US 12,221,133 B2
Method for automatic control of vehicle and method for training lane change intention prediction network
Jue Wang, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on Dec. 16, 2021, as Appl. No. 17/553,696.
Application 17/553,696 is a continuation of application No. PCT/CN2020/117384, filed on Sep. 24, 2020.
Claims priority of application No. 201910984614.0 (CN), filed on Oct. 16, 2019.
Prior Publication US 2022/0105961 A1, Apr. 7, 2022
Int. Cl. B60W 60/00 (2020.01); B60W 50/00 (2006.01); G06N 20/00 (2019.01)
CPC B60W 60/0027 (2020.02) [B60W 50/0098 (2013.01); G06N 20/00 (2019.01); B60W 2050/0022 (2013.01); B60W 2552/05 (2020.02); B60W 2552/53 (2020.02); B60W 2554/4041 (2020.02); B60W 2554/4042 (2020.02); B60W 2554/4043 (2020.02); B60W 2554/4044 (2020.02); B60W 2554/4045 (2020.02); B60W 2554/803 (2020.02); B60W 2554/804 (2020.02); B60W 2555/60 (2020.02)] 18 Claims
OG exemplary drawing
 
1. A method for automatic control of a vehicle, performed by an electronic device, the method comprising:
receiving a plurality of types of vehicle traveling information of a target vehicle;
inputting the plurality of types of vehicle traveling information of the target vehicle into a lane change intention prediction network, the lane change intention prediction network comprising a plurality of sub-networks being in a one-to-one correspondence with the plurality of types of vehicles, the lane change intention prediction network being used for predicting a lane change intention of a vehicle in a traveling state, each of the sub-networks comprises a plurality of feature extraction windows, and the feature extraction windows correspond to feature extraction at different traveling moments;
sequentially performing, through each of the sub-networks, feature extraction on the types of vehicle traveling information in a traveling moment order according to the plurality of feature extraction windows in each of the sub-networks, and outputting feature extraction results;
performing feature fusion on the feature extraction results outputted by the sub-networks, and predicting a lane change intention of the target vehicle according to a feature fusion result; and
updating an autonomous driving route of a current vehicle according to the lane change intention of the target vehicle.