Enabling ‘See-and-Point’ Communication between Robots
Published in IEEE Transactions on Mobile Computing, 2026, 2026
Recommended citation: Huangwei Wu, Weiguo Wang, Meng Jin, Zhuxuan He, Qi Cao, Xinbing Wang, Chenghu Zhou. "Enabling See-and-Point Communication between Robots," IEEE Transactions on Mobile Computing, 2026. https://doi.org/10.1109/TMC.2026.3665613
[CCF-A] Sole first author
We propose a physical-world addressing mechanism that uses multipath channel profiles as physical addresses, combined with vision-driven real-time scene-to-channel conversion. Robots can establish precise directional communication links using only an onboard camera, without pre-built network infrastructure. The end-to-end prototype achieves 99.58% connection matching rate, 0.3–0.5 m spatial resolution, and <412 ms connection latency at up to 2 m/s mobility.