Self-Driving Ships

By | October 16, 2018

The Verge reports on a partnership between Intel and Rolls-Royce to build “self-driving” ships. The article blends discussion of three different scenarios:

  1. autonomous long-haul shipping
  2. remote-control operation
  3. pilot assistance for docking and similar scenarios

I have almost no knowledge of shipping or boats or the ocean or even water. I do know how to swim.

Nonetheless, I speculate that #3 seems the most useful.

The gains achieved by removing a human crew from a cargo ship seem minimal. In the context of a massive shipping vessel stuffed with rectangular containers, the cost of the human crew just doesn’t seem that significant.

But in the context of the close quarters of a harbor or port, I can imagine that there might be substantial performance gains from automation or pilot assistance.

Again, knowing not much about the actual constraints of maritime shipping, I could imagine harbors as bottlenecks, where ships get queued up in lines, waiting for relatively scarce tugboats and harbor pilots. Furthermore, ships do not turn on a dime, and so presumably need to maintain substantial buffer distances.

Autonomous shipping in close quarters might improve both the latency of docking (by allowing ships to skip the line) and the throughput (by allowing ships to shrink buffer distances).


Self-Driving Ships was originally published in Self-Driving Cars on Medium, where people are continuing the conversation by highlighting and responding to this story.

Read the original article

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.