PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
November 9, 20250 citationsOpen Access

Multimodal-Wireless: A Large-Scale Dataset for Sensing and Communication

View Full Paper
TMTianhao MaoLLLe LiangJYJie Yang

Key Points

  • The dataset comprises approximately 160,000 frames collected across four virtual towns and three weather conditions.
  • Key features include various sensing modalities such as radar and inertial measurement units that enhance communication capabilities.
  • Analysis using this dataset supports innovative applications like collaborative perception and beam prediction.
  • Further exploration of this dataset may enable advancements in wireless communication and multimodal sensing.

Abstract

This paper presents Multimodal-Wireless, an open-source multimodal sensing dataset designed for wireless communication research. The dataset is generated through an integrated and customizable data pipeline built upon the CARLA simulator and Sionna framework. It contains approximately 160,000 frames collected across four virtual towns, sixteen communication scenarios, and three weather conditions, encompassing multiple sensing modalities--communication channel, light detection and ranging, RGB and depth cameras, inertial measurement unit, and radar. This paper provides a comprehensive overview of the dataset, outlining its key features, overall framework, and technical implementation details. In addition, it explores potential research applications concerning communication and collaborative perception, exemplified by beam prediction using a multimodal large language model. The dataset is open in https://le-liang.github.io/mmw/.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Mao et al. (2025) studied this question.

synapsesocial.com/papers/690fdcdaf60c54d04ea38126https://doi.org/10.48550/arxiv.2511.03220
Ask AI
Helpful
Bookmark
Share
View Full Paper