The invention relates to a lane changing decision-making method considering surrounding vehicle driving intention and self driving expectation, the method considers surrounding vehicle driving intention and self driving expectation at the same time, during driving intention identification, a Bayesian network is constructed, and by means of big data statistics and strong computing power of a cloud platform, driving intention identification is carried out. The influence of multiple factors of traffic environment on driving intentions is comprehensively considered, the next driving intentions and probability values of drivers of surrounding vehicles are more accurately recognized, then income matrixes of the two vehicles gaming under different strategies are calculated, Nash equilibrium is solved according to the expected income of the own vehicle and the vehicles behind the target lane, the optimal behavior strategy is obtained, and the driving intentions of the vehicles in the next step are more accurately recognized. And the safety of automatic driving is improved.
本发明涉及一种考虑周车驾驶意图及自身驾驶期望的换道决策方法,该方法同时考虑周车驾驶意图及自身驾驶期望,在驾驶意图识别时,构建贝叶斯网络,借助于云平台的大数据统计与强大的计算能力,全面综合的考虑到交通环境多因素对驾驶意图的影响,更加准确的识别周车驾驶员下一步的驾驶意图和概率值,之后计算不同策略下博弈的两车辆的收益矩阵,根据自车与目标车道后车的预期收益求解纳什均衡,得到最优行为策略,提高了自动驾驶的安全性。
Lane changing decision-making method considering driving intention of surrounding vehicles and driving expectation of surrounding vehicles
一种考虑周车驾驶意图及自身驾驶期望的换道决策方法
2024-06-21
Patent
Electronic Resource
Chinese
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
European Patent Office | 2024
|European Patent Office | 2025
|Wiley | 2022
|European Patent Office | 2024
|DOAJ | 2022
|