Demo: VI-Planning: Infrastructure-Assisted Real-Time Planning Optimization for Autonomous Driving

Yang Lu; Jie Wang; Xiaoyun Dong; Ziyao Huang; Bingyi Liu; Jen-Ming Wu; Jianping Wang

doi:10.1145/3680207.3765605

Demo: VI-Planning: Infrastructure-Assisted Real-Time Planning Optimization for Autonomous Driving

Yang Lu
, Jie Wang
, Xiaoyun Dong
, Ziyao Huang^*
, Bingyi Liu^*
, Jen-Ming Wu
, Jianping Wang^*

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

We propose VI-Planning, an innovative system that leverages the scene-level future occupancy grid maps predicted by the infrastructure as future drivable area references to directly optimize the planning trajectories of autonomous vehicles in real time. Since VI-Planning operates only at the autonomous vehicle’s final output stage, without modifying the underlying system architecture, it can be plug- and-play for most autonomous driving systems. Moreover, VI-Planning employs a novel bitwise encoding mechanism to efficiently compress these maps, enabling practical transmission. The experimental results demonstrate that VI-Planning can achieve real-time planning optimization with extremely low bandwidth consumption, significantly enhancing the driving safety of autonomous systems. The source code and video demonstration of VI-Planning are available on GitHub: https://github.com/YANG-Deep/VI-Planning. © 2025 Copyright held by the owner/author(s).

Original language	English
Title of host publication	ACM MobiCom ’25
Subtitle of host publication	Proceedings of the 2025 the 31st Annual International Conference on Mobile Computing and Networking
Publisher	Association for Computing Machinery
Pages	1245-1247
Number of pages	3
ISBN (Print)	9798400711299
DOIs	https://doi.org/10.1145/3680207.3765605
Publication status	Published - 2025
Event	31st Annual International Conference on Mobile Computing and Networking (ACM MobiCom 2025) - , Hong Kong, China Duration: 4 Nov 2025 → 8 Nov 2025 https://www.sigmobile.org/mobicom/2025/index.html

Conference

Conference	31st Annual International Conference on Mobile Computing and Networking (ACM MobiCom 2025)
Abbreviated title	ACM MobiCom ’25
Place	Hong Kong, China
Period	4/11/25 → 8/11/25
Internet address	https://www.sigmobile.org/mobicom/2025/index.html

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access Output

10.1145/3680207.3765605

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Lu, Y., Wang, J., Dong, X., Huang, Z., Liu, B., Wu, J.-M., & Wang, J. (2025). Demo: VI-Planning: Infrastructure-Assisted Real-Time Planning Optimization for Autonomous Driving. In ACM MobiCom ’25: Proceedings of the 2025 the 31st Annual International Conference on Mobile Computing and Networking (pp. 1245-1247). Association for Computing Machinery. https://doi.org/10.1145/3680207.3765605

@inproceedings{9205ec52c9d24357b0503f53d1b4de88,

title = "Demo: VI-Planning: Infrastructure-Assisted Real-Time Planning Optimization for Autonomous Driving",

abstract = "We propose VI-Planning, an innovative system that leverages the scene-level future occupancy grid maps predicted by the infrastructure as future drivable area references to directly optimize the planning trajectories of autonomous vehicles in real time. Since VI-Planning operates only at the autonomous vehicle{\textquoteright}s final output stage, without modifying the underlying system architecture, it can be plug- and-play for most autonomous driving systems. Moreover, VI-Planning employs a novel bitwise encoding mechanism to efficiently compress these maps, enabling practical transmission. The experimental results demonstrate that VI-Planning can achieve real-time planning optimization with extremely low bandwidth consumption, significantly enhancing the driving safety of autonomous systems. The source code and video demonstration of VI-Planning are available on GitHub: https://github.com/YANG-Deep/VI-Planning. {\textcopyright} 2025 Copyright held by the owner/author(s).",

author = "Yang Lu and Jie Wang and Xiaoyun Dong and Ziyao Huang and Bingyi Liu and Jen-Ming Wu and Jianping Wang",

note = "Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).; 31st Annual International Conference on Mobile Computing and Networking (ACM MobiCom 2025), ACM MobiCom {\textquoteright}25 ; Conference date: 04-11-2025 Through 08-11-2025",

