Abstract
Sharing the sensor data collected by roadside infrastructure is an emerging paradigm for extending the perception of autonomous vehicles and improving driving safety. However, enabling perception sharing is challenging due to the high data rate of perception data, which incurs significant communication overhead. Previous systems have relied on Infrastructure-to-Vehicle (I2V) communication, which is susceptible to high mobility and scales poorly with traffic density. This demo presents Infrastructure-to-Road (I2R) beam-forming, a new paradigm that enables efficient perception sharing for infrastructure-assisted autonomous driving. We demonstrate BeamDrop, a prototype that strategically beamforms tailored point cloud segments to geographic cells, allowing a receiver that enters a cell to receive the needed navigation data without the overhead of coordinating with the infrastructure to adapt beamforming under mobility. © 2024 Copyright held by the owner/author(s).
| Original language | English |
|---|---|
| Title of host publication | ACM SIGCOMM Posters and Demos '24: Proceedings of the ACM SIGCOMM 2024 Conference: Posters and Demos |
| Publisher | Association for Computing Machinery |
| Pages | 89-91 |
| ISBN (Print) | 9798400707179 |
| DOIs | |
| Publication status | Published - Aug 2024 |
| Event | 2024 Annual Conference of the ACM Special Interest Group on Data Communication (SIGCOMM 2024) - University of New South Wales, Sydney, Australia Duration: 4 Aug 2024 → 8 Aug 2024 Conference number: 38 https://conferences.sigcomm.org/sigcomm/2024/ |
Publication series
| Name | SIGCOMM Posters and Demos - Proceedings of the SIGCOMM Poster and Demo Sessions, Part of: SIGCOMM |
|---|
Conference
| Conference | 2024 Annual Conference of the ACM Special Interest Group on Data Communication (SIGCOMM 2024) |
|---|---|
| Country/Territory | Australia |
| City | Sydney |
| Period | 4/08/24 → 8/08/24 |
| Internet address |
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).Funding
We sincerely thank the anonymous reviewers for their valuable feedback and constructive suggestions. This work is supported in part by the Research Grants Council (RGC) of Hong Kong under General Research Fund No. 14222222.
Research Keywords
- infrastructure-assisted autonomous driving
- smart roadside infrastructure
- V2X
Publisher's Copyright Statement
- This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/
