,808 is a continuation of application No. 15/615,971, filed on Jun. 7, 2017, granted, now 10,860,030.
Claims priority of application No. 10-2017-0038405 (KR), filed on Mar. 27, 2017.
Prior Publication US 2021/0048826 A1, Feb. 18, 2021
Int. Cl. G06N 3/045 (2023.01); G05B 23/02 (2006.01); G05D 1/00 (2006.01); G06N 3/08 (2023.01); B60W 50/02 (2012.01); G06N 3/042 (2023.01)
CPC G05D 1/0221 (2013.01) [G05B 23/0229 (2013.01); G05B 23/0294 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); B60W 50/0205 (2013.01); G06N 3/042 (2023.01)] 16 Claims
OG exemplary drawing
 
1. A deep learning-based autonomous vehicle control system, comprising:
a processor configured to determine an autonomous driving control based on deep learning, to correct an error in determination of a deep learning-based autonomous driving control based on determination of an autonomous driving control based on a predetermined expert rule, and to control an autonomous vehicle; and
a non-transitory computer-readable storage medium storing data for the determination of the deep learning-based autonomous driving control, data for the determination of the expert rule-based autonomous driving control, and information about the error in the determination of the deep learning-based autonomous driving control,
wherein the processor is further configured to:
output a deep learning-based autonomous driving control output value for the deep learning-based autonomous driving control;
output an expert rule-based autonomous driving control output value based on the expert rule; and
compare the deep learning-based autonomous driving control output value with the expert rule-based autonomous driving control output value and outputting a final autonomous driving control output value depending on a comparison result,
wherein when the deep learning-based an autonomous driving control output value corresponds to a steering or acceleration/deceleration output control less than a predetermined minimum time to collision (TTC), the processor stops the steering or acceleration/deceleration output control less than the predetermined minimum TTC, and
when the deep learning-based autonomous driving control output value corresponds to a steering value greater than a predetermined steering reference value, the processor adjusts the steering value to be less than the steering reference value.