North Sea Deployment Shows How Quadruped Robots Can Be Commercially Useful
As much as we like writing about quadrupedal robots, it’s always been a little bit tricky to see how they might be commercially useful in the near term outside of specialized circumstances like disaster response. We’ve seen some hints of what might be possible from Boston Dynamics, which has demonstrated construction inspection with SpotMini, but that’s not necessarily a situation where a robot is significantly better than a human.
In September, ANYbotics brought one of their industrial quadrupeds, ANYmal, to an offshore power distribution platform in the North Sea. It’s very remote, and nothing much happens there, but it still requires a human or two to wander around checking up on stuff, a job that nobody wants.
A crucial task for energy providers is the reliable and safe operation of their plants, especially when producing energy offshore. Autonomous mobile robots are able to offer comprehensive support through regular and automated inspection of machinery and infrastructure. In a world’s first pilot installation, transmission system operator TenneT tested the autonomous legged robot ANYmal on one of the world’s largest offshore converter platforms in the North Sea.
The video does a good job of showing why a quadruped like ANYmal is ideal for these kinds of industrial environments. While it’s mostly flat, empty corridors, there are some stairs and tight spaces where ANYmal’s legs and adaptive shape are advantageous. A humanoid would almost certainly struggle, and while a tracked platform might do better, there are lots of small obstacles that ANYmal can simply step over. Since speed and efficiency aren’t a huge concern, a quadruped offers a good combination of the versatility of legs with the consistent stability of tracks or wheels.
Having said that, there are a few situations even in this demo video where ANYmal is not ideal—the poor little guy is on the short side, which makes it hard to read some of the gauges and indicators, and it looks like some electrical cabinets have to be left open for inspection since the robot can’t open them itself. These things could be solved without much work with a minimal redesign to environments like this to make them a little bit more robot friendly, which seems like not too much to ask to be able to have a robot patrolling out there instead of a human.
The obvious issue that ANYmal does have, of course, is that it’s much more of a problem detector than a problem solver—it can let you know if something’s wrong, but there’s not a lot that it can do to fix things. So, it’s still not about replacing humans completely, but rather about making their jobs suck less.
For more detail, we spoke with Péter Fankhauser, co-founder and chief business development officer at ANYbotics.
IEEE Spectrum: Why are the specific capabilities of ANYmalnecessary in this environment?
Péter Fankhauser: Operating a mobile robot in a real-world industrial setting requires solving a range of difficult problems. The most important capabilities are the autonomous and versatile mobility in large-scale, complex environments in combination with a variety of inspection tools. In an environment built for humans, ANYmal’s legs provide the means to travel all walkable surfaces including climbing steps and stairs and crawling through tight and narrow spaces. Onboard vision and lidar allow ANYmal to localize itself in the environment and plan a safe path over and around obstacles. The inspection payload includes a zoom camera, thermal cameras, and microphones to provide data for detailed situational awareness for the operator.
What were some of the biggest challenges you had to solve when deploying ANYmal? Anything that surprised you?
With help of the operator TenneT, we were able to prepare well for the deployment of ANYmal to make sure we wouldn’t hit any surprises. This included a detailed study of the requirements and tasks that needed to be solved and simulations based on the floor plans and virtual tours of the facility. Logistically, the efforts to comply with the high safety requirements for offshore work was quite intense. This included a one-week safety training for fire protection, helicopter escape, and survival on sea scenarios, and equipping our field team with the protective clothing. And of course, we had to make sure we had planned for any eventualities since one cannot quickly go to the hardware store when you’re out 100 km on the ocean.
To what extent would ANYmal realistically be able to replace a human in a situation like this?
We are still far away from replicating the human capability to understand context and manipulate objects and tools. So instead of trying to replace human workers, our goal is to extend the workforce with automated robotic inspection. This way, the operator can increase the safety and efficiency of their plants.
When will ANYmal be ready for long-term fully autonomous deployment? What are your plans for making this happen?
We are increasing the mission complexity and duration on a project-by-project basis. The next steps include monitoring over long distance (e.g., onshore-offshore) and long-term testing of the docking station. We will provide a fully commercialized product in the near future.
What other realistic commercial opportunities do you think there are for autonomous robots like ANYmal?
We currently work on a number of projects with the energy and manufacturing industry but also with construction, agriculture, underground productions, and general mobility. In these areas, an autonomous mobile robot can provide significant value over traditional approaches. What we have experienced in our work with ANYmal is that people have ideas for exciting opportunities we could not have found ourselves. In the future, the range of commercial opportunities will grow together with the capabilities of the robot.