US 11,983,245 B2
Unmanned driving behavior decision-making and model training
Shuguang Ding, Beijing (CN); Qin Han, Beijing (CN); Dongchun Ren, Beijing (CN); Sheng Fu, Beijing (CN); and Deheng Qian, Beijing (CN)
Assigned to Beijing Sankuai Online Technology Co., Ltd, Beijing (CN)
Appl. No. 17/276,113
Filed by Beijing Sankuai Online Technology Co., Ltd, Beijing (CN)
PCT Filed Sep. 4, 2019, PCT No. PCT/CN2019/104334
§ 371(c)(1), (2) Date Mar. 12, 2021,
PCT Pub. No. WO2020/052480, PCT Pub. Date Mar. 19, 2020.
Claims priority of application No. 201811062839.2 (CN), filed on Sep. 12, 2018.
Prior Publication US 2022/0051058 A1, Feb. 17, 2022
Int. Cl. G06F 18/214 (2023.01); G06F 18/213 (2023.01); G06N 20/00 (2019.01)
CPC G06F 18/2155 (2023.01) [G06F 18/213 (2023.01); G06N 20/00 (2019.01)] 15 Claims
OG exemplary drawing
 
1. A computer implemented method for training an unmanned driving decision-making model, comprising:
acquiring sample data, wherein the sample data comprises a sample image;
extracting a sample feature vector corresponding to the sample data, wherein a feature vector of the sample image is extracted by manifold dimension reduction; and
obtaining a target decision-making model by performing training in a semi-supervised learning mode based on the sample feature vector, wherein the target decision-making model is for decision-making classification.