Drones. Self-driving cars. Flying robots. If you believe the headlines of the last few years, ground transportation in the future will replace robotic stagecoaches and devices that practically do not require human intervention, well, except that only download the application. But what about the remaining 70% of the planet’s surface — the part that is covered by water? Of course, there are already underwater drones capable of recording 4K video for the next BBC documentary. Remote-controlled vehicles (ROV) are capable of going down thousands of meters to explore ocean openings or repair industrial infrastructure.
However, most robots that are now on water or under water are still heavily dependent on the human factor. And this is understandable, given the unstructured environment of the seas and weak communication capabilities for anything that moves below the waves. Autonomous underwater vehicles (AUV) are probably the closest to intelligent ocean machines today, but most often follow pre-programmed instructions.
A new generation of waterfowl robots that conquer the seas-and use artificial intelligence, machine vision, advanced sensors and other technologies — is ready to dive to the depth. Let’s see what the engineers have prepared for us.
Nick Radford, CTO of Houston Mechatronics Inc. (HMI), hesitates to say the word “autonomy”, talking about the best creation of its startup — Aquanaut. He preferred the term “overall control”.
Aquanaut seems to come down from the screen of the movie”transformers”. The underwater robot begins each mission in the form of a submarine capable of autonomously overcoming up to 200 kilometers on the battery, depending on the destination.
When Aquanaut reaches its destination-the oil and gas industry is first in line to change the HMI-its four specially designed and built linear actuators are taken over. Aquanaut decomposes into a robot with a head, upper torso and two manipulators, while remaining afloat.
The moment of insight, when the engineer realized how to turn the submarine into a robot, arose on the day when the office laid out the table. The answer suddenly seemed obvious.
“We’re just going to build a big, giant, underwater folding table,” Radford says.
The hardware was not the only problem of the team, consisting of veterans of robotics NASA like Radford, which they followed to solve it. To get rid of the expensive support vessels and large teams of people needed to manage traditional ROV, Aquanaut had to be able to feel its environment in great detail and transmit this information back to headquarters using the underwater acoustic communication system that existed even before the Internet connection over the telephone line.
To solve the problem of low bandwidth, HMI equipped Aquanaut with a machine vision system consisting of acoustic, optical and laser sensors. All this dense data is compressed using its own HMI technology and transmitted to a single operator-the person who controls Aquanaut by means of a conventional computer mouse. Even the joystick is not required.
“I do not know anyone who has achieved this level of autonomy in dealing with the environment,” says Radford.
Earlier this year, HMI received $ 20 million from Transocean, one of the world’s largest offshore drilling contractors. That should be enough to finish the Aquanaut prototype, which, according to Redford, is 99.8% ready. High-profile demonstrations are already planned for early next year, and commercial deployment is planned for 2020.
“What gives us an incredible advantage is that we were born and raised to build robotic systems for remote locations,” Radford says. “This is my life, I bet on it.”
On cruise control
Meanwhile, a startup from Boston is trying to solve the problem of ensuring the autonomy of ships at sea. Sea Machines received about 12.5 million dollars of investment, in the list of investors was Toyota AI.
Sea Machines is looking for inspiration in the Autonomous vehicle industry by developing so-called “ship reconnaissance” systems that can be modified to existing commercial vessels or newly built working vessels.
Earlier this year, the startup announced a deal with Maersk, the world’s largest container shipping company, to deploy an artificial intelligence, computer vision and LiDAR system on a new container ship of the Danish company. The technology works similarly to advanced driver assistance systems that are installed in cars to avoid hazards. The proof of concept will lay the Foundation for a future Autonomous collision avoidance system.
Not only startups are trying to create Autonomous navigation systems. Radford noted that Rolls Royce is a leader in the development of Autonomous ships. Its Intelligence Awareness system uses almost all types of high-profile modern technologies: neural networks, augmented reality, virtual reality and LiDAR.
In augmented reality mode, for example, a live stream of video from the ship’s sensors could detect static and moving objects simultaneously, overlaying the scene with information about the types of ships in the area, as well as the distance to them, the course and other data.
While safety is the primary motivation for ship automation — more than 1,100 ships have been lost in the last decade — these new technologies can make ships more efficient and less expensive to operate.
Sea hunting meets science
Marine robots can play an important role in saving the seas from environmental threats. In particular, from such threat as the lionfish. According to the ocean support Fund, the population of these poisonous endemic fish is growing rapidly as the fish find new habitats and eat thirty times more than fits into the stomach. It is rapidly reducing the population of young reef fish. Scientists and engineers are developing Autonomous robots to destroy the invasive predator.
At Worcester Polytechnic, for example, students build robots with spears that use machine learning and computer vision to distinguish the lionfish from other aquatic species. Students have trained algorithms on thousands of different images of winglets. The result was a machine for killing winglets, which boasts an accuracy of more than 95%.
A new wave of smart, independent robots is diving, swimming and traveling the ocean and its deepest depths. These Autonomous systems are not necessarily designed to replace people — rather, to enable us to go where we could not before without risk, or to improve safety at sea. Perhaps these innovations will inspire robots that will someday plunge into the depths of water planets away from Earth.