Clearpath's OTTO Robot Can Autonomously Haul a Ton of Stuff

This robot can take just about whatever you want to just about wherever you want it

4 min read
Clearpath's OTTO Robot Can Autonomously Haul a Ton of Stuff
Image: Clearpath Robotics

Today, Clearpath Robotics (best known for its rugged, ROS-friendly, and infallibly black and yellow robotic platforms) is announcing OTTO, a “heavy-load material transporter” that can carry a ton of stuff around warehouses, fully autonomously. Actually, “a ton of stuff” is underselling OTTO’s capabilities, since it can happily roll away with one metric ton and a half of payload: that’s a staggering 1500 kilograms (3300 pounds), or more than 22 robotics bloggers. Oof.

In addition to its enourmous payload, the key thing to know about OTTO, announced today at RoboBusiness in Santa Clara, Calif., is that it doesn’t require any infrastructure to navigate. OTTO doesn’t need barcodes on the floor (like Kiva Systems, er, Amazon Robotics warehouse robots), lights on the ceiling, beacons in the halls, RFID tags on the walls, guide dogs, interns with joysticks, or any other form of navigation devices. It’s got 20-meter lasers front and back (with an option for 50-meter range), and can localize against an existing basemap with an accuracy of about an inch. OTTO has no problem dealing with changing environments and maneuvering around inconvenient obstacles, including people (even moving ones). And if you won’t get out of its way, OTTO will use flashing LEDs and “polite” audio prompts. 

For a robot of this size (unloaded, it’s 500 kg), and with a brisk top speed of 2 m/s (4.5 mph), safety is a critical aspect of autonomy. Fully loaded, OTTO’s a total mass of 2,000 kilograms, which even when moving at low speeds represents a substantial amount of energy. So obviously, making sure OTTO is safe to work around is a priority for Clearpath, and they’re confident that they’ve got safety around humans nailed. Confident enough, in fact, that they’re already in the middle of five pilot programs. The first of those programs is in a General Electric facility, and it’s not a coincidence that GE Ventures has also just become a strategic investor in Clearpath for an undisclosed sum.

Here’s the rest of the specs that you’ve been waiting for:

img

Custom paint? Bring on the flames!

Yesterday, we spoke with Matt Rendall, CEO of Clearpath, about where OTTO came from and how likely it is to flatten us if we stand in front of it.

IEEE Spectrum: How long have you been working on OTTO?

Matt Rendall: We’ve been working on OTTO for about two years. We wanted to make sure that we didn’t release the product prematurely—as we transition into an industrial category, there’s a lot less forgiveness. If you look at autonomous mining, there have been companies early to the game that released autonomous vehicles a little bit prematurely, and because of that, there have been expectations that were not met, and it sort of stagnated the industry, I think.

So what made you decide two years ago that OTTO was the thing to create?

One of the great things about the work that we’ve been doing for the last five or six years in the research market is that we get exposed to basically every application for mobile robots you can imagine, across whatever industry. What that allows us to do is gain access to a tremendous dataset, and understand competitive factors, willingness to buy, pain points, technology readiness, internal company capabilities, pretty much everything. Of all of the different industries that were pulling on us to work in research and development, materials handling was one of the strongest, and so we began to investigate that industry and try to understand the problems in that space very well, and figure out how we could shape the technology we’d been working on into a compelling product. And I think that’s what OTTO represents for us.

How does OTTO differentiate itself from other materials transport robots?

As the market has matured, we’ve seen a lot of robotics companies come up with small form factor robots, call it 200-pound or less payloads. Dealing with a heavier load is a lot more challenging because of the safety considerations and the mechanical engineering considerations. Our logic was, everything that gets shipped comes into a dock on a pallet and leaves a dock on a pallet, so our system should be very well equipped to handle a pallet. If we can do that, we’ll have the most flexibility of any robot to accommodate different use cases in different environments.

A robot this big definitely needs to be safe enough to operate around people, right?

The vehicle can move at about 2 m/s, and we do that in an industrially safe manner. We’re working to maintain compliance with industrial safety ratings; it’s a bit of a challenge in the industrial space right now because the regulatory bodies and the standards agencies really haven’t caught up to the technology yet, so we’re doing our best to understand the certification ecosystem to make sure our system is compliant for safe operation in an industrial environment in collaboration with humans.

And what’s next after OTTO? Maybe a mobile manipulator?

We’ve got a lot of experience with mobile manipulation. I think in the industrial space, you really need to release a polished product that can meet exactly the expectations that it’s promising. Mobile manipulation, in our experience, still has several years before it’s going to be able to meet the promises that it’s making, at least in an employed industrial environment where the only thing that matters is throughput, uptime, and return on investment. It’s going to be something that we continue to experiment with, but our focus right now is just straight material transport.

Clearpath may only be experimenting with mobile manipulators, but here are some interesting potential modular attachments:

img

OTTO is available now, and costs somewhere between free and a million dollars. We wish we could be more helpful, but Clearpath isn’t talking pricing, at least partially because OTTO has to be integrated into your existing warehouse in such a way that you can’t just buy a robot straight up. However, we were told that it does not cost more than a Grizzly, so if you bought one of those, leave us a comment so that we can at least get an order of magnitude.

[ OTTO ]

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
LightGreen

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

"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.

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