Home        Store        Learn        Blog

What does autonomy in marine robotics mean to you?

I have an open ended question for anyone here:

What does autonomy in marine robotics mean to you and what do you hope to get from it?

What do you hope that autonomy will allow you to do in the future? How will autonomy make marine robotics more useful to you?

The reason I ask this is because we’ve seen a striking increase in interest in autonomy and AI over our past few customer interest surveys. In 2016, 31% of respondents were interested in autonomy and AI. In 2018, it was 39% and in 2021 it was 51% or survey respondents. Interest is clearly growing.

But, “autonomy” is a huge category and can mean a lot of different things to different people. What does it mean to you and what do you hope to get from it?

6 Likes

In the World that I work in … sending ET out on its own and expecting it to do the mission package you programmed it to do with the run-time life that you have built it for and being able to get the data back to the home craft by either returning or a communications with the launching platform or others before it goes to the bottom of the ocean somewhere.

So the big show killers are Navigation, Power, Sensors and Communications. Those all are expensive hurdles to jump. If I had to rank life, I would put Power at #1 because nothing else works without it and then very accurate Navigation or homing capability so you don’t loose a platform.

Communications next because without that you might as well leave it on the kitchen table and come back after a while and stare at it. Same results without having any data from the platform and last but not least, depending on what you want to do, is the Sensor suite.

1 Like

Thanks, Harold! I agree - all of those systems are absolutely critical. You can’t really start thinking about autonomy until the basic system is working and working very reliably.

1 Like

Hey Rusty,

For us, it is driving to the data with an operator that doesn’t miss something or fall asleep. We have focused for years now on GPS Denied and -C2 (negative or no Command & Control) operations, as the logistical resources for manned-unmanned deployments are prohibitive.

And, sometimes the ‘roomba mode’, where we just wander until we find something interesting, provides the best overall picture of what is happening.

So, we began focusing on data-centric logic in our control theories. If we can pull data from our sensors into the navigational logic, then we can perform simple rule-based autonomy from there.

Example:

Have the USV conduct a surface water quality profile along the WP route (or grid). If the indicated parameters (say Chlorophyll A, temperature, 1m current direction & velocity, and DO) exceed threshold values, position keep and conduct a vertical profile. If the vertical profile indicates a thermocline with different variables, launch ROV and conduct a sinusoidal vertical profile from new WP1 to WP2 along the predominant subsurface current heading.

We can do all of this today, but it does not use AI as most people want to believe. I don’t think we are even close to that yet, as I would have no idea how to train the algorithm. We can, however, stack a bunch of rules into a flow program and conduct a mission. Think of those like macros or scripts. And, each macro can call on another - sort of like we do in CNC.

Today we can pull over 1000 parameters (water quality, Wx, physical, navigational, performance) into this logic - depending on the types of sensors installed. That was a lot of work and required a ton of code to translate sometimes proprietary vehicle CAN or sensor messages into a common format.

So, to really answer your question - why do we need autonomy in the first place? To create a force multiplier and find the data of interest so we can make new and informed regulation, compliance levels, reclamation, and restoration.

We are also very interested in marsupialism and further increasing the old ‘swarming’ concepts in autonomy.

Chandler

1 Like

Hey Harold,

Power is indeed a huge challenge. We have been trying to slay that dragon for a while and have certainly tried all the trick technologies (hybrids, battery chemistries, fuel cell, etc.).

In the end, we are attacking the issue in the most basic and analog way possible in two ways. One, having control logic that helps the asset perform most efficiently is paramount. Why is the asset going North on its mission if that is into the wind or current? Can we take external environmental data or observation and optimize our mission grid?

Second, low power modes. Doing everything possible to determine why you use energy and optimize the heaviest loads is a main focus. Why do we have ballast weight if we could replace that with battery weight?

On the comms front, becoming communications agnostic was a huge benefit. We used to be adamant on the frequency or radio brands we used. Then, we began creating radio modules, so we could create failover.

But far and away the most beneficial was looking at every possible way to cut that link requirement. Put the smarts on the asset, and let it go. Yes, we need situational awareness and safety - but a text message from a USV miles away like “I’m on mission and conducting survey grid M01, no issues, completion with estimated 36% energy reserves” goes a long way to keeping everyone satisfied and assured things are going well…

Chandler, our company makes some crazy battery technology that has high power densities. It is a once shot use, but you can swap out the “power” area. Take a look at this link.

I have worked with these guys on some stuff for testing purposes; however, I don’t know if they sell the battery packs commercially. The other thing is I don’t think the price is going to be something in the hobby market but scaling upward there could be openings for use.

Thanks for the link - I wonder if that UUV / AUV tech was part of the OceanServer / Iver acquisition by L3?

Wow - combining smart usage and smart power certainly gives us more reach.

I don’t know for sure … I know we acquired the guys who make the IVER. Next time I see the Borg Queen I will asked if they have been assimilated yet :slight_smile: