当前位置: X-MOL 学术EURASIP J. Adv. Signal Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Target-driven obstacle avoidance algorithm based on DDPG for connected autonomous vehicles
EURASIP Journal on Advances in Signal Processing ( IF 1.7 ) Pub Date : 2022-07-12 , DOI: 10.1186/s13634-022-00872-5
Yu Chen , Wei Han , Qinghua Zhu , Yong Liu , Jingya Zhao

In the field of autonomous driving, obstacle avoidance is of great significance for safe driving. At present, in addition to traditional obstacle avoidance algorithms including VFH algorithm, artificial potential field method, a large number of related researches are focused on algorithms based on vision and neural networks. Researches on these algorithms have achieved some results, and some of which have completed real road tests. However, most of algorithms consider only local environmental information which may cause local optimum in complex driving environments. Therefore, it is necessary to consider the environmental information beyond the sensor's perceptual ability for autonomous driving in complex environment. In the network-assisted automated driving system, networked vehicles can obtain road obstacles’ and condition information through roadside sensors and mobile network, so as to gain extra sensing ability. Therefore, network-assisted automated driving is of great significance in obstacle avoidance. Under this background, this paper presents an automatic driving obstacle avoidance strategy combining path planning and reinforcement learning. At first, a global optimal path is planned through global information, then merge the global optimal path and vehicle information into a vector. Use this vector as input of reinforcement learning neural network and output vehicle control signals to follow optimal path while avoiding obstacles.



中文翻译:

基于DDPG的网联自动驾驶目标驱动避障算法

在自动驾驶领域,避障对于安全驾驶具有重要意义。目前,除了传统的避障算法包括VFH算法、人工势场法外,大量的相关研究都集中在基于视觉和神经网络的算法上。对这些算法的研究已经取得了一些成果,其中一些已经完成了实车路试。然而,大多数算法只考虑局部环境信息,在复杂的驾驶环境中可能会导致局部最优。因此,复杂环境下的自动驾驶需要考虑超出传感器感知能力的环境信息。在网络辅助自动驾驶系统中,联网车辆可以通过路边传感器和移动网络获取道路障碍物和路况信息,从而获得额外的感知能力。因此,网络辅助自动驾驶在避障方面具有重要意义。在此背景下,本文提出了一种结合路径规划和强化学习的自动驾驶避障策略。首先通过全局信息规划一条全局最优路径,然后将全局最优路径和车辆信息合并为一个向量。使用该向量作为强化学习神经网络的输入,并输出车辆控制信号以在避开障碍物的同时遵循最优路径。在此背景下,本文提出了一种结合路径规划和强化学习的自动驾驶避障策略。首先通过全局信息规划一条全局最优路径,然后将全局最优路径和车辆信息合并为一个向量。使用该向量作为强化学习神经网络的输入,并输出车辆控制信号以在避开障碍物的同时遵循最优路径。在此背景下,本文提出了一种结合路径规划和强化学习的自动驾驶避障策略。首先通过全局信息规划一条全局最优路径,然后将全局最优路径和车辆信息合并为一个向量。使用该向量作为强化学习神经网络的输入,并输出车辆控制信号以在避开障碍物的同时遵循最优路径。

更新日期:2022-07-13
down
wechat
bug