Deploying Traffic Smoothing Cruise Controllers Learned from Trajectory Data

Deploying Traffic Smoothing Cruise Controllers Learned from Trajectory Data
复制标题

部署从轨迹数据中学习的交通平滑巡航控制器

DOI:
10.1109/icra46639.2022.9811912
复制
发表时间:
2022
期刊:
2022 International Conference on Robotics and Automation (ICRA
影响因子:
--
通讯作者:
Bayen, Alexandre M.
Bayen, Alexandre M.
中科院分区:
--
文献类型:
--
作者:
Lichtle, Nathan;Vinitsky, Eugene;Nice, Matthew;Seibold, Benjamin;Work, Dan;Bayen, Alexandre M.

文献摘要

参考文献

被引文献

相似文献

由于校准多代理交通模拟器的挑战,基于自主车辆的交通平滑控制器通常不会转移到现实世界中使用。我们展示了一个管道,通过收集轨迹数据和直接从轨迹数据中学习控制器,然后将其部署到高速公路上,从而避免了这种校准问题。我们构建了一个数据集的772.3公里的记录驱动器上的I-24。然后,我们构建了一个简单的模拟器,使用记录的驱动器作为在一个模拟的排,包括一个自动驾驶汽车和五个人类追随者前面的领先车辆。使用政策梯度方法与非对称的评论家学习控制器,我们表明,我们能够提高平均MPG的11%,在模拟拥挤的轨迹。我们部署此控制器的混合排4自主丰田RAV-4的和7个人类司机在验证实验中,并证明了预期的时间间隔的控制器保持在真实的世界测试。最后,我们在https://github.com/nathanlct/trajectory-training-icra上发布了驾驶数据集[1],模拟器和经过训练的控制器。
Autonomous vehicle-based traffic smoothing con-trollers are often not transferred to real-world use due to challenges in calibrating many-agent traffic simulators. We show a pipeline to sidestep such calibration issues by collecting trajectory data and learning controllers directly from trajectory data that are then deployed zero-shot onto the highway. We construct a dataset of 772.3 kilometers of recorded drives on the I–24. We then construct a simple simulator using the recorded drives as the lead vehicle in front of a simulated platoon consisting of one autonomous vehicle and five human followers. Using policy-gradient methods with an asymmetric critic to learn the controller, we show that we are able to improve average MPG by 11% in simulation on congested trajectories. We deploy this controller to a mixed platoon of 4 autonomous Toyota RAV-4's and 7 human drivers in a validation experiment and demonstrate that the expected time-gap of the controller is maintained in the real world test. Finally, we release the driving dataset [1], the simulator, and the trained controller at https://github.com/nathanlct/trajectory-training-icra.
DOI: 10.1016/j.trc.2018.02.005
发表时间: 2018-04-01
影响因子: 8.3
作者:
Stern, Raphael E.;Cui, Shumo;Work, Daniel B.
通讯作者: Work, Daniel B.
DOI: 10.5555/3463952.3464002
发表时间: 2021-02
期刊: ArXiv
影响因子: --
作者:
Jiaxu Cui;William Macke;Harel Yedidsion;Aastha Goyal;Daniel Urielli;P. Stone
通讯作者: Jiaxu Cui;William Macke;Harel Yedidsion;Aastha Goyal;Daniel Urielli;P. Stone
FollowerStopper的可达性分析:安全性分析和实验结果
DOI: 10.1109/icra48506.2021.9561360
发表时间: 2021
期刊: 2021 IEEE International Conference on Robotics and Automation (ICRA)
影响因子: --
作者:
Fang;Marsalis T. Gibson;R. Bhadani;A. Bayen;J. Sprinkle
通讯作者: J. Sprinkle
DOI: --
发表时间: 2021-07
期刊: ArXiv
影响因子: --
作者:
Behrad Toghi;Rodolfo Valiente;Dorsa Sadigh;Ramtin Pedarsani;Y. P. Fallah
通讯作者: Behrad Toghi;Rodolfo Valiente;Dorsa Sadigh;Ramtin Pedarsani;Y. P. Fallah
DOI: 10.1076/vesd.32.4.313.2083
发表时间: 1999-11-01
影响因子: 3.6
作者:
Liang, CY;Peng, H
通讯作者: Peng, H