面向智能驾驶感知盲区补充的传感器共享策略

Sensor sharing strategy for blind spots supplement in intelligent driving

针对动态交通流中智能驾驶车载传感器感知盲区补充的问题,构建了用于分析传感器感知盲区的动态交通流感知盲区模型,以该模型为基础提出了一种基于熵权法的传感器共享节点选择策略,用于选择最佳的共享车辆节点来进行盲区补充。实验结果表明,动态交通流感知盲区模型对实际交通场景具有良好的表征,基于熵权法的传感器共享节点选择策略选出的节点能有效地补充车辆感知盲区,扩大了车辆的感知范围,提高了智能驾驶汽车的安全性。

Aiming at the problem of supplementing the blind spots of intelligent driving vehicle sensors in dynamic traffic flow, a perception blind spot model in dynamic traffic flow is constructed to analyze sensor blind spots, and a sensor sharing node selection strategy based on the entropy weight method is proposed to select suitable vehicle nodes for blind spots supplement. Experimental results show that the dynamic traffic flow sensing blind spots model has a good representation of actual traffic scenarios. The nodes selected by the sensor sharing node selection strategy based on the entropy weight method can effectively supplement the vehicle sensing blind spots, expand the vehicle’s perception range, and improve driving safety of intelligent driving vehicles.