year = "2025",

doi = "10.1145/3680207.3765605",

language = "English",

isbn = "9798400711299",

pages = "1245--1247",

booktitle = "ACM MobiCom {\textquoteright}25",

publisher = "Association for Computing Machinery",

address = "United States",

url = "https://www.sigmobile.org/mobicom/2025/index.html",

}

Lu, Y, Wang, J, Dong, X , Huang, Z , Liu, B, Wu, J-M & Wang, J 2025, Demo: VI-Planning: Infrastructure-Assisted Real-Time Planning Optimization for Autonomous Driving. in ACM MobiCom ’25: Proceedings of the 2025 the 31st Annual International Conference on Mobile Computing and Networking. Association for Computing Machinery, pp. 1245-1247, 31st Annual International Conference on Mobile Computing and Networking (ACM MobiCom 2025), Hong Kong, China, 4/11/25. https://doi.org/10.1145/3680207.3765605

Demo: VI-Planning: Infrastructure-Assisted Real-Time Planning Optimization for Autonomous Driving. / Lu, Yang; Wang, Jie; Dong, Xiaoyun et al.
ACM MobiCom ’25: Proceedings of the 2025 the 31st Annual International Conference on Mobile Computing and Networking. Association for Computing Machinery, 2025. p. 1245-1247.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Demo

T2 - 31st Annual International Conference on Mobile Computing and Networking (ACM MobiCom 2025)

AU - Lu, Yang

AU - Wang, Jie

AU - Dong, Xiaoyun

AU - Huang, Ziyao

AU - Liu, Bingyi

AU - Wu, Jen-Ming

AU - Wang, Jianping

N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

PY - 2025

Y1 - 2025

N2 - We propose VI-Planning, an innovative system that leverages the scene-level future occupancy grid maps predicted by the infrastructure as future drivable area references to directly optimize the planning trajectories of autonomous vehicles in real time. Since VI-Planning operates only at the autonomous vehicle’s final output stage, without modifying the underlying system architecture, it can be plug- and-play for most autonomous driving systems. Moreover, VI-Planning employs a novel bitwise encoding mechanism to efficiently compress these maps, enabling practical transmission. The experimental results demonstrate that VI-Planning can achieve real-time planning optimization with extremely low bandwidth consumption, significantly enhancing the driving safety of autonomous systems. The source code and video demonstration of VI-Planning are available on GitHub: https://github.com/YANG-Deep/VI-Planning. © 2025 Copyright held by the owner/author(s).

AB - We propose VI-Planning, an innovative system that leverages the scene-level future occupancy grid maps predicted by the infrastructure as future drivable area references to directly optimize the planning trajectories of autonomous vehicles in real time. Since VI-Planning operates only at the autonomous vehicle’s final output stage, without modifying the underlying system architecture, it can be plug- and-play for most autonomous driving systems. Moreover, VI-Planning employs a novel bitwise encoding mechanism to efficiently compress these maps, enabling practical transmission. The experimental results demonstrate that VI-Planning can achieve real-time planning optimization with extremely low bandwidth consumption, significantly enhancing the driving safety of autonomous systems. The source code and video demonstration of VI-Planning are available on GitHub: https://github.com/YANG-Deep/VI-Planning. © 2025 Copyright held by the owner/author(s).

UR - https://www.scopus.com/pages/publications/105023822910

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105023822910&origin=recordpage

U2 - 10.1145/3680207.3765605

DO - 10.1145/3680207.3765605

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9798400711299

SP - 1245

EP - 1247

BT - ACM MobiCom ’25

PB - Association for Computing Machinery

Y2 - 4 November 2025 through 8 November 2025

ER -

Lu Y, Wang J, Dong X , Huang Z , Liu B, Wu JM et al. Demo: VI-Planning: Infrastructure-Assisted Real-Time Planning Optimization for Autonomous Driving. In ACM MobiCom ’25: Proceedings of the 2025 the 31st Annual International Conference on Mobile Computing and Networking. Association for Computing Machinery. 2025. p. 1245-1247 Epub 2025 Nov 21. doi: 10.1145/3680207.3765605

Demo: VI-Planning: Infrastructure-Assisted Real-Time Planning Optimization for Autonomous Driving

Abstract

Conference

Bibliographical note

UN SDGs

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this