The July 2022 issue of IEEE Spectrum is here!

Close bar

Competition Spurs Robotics and AI Innovations for Maritime Challenges

ASPIRE’s grand technical challenge promises to introduce a new technological paradigm to maritime environments

4 min read
A swarm of drones flies over ships

The competition will leverage AI and robotics to develop an entirely autonomous system for solving maritime problems that arise from piracy, illegal fishing, and smuggling.


This is a sponsored article brought to you by MBZIRC Maritime Grand Challenge.

Strategies for driving innovation, whether on the corporate or the sovereign-state level, is wrought with challenges. Abu Dhabi-based ASPIRE has adopted a creative approach to overcoming many of these challenges by creating grand technical challenge competitions to drive the development of innovative technologies. These challenges are essentially opening up to competition the development of solutions to key industrial and societal problems and offering prize money to the winners.

Currently, ASPIRE is organizing a challenge called The Mohamed Bin Zayed International Robotics Challenge (MBZIRC). The MBZIRC had two previous iterations that were organized by Khalifa University in Abu Dhabi. In this latest version, ASPIRE has taken the reins of a challenge in which AI and robotics will be leveraged to develop an entirely autonomous system for solving maritime problems that arise from piracy, illegal fishing, and smuggling.

“We picked this challenge because it's a challenge that affects any country that's got a coastline,” said Dr. Arthur Morrish, the chief executive officer of ASPIRE. “Both robots and AI are really good at doing the dull, the dirty, and the dangerous. And the maritime environment actually lends itself really well to those kinds of applications.”

The basic aim of the challenge is to find the proverbial needle in a haystack using a combination of unmanned aerial vehicles (UAVs) and an unmanned surface vessel (USV) to search an area that the Coast Guard would have to search in person to find a bad actor vessel.

Some of the restrictions of the challenge are that you can only have between 5 and 20 UAVs, you can have only one USV (provided by ASPIRE), and you cannot use Global Navigation Satellite System (GNSS) navigation. This is because the challenge is not trying to determine how good your GPS tracking code is or your GLONASS tracking code or your Galileo tracking code. What is of interest is how good are your tracking algorithms for ensuring your UAV swarms work together.

“When we were thinking about putting this challenge together, we heard from people that said, ‘Somewhere between now and the next five to seven years, there's no reason to believe that non-state actors that have high-value target-- high-value cargos aren't going to be able to spoof GPS.’ So, just from both a police and a coast guard perspective, doing this in a GNSS denied environment is probably the right thing to do,” said Morrish.

The participants in the challenge find the target vessel by using an initial police report that provides some minor details about the boat, i.e., its color, some digits in its identification number, etc. At that point, everything to locate the vessel and extract any contraband from it must be accomplished autonomously.

“Robots and AI are really good at doing the dull, the dirty, and the dangerous. And the maritime environment actually lends itself really well to those kinds of applications.”

—Dr. Arthur Morrish, CEO of ASPIRE

The challenge runs in three phases. There's a white-paper phase. There's a simulation phase. And then there's the demonstration phase where the participants actually have to build it and then compete. The white paper phase closed on January 31st. The participants now have six months to develop their simulations. After the simulations are judged, approximately five teams will need to put their solutions to the test on the water off the coast of Abu Dhabi in the summer of 2023.

For the simulation phase of the challenge, MBZIRC will be using the same company that did the simulation for the DARPA Subterranean Challenge that was held last September to provide the simulation environment. “Each team will then take what they propose, simulate it in the simulation environment, and at the end of the day, we will look at all those simulations in the simulation environment and pick the top five,” added Morrish.

The final five participants who make it to the physical testing phase will split a $500,000 prize and then the final winner will take home a grand prize of $2 million. Perhaps more important than the prize money is an opportunity for ASPIRE to help them commercialize the technology.

Rendering of drone flying over boats.

Through the grand challenge, ASPIRE seeks to bridge the gap in current robotic capabilities and real-world requirements by pushing the boundaries of technology.


“We're asking the teams for a non-exclusive license to their IP because there are people out there that are really interested in this technology,” said Morrish. “We want to help the teams commercialize it. Of course, if they want to commercialize it on their own, that's fine. That's why it's a non-exclusive license. But if they don't commercialize it, then we will use our non-exclusive license to help keep it moving because there's people that want this kind of technology.”

Morrish is emphatic that this challenge will lead to the development of a “system of systems” solution. The purpose of this challenge is not just to develop a UAV that may have some AI in it to go out and do something. To Morrish that's really one system doing one thing.

“When I say a system of systems, what I'm thinking about is I've got 20 UAVs, I've got a USV, and I've got a robotic arm. I have to control all of those in an uncontrolled environment doing a specific task, and it's all got to be done autonomously,” said Morrish.


The Mohamed Bin Zayed International Robotics Challenge (MBZIRC) will be held in the UAE capital, Abu Dhabi, in June 2023, where tech innovators will participate to seek marine safety and security solutions to take home more than US $3 million in prize money.

Organized by ASPIRE, the dedicated technology programme management pillar of the Advanced Technology Research Council (ATRC), the overarching advanced technology research body in Abu Dhabi, UAE, the MBZIRC is held every two years.

The upcoming edition, called MBZIRC Maritime Grand Challenge, focuses on real-time solutions to maritime safety and security challenges and seeks to claim its place among the largest and most prestigious AI and robotics competitions in the world.

For more information, visit

In addition to the UAVs, USV and robotic arms, the system of systems will need to include tracking and location algorithms and communication systems between the UAVs, which you wouldn't have if it was just a USV going out and doing something. “There are a number of systems that are working together as a larger system,” added Morrish.

More broadly, ASPIRE’s aim for these grand technical challenges is to fast track the development of innovative technologies in the United Arab Emirates (UAE). The Emirates want to move from a resource-based economy to a knowledge-based economy, according to Morrish.

“We're building on the shoulders of some really excellent work that was done in the first two phases of the Mohamed Bin Zayed International Robotics Challenge, which was run by Khalifa University,” said Morrish. “We intend to run this particular challenge for a long time. I want this to be a world-class robotics challenge.”

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman

“I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

This article is part of our special report on AI, “The Great AI Reckoning.”

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓Show less