当前位置: X-MOL 学术arXiv.cs.RO › 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.)
RACE: Reinforced Cooperative Autonomous Vehicle Collision AvoidancE
arXiv - CS - Robotics Pub Date : 2020-04-02 , DOI: arxiv-2004.01286
Yali Yuan, Robert Tasik, Sripriya Srikant Adhatarao, Yachao Yuan, Zheli Liu, Xiaoming Fu

With the rapid development of autonomous driving, collision avoidance has attracted attention from both academia and industry. Many collision avoidance strategies have emerged in recent years, but the dynamic and complex nature of driving environment poses a challenge to develop robust collision avoidance algorithms. Therefore, in this paper, we propose a decentralized framework named RACE: Reinforced Cooperative Autonomous Vehicle Collision AvoidancE. Leveraging a hierarchical architecture we develop an algorithm named Co-DDPG to efficiently train autonomous vehicles. Through a security abiding channel, the autonomous vehicles distribute their driving policies. We use the relative distances obtained by the opponent sensors to build the VANET instead of locations, which ensures the vehicle's location privacy. With a leader-follower architecture and parameter distribution, RACE accelerates the learning of optimal policies and efficiently utilizes the remaining resources. We implement the RACE framework in the widely used TORCS simulator and conduct various experiments to measure the performance of RACE. Evaluations show that RACE quickly learns optimal driving policies and effectively avoids collisions. Moreover, RACE also scales smoothly with varying number of participating vehicles. We further compared RACE with existing autonomous driving systems and show that RACE outperforms them by experiencing 65% less collisions in the training process and exhibits improved performance under varying vehicle density.

中文翻译:

RACE:增强型协同自动驾驶汽车防撞

随着自动驾驶的快速发展,防撞技术受到了学术界和工业界的广泛关注。近年来出现了许多防撞策略,但驾驶环境的动态性和复杂性对开发鲁棒的防撞算法提出了挑战。因此,在本文中,我们提出了一个名为 RACE: Reinforced Cooperative Autonomous Vehicle Collision avoidance 的去中心化框架。利用分层架构,我们开发了一种名为 Co-DDPG 的算法来有效地训练自动驾驶汽车。自动驾驶汽车通过一个安全守恒的渠道分发他们的驾驶策略。我们使用对手传感器获得的相对距离来构建 VANET 而不是位置,这确保了车辆的位置隐私。通过领导者-跟随者架构和参数分布,RACE 可以加速最优策略的学习并有效利用剩余资源。我们在广泛使用的 TORCS 模拟器中实现了 RACE 框架,并进行了各种实验来测量 RACE 的性能。评估表明,RACE 可以快速学习最佳驾驶策略并有效避免碰撞。此外,RACE 还可以随着参与车辆数量的变化而平稳扩展。我们进一步将 RACE 与现有的自动驾驶系统进行了比较,结果表明,RACE 在训练过程中的碰撞次数减少了 65%,并且在不同车辆密度下表现出更好的性能。我们在广泛使用的 TORCS 模拟器中实现了 RACE 框架,并进行了各种实验来测量 RACE 的性能。评估表明,RACE 可以快速学习最佳驾驶策略并有效避免碰撞。此外,RACE 还可以随着参与车辆数量的变化而平稳扩展。我们进一步将 RACE 与现有的自动驾驶系统进行了比较,结果表明,RACE 在训练过程中的碰撞次数减少了 65%,并且在不同车辆密度下表现出更好的性能。我们在广泛使用的 TORCS 模拟器中实现了 RACE 框架,并进行了各种实验来测量 RACE 的性能。评估表明,RACE 可以快速学习最佳驾驶策略并有效避免碰撞。此外,RACE 还可以随着参与车辆数量的变化而平稳扩展。我们进一步将 RACE 与现有的自动驾驶系统进行了比较,结果表明,RACE 在训练过程中的碰撞次数减少了 65%,并且在不同车辆密度下表现出更好的性能。
更新日期:2020-04-06
down
wechat
bug