会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 4. 发明公开
    • METHOD, COMPUTER SYSTEM AND NON-TRANSITORY COMPUTER READABLE MEDIUM FOR TARGET SELECTION IN THE VICINTY OF A VEHICLE
    • EP4219258A1
    • 2023-08-02
    • EP22153827.5
    • 2022-01-28
    • Aptiv Technologies Limited
    • ZHAO, KunSCHAEFER, MaximilianBUEHREN, Markus
    • B60W30/095B60W60/00
    • The invention relates to a computer implemented method for target selection in the vicinity of a vehicle. In step 210, the method 200 obtains vehicle state information. In step 220 then a machine-learning algorithm is performed to predict a first trajectory of the vehicle based on the vehicle state information for a first prediction time horizon. The prediction is put out in step 230. In step 240, state information from road users different from the vehicle are obtained. In step 250 a machine-learning algorithm is performed on the road users state information and the vehicle state information to predict a second trajectory of vehicle for the first prediction time horizon. The prediction is put out in step 260. Then, in step 265, a first similarity comparison is performed based on the first predicted trajectory of the vehicle as put out in step 230 and the second predicted trajectory of the vehicle as put out in step 260 to determine whether the road users are a potential target of the vehicle for the first prediction time horizon. In step 270, state information from only one road user, i.e. a first road user, is used as input together with the vehicle state information, on which the machine -learning algorithm is performed in step 280 to predict a third trajectory of the vehicle for the first prediction time horizon, which is put out at 290. Then, in step 295, a second similarity comparison is performed based on the second predicted trajectory of the vehicle as put out in step 260 and the third predicted trajectory of the vehicle as put out in step 290 to determine whether the one road user is a potential target of the vehicle for the first prediction time horizon. This is done based on a relevance threshold previously determined based on first similarity comparison of step 265. These last four steps 270, 280, 290 and 295 may then be repeated based on state information of another one of the road users, i.e. a second, a third and/or a fourth road user together with the vehicle state information to perform a third and/or a fourth similarity comparison.