What’s Going on With Amazon’s “High-Tech” Warehouse Robots?

Amazon describes these as high-tech autonomous vehicles, but the technology looks like it’s already out of date

5 min read
Amazon Robotics' Bert AMR
Screenshot: Amazon Robotics

Amazon’s innovation blog recently published a post entitled “New technologies to improve Amazon employee safety,” which highlighted four different robotic systems that Amazon’s Robotics and Advanced Technology teams have been working on. Three of these robotic systems are mobile robots, which have been making huge contributions to the warehouse space over the past decade. Amazon in particular was one of the first (if not the first) e-commerce companies to really understand the fundamental power of robots in warehouses, with their $775 million acquisition of Kiva Systems’ pod-transporting robots back in 2012.

Since then, a bunch of other robotics companies have started commercially deploying robots in warehouses, and over the past five years or so, we’ve seen some of those robots develop enough autonomy and intelligence to be able to operate outside of restricted, highly structured environments and work directly with humans. Autonomous mobile robots for warehouses is now a highly competitive sector, with companies like Fetch Robotics, Locus Robotics, and OTTO Motors all offering systems that can zip payloads around busy warehouse floors safely and efficiently.

But if we’re to take the capabilities of the robots that Amazon showcased over the weekend at face value, the company appears to be substantially behind the curve on warehouse robots.

Let’s take a look at the three mobile robots that Amazon describes in their blog post:

“Bert” is one of Amazon’s first Autonomous Mobile Robots, or AMRs. Historically, it’s been difficult to incorporate robotics into areas of our facilities where people and robots are working in the same physical space. AMRs like Bert, which is being tested to autonomously navigate through our facilities with Amazon-developed advanced safety, perception, and navigation technology, could change that. With Bert, robots no longer need to be confined to restricted areas. This means that in the future, an employee could summon Bert to carry items across a facility. In addition, Bert might at some point be able to move larger, heavier items or carts that are used to transport multiple packages through our facilities. By taking those movements on, Bert could help lessen strain on employees.

This all sounds fairly impressive, but only if you’ve been checked out of the AMR space for the last few years. Amazon is presenting Bert as part of the “new technologies” they’re developing, and while that may be the case, as far as we can make out these are very much technologies that seem to be new mostly just to Amazon and not really to anyone else. There are any number of other companies who are selling mobile robot tech that looks to be significantly beyond what we’re seeing here—tech that (unless we’re missing something) has already largely solved many of the same technical problems that Amazon is working on.

We spoke with mobile robot experts from three different robotics companies, none of whom were comfortable going on record (for obvious reasons), but they all agreed that what Amazon is demonstrating in these videos appears to be 2+ years behind the state of the art in commercial mobile robots.

We’re obviously seeing a work in progress with Bert, but I’d be less confused if we were looking at a deployed system, because at least then you could make the argument that Amazon has managed to get something operational at (some) scale, which is much more difficult than a demo or pilot project. But the slow speed, the careful turns, the human chaperones—other AMR companies are way past this stage.

Kermit is an AGC (Autonomously Guided Cart) that is focused on moving empty totes from one location to another within our facilities so we can get empty totes back to the starting line. Kermit follows strategically placed magnetic tape to guide its navigation and uses tags placed along the way to determine if it should speed up, slow down, or modify its course in some way. Kermit is further along in development, currently being tested in several sites across the U.S., and will be introduced in at least a dozen more sites across North America this year.

Most folks in the mobile robots industry would hesitate to call Kermit an autonomous robot at all, which is likely why Amazon doesn’t refer to it as such, instead calling it a “guided cart.” As far as I know, pretty much every other mobile robotics company has done away with stuff like magnetic tape in favor of map-based natural-feature localization (a technology that has been commercially available for years), because then your robots can go anywhere in a mapped warehouse, not just on these predefined paths. Even if you have a space and workflow that never ever changes, busy warehouses have paths that get blocked for one reason or another all the time, and modern AMRs are flexible enough to plan around those paths to complete their tasks. With these autonomous carts that are locked to their tapes, they can’t even move over a couple of feet to get around an obstacle.

I have no idea why this monstrous system called Scooter is the best solution for moving carts around a warehouse. It just seems needlessly huge and complicated, especially since we know Amazon already understands that a great way of moving carts around is by using much smaller robots that can zip underneath a cart, lift it up, and carry it around with them. Obviously, the Kiva drive units only operate in highly structured environments, but other AMR companies are making this concept work on the warehouse floor just fine.

Why is Amazon at “possibilities” when other companies are at commercial deployments? 

I honestly just don’t understand what’s happening here. Amazon has (I assume) a huge R&D budget at its disposal. It was investing in robotic technology for e-commerce warehouses super early, and at an unmatched scale. Even beyond Kiva, Amazon obviously understood the importance of AMRs several years ago, with its $100+ million acquisition of Canvas Technology in 2019. But looking back at Canvas’ old videos, it seems like Canvas was doing in 2017 more or less what we’re seeing Amazon’s Bert robot doing now, nearly half a decade later.

We reached out to Amazon Robotics for comment and sent them a series of questions about the robots in these videos. They sent us this response:

The health and safety of our employees is our number one priority—and has been since day one. We’re excited about the possibilities robotics and other technology can play in helping to improve employee safety.

Hmm.

I mean, sure, I’m excited about the same thing, but I’m still stuck on why Amazon is at possibilities, while other companies are at commercial deployments. It’s certainly possible that the sheer Amazon-ness of Amazon is a significant factor here, in the sense that a commercial deployment for Amazon is orders of magnitude larger and more complex than any of the AMR companies that we’re comparing them to are dealing with. And if Amazon can figure out how to make (say) an AMR without using lidar, it would make a much more significant difference for an in-house large-scale deployment relative to companies offering AMRs as a service.

For another take on what might be going on with this announcement from Amazon, we spoke with Matt Beane, who got his PhD at MIT and studies robotics at UCSB’s Technology Management Program. At the ACM/IEEE International Conference on Human-Robot Interaction (HRI) last year, Beane published a paper on the value of robots as social signals—that is, organizations get valuable outcomes from just announcing they have robots, because this encourages key audiences to see the organization in favorable ways. “My research strongly suggests that Amazon is reaping signaling value from this announcement,” Beane told us. There’s nothing inherently wrong with signaling, because robots can create instrumