Tsukada Lab. Computer Network Group
← Publications Int'l conference

Roadside-assisted Cooperative Planning using Future Path Sharing for Autonomous Driving

Mai Hirata, Manabu Tsukada, Keisuke Okumura, Yasumasa Tamura, Hideya Ochiai, Xavier Défago

IEEE 94th Vehicular Technology Conference (VTC2021-Fall), Online, Sep 27, 2021

Summary in three lines

  • The paper defines how automated vehicles share planned trajectories at intersections.
  • A roadside unit uses those trajectories to detect conflicts or opportunities to accelerate and adjusts vehicle speeds accordingly.
  • In an Autoware and LGSVL simulation of a blind intersection, roadside coordination reduced the two vehicles’ travel times by 23.0% and 28.1%, respectively.

Figures from the paper

Figure 1: Intersection coordination through future-path sharing
Figure 1. Intersection coordination through future-path sharingSource: Figure 1 from Hirata et al., IEEE VTC-Fall 2021 (original figure from the authors’ manuscript)The diagram shows vehicles sharing planned movements with a roadside unit so it can coordinate their passage.
Figure 6: Travel times across ten trials
Figure 6. Travel times across ten trialsSource: Figure 6 from Hirata et al., IEEE VTC-Fall 2021 (original figure from the authors’ manuscript)The figure compares travel time at the blind intersection under different coordination settings.

Abstract

Cooperative intelligent transportation systems (ITS) are used by autonomous vehicles to communicate with surrounding autonomous vehicles and roadside units (RSU). Current C-ITS applications focus primarily on real-time information sharing, such as cooperative perception. In addition to real-time information sharing, self-driving cars need to coordinate their action plans to achieve higher safety and efficiency. For this reason, this study defines a vehicle’s future action plan/path and designs a cooperative path-planning model at intersections using future path sharing based on the future path information of multiple vehicles. The notion is that when the RSU detects a potential conflict of vehicle paths or an acceleration opportunity according to the shared future paths, it will generate a coordinated path update that adjusts the speeds of the vehicles. We implemented the proposed method using the open-source Autoware autonomous driving software and evaluated it with the LGSVL autonomous vehicle simulator. We conducted simulation experiments with two vehicles at a blind intersection scenario, finding that each car can travel safely and more efficiently by planning a path that reflects the action plans of all vehicles involved. The time consumed by introducing the RSU is 23.0 % and 28.1 % shorter than that of the stand-alone autonomous driving case at the intersection.

Video

Related video: Extending Autoware for Cooperative Driving: Integrating Perception, Planning, and Coordination

Related research and software

How to cite

M. Hirata, M. Tsukada, K. Okumura, Y. Tamura, H. Ochiai, and X. Défago, “Roadside-assisted Cooperative Planning using Future Path Sharing for Autonomous Driving,” in IEEE 94th Vehicular Technology Conference (VTC2021-Fall), Online, 2021, doi: 10.1109/VTC2021-Fall52928.2021.9625324.

BibTeX

@inproceedings{Hirata2021b,
  title         = {Roadside-assisted Cooperative Planning using Future Path Sharing for Autonomous Driving},
  author        = {Mai Hirata and Manabu Tsukada and Keisuke Okumura and Yasumasa Tamura and Hideya Ochiai and Xavier Défago},
  url           = {https://arxiv.org/abs/2108.04629 https://youtu.be/xaBIQC0SClE},
  doi           = {10.1109/VTC2021-Fall52928.2021.9625324},
  year          = {2021},
  date          = {2021-09-27},
  urldate       = {2021-09-27},
  booktitle     = {IEEE 94th Vehicular Technology Conference (VTC2021-Fall)},
  address       = {Online},
  abstract      = {Cooperative intelligent transportation systems (ITS) are used by autonomous vehicles to communicate with surrounding autonomous vehicles and roadside units (RSU). Current C-ITS applications focus primarily on real-time information sharing, such as cooperative perception. In addition to real-time information sharing, self-driving cars need to coordinate their action plans to achieve higher safety and efficiency. For this reason, this study defines a vehicle’s future action plan/path and designs a cooperative path-planning model at intersections using future path sharing based on the future path information of multiple vehicles. The notion is that when the RSU detects a potential conflict of vehicle paths or an acceleration opportunity according to the shared future paths, it will generate a coordinated path update that adjusts the speeds of the vehicles. We implemented the proposed method using the open-source Autoware autonomous driving software and evaluated it with the LGSVL autonomous vehicle simulator. We conducted simulation experiments with two vehicles at a blind intersection scenario, finding that each car can travel safely and more efficiently by planning a path that reflects the action plans of all vehicles involved. The time consumed by introducing the RSU is 23.0 % and 28.1 % shorter than that of the stand-alone autonomous driving case at the intersection.},
  keywords      = {ITS},
  pubstate      = {published},
  tppubtype     = {inproceedings}
}