自动驾驶障碍车辆行为预测技术研究

为了使自动驾驶车辆可以像有经验的驾驶员一样对周围车辆的行为做出准确的判断,通过车辆周围传感器来感知障碍车辆的相对位置信息,并结合自身车辆的高精定位信息,获得障碍车辆的精确位置,通过应用隐马尔可夫模型建立不同驾驶行为的预测模型,最终通过模型的预测来判断障碍车辆的可能驾驶意图,辅助自动驾驶车辆进行有效的驾驶决策,更好的规划安全高效的行驶路线。

Research on Behaviour Prediction Technologies of Autonomous Driving Obstacle Vehicles

In order to make autonomous vehicles have accurate judgments on the behaviour of surrounding vehicles like experienced drivers,the relative position information of the obstacle vehicles is felt by sensors around the vehicles,and the accurate position of the obstacle vehicles is obtained by combining the high-precision positioning information of their own vehicles.The prediction models of different driving behaviours are established by using the Hidden Markov Model(HMM),and the final result is that through the prediction of the model,the judgement of the possible driving intention of the obstacle vehicle can be available,assisting the automatic driving vehicle to make effective driving decision,and having a better plan for the safe and efficient driving route.