Coordination and Communication in High Latency Underwater Networks

This direction is split into other directions: hybrid acoustic-optical communication, underwater acoustic communication challenges, underwater signal attenuation. Its last version stays readable and citable here.

Version 1 of 1117 papers137 conceptsfrozen 2026-10-04

In the terrestrial world, we take for granted that wireless signals travel at the speed of light. For a Wi-Fi router or a cell tower, the time it takes for a signal to reach a device is effectively zero compared to the time it takes to process the data. But once you submerge a robot in the ocean, the physics of communication flip upside down.

Seawater is a "wireless dead zone" for the electromagnetic waves we use on land. Radio frequencies, Wi-Fi, and GPS signals are absorbed by saltwater within meters. To communicate over any significant distance, researchers must turn to acoustic waves—sound. However, sound travels five orders of magnitude slower than light. This shift creates a fundamental "space-time coupling" where the delay of a message is often longer than the message itself, requiring a total rethink of how autonomous systems coordinate.

The Propagation Bottleneck

In traditional networking, we assume that if two nodes talk at the same time, they will hear the collision immediately. In underwater acoustic networks (UANs), as Josko Catipovic and S. Etchemendy pointed out in their foundational work on the Acoustic Local Area Network (ALAN), the propagation delay is often equal to or greater than the duration of the data packets.

This creates a "sluggish" environment where nodes are essentially shouting at each other from across a vast canyon. By the time a robot receives a "stop" command, it may have already drifted into an obstacle. Yan Wang and Fei Ji describe this as space-time coupling, where packet collisions depend not just on when you send, but where you are located. Standard collision-avoidance protocols break down here because the network state is never synchronized in real-time.

Shared Autonomy and the Latency Gap

Because of this lag, teleoperating an underwater vehicle is like trying to drive a car while looking through a camera feed that is five seconds behind. To solve this, researchers like Saverio Iacoponi and Federico Renda employ shared autonomy.

Instead of an operator controlling every fin beat of a robotic fish, the operator sends high-level "intent" (e.g., "move to these coordinates"), and the robot’s local reactive system handles the low-level physics and obstacle avoidance. This approach, pioneered for underwater use by R. Peter Bonasso, allows the vehicle to maintain robust performance even when the communication link is intermittent or lagging.

Fitting Big Data into Tiny Pipes

If latency is the first hurdle, bandwidth is the second. Acoustic modems typically offer data rates between 0.1 and 15 kbps—roughly the speed of a 1980s dial-up modem. Yujia Yang and Chris Manzie note that these narrow bandwidths make it impossible to exchange the high-fidelity state information usually required for swarm coordination.

To overcome this, the research has moved toward two extremes:

  1. Extreme Compression: Systems like AquaScope use generative AI to reconstruct images from tiny amounts of data, allowing color photos to be sent via sound in seconds rather than minutes.
  2. On-Device Intelligence: Rather than sending raw sensor data to the surface, the Internet of Underwater Things (IoUT) paradigm, discussed by Tayyaba Zainab, suggests that seafloor nodes should use AI to detect "patterns of interest" and only transmit the summary. Nancy Victor further proposes Federated Learning, where robots only exchange model updates rather than raw datasets, bypassing the bandwidth bottleneck entirely.

Digital Twins and Virtual Prototyping

Testing these complex behaviors in the open ocean is prohibitively expensive and risky. A single software bug can result in the loss of a million-dollar AUV. To mitigate this, Alexander Barbie and Wilhelm Hasselbring have championed the use of Digital Twin Prototypes (DTPs).

By creating a virtual mirror of the underwater environment and the robotic assets, researchers can run "Software-in-the-Loop" tests that simulate the exact acoustic constraints of the target deployment site. This allows for the optimization of serialization schemes and coordination logic before the first piece of hardware ever touches the water.

Alternative Modalities: Light and Gestures

When acoustic communication is too slow and radio is impossible, researchers look for "middle ground" physics. Nasir Saeed explores Underwater Optical Wireless Communications (UOWC), which uses lasers or LEDs to achieve gigabit speeds. The catch? Light only travels tens of meters and requires perfect alignment.

Perhaps most creatively, Karim Koreitem and Gregory Dudek have demonstrated communication via gestures. By having one robot perform specific 3D orientations (gestures) that a following robot decodes visually, they bypass the need for modems entirely for close-range coordination.

The common thread across this research is a move away from "perfect" communication. Whether through shared autonomy, predictive routing, or digital mirroring, the goal is to build systems that expect—and can handle—the silence and lag of the deep ocean.

Papers in this version

Showing 60 of 117 papers.

History & citationVersion 1 · 2026-10-04

Split into other directions · Permanent link

View frozen version 1

Cite this direction

Latest version (a living page):

@misc{lacuna_coordination_and_communication_in_high_l_0a016106,
  title = {Coordination and Communication in High Latency Underwater Networks},
  author = {{Lacuna}},
  howpublished = {Lacuna research direction},
  year = {2026},
  url = {https://lacuna.tiptreesystems.com/direction/coordination-and-communication-in-high-latency-underwater-networks/rdr_0a0161069c2e47df8c13f68b60edc828},
  note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}

This exact version (version 1, frozen text):

@misc{lacuna_coordination_and_communication_in_high_l_0a016106_v1,
  title = {Coordination and Communication in High Latency Underwater Networks},
  author = {{Lacuna}},
  howpublished = {Lacuna research direction},
  year = {2026},
  url = {https://lacuna.tiptreesystems.com/direction/coordination-and-communication-in-high-latency-underwater-networks/rdr_0a0161069c2e47df8c13f68b60edc828/v/1},
  note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}