CoWear: Collaborative Inertial Localization with Multi-Device Wearables
CoWear: Towards Collaborative Wearable Inertial Localization with Multiple Smart Devices
CoWear introduces a dataset and framework for collaborative inertial localization using smartphones, smartwatches, and smart glasses. Multi-device fusion improves displacement and trajectory accuracy compared to individual device estimates.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
participants
>30
walking sessions
>300
aggregate device trajectories
>30 hours
aggregate device trajectories
100
View original evidence
and more than 30 hours and 100 km of aggregate device trajectories
Open source S3distance
100
View original evidence
and more than 30 hours and 100 km of aggregate device trajectories
Open source S3
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
dataset contains over 30 participants, over 300 walking sessions, and more than 30 hours and 100 km of aggregate device trajectories, with each device individually tracked by motion capture. To enable collaboration across distinct body motions, we train role-specific estimators to predict the displacement of a common reference device over synchronized temporal windows. Their predictions are transformed to the world f
Open source S3
rame using gyroscope integration and fused according to learned uncertainty. Experiments using phone, glasses, and watch as reference targets show that multi-device fusion consistently improves both displacement and trajectory rollout accuracy over individual-device estimation. CoWear provides a dataset and reproducible baseline for studying collaborative inertial localization across heterogeneous consumer wearables.
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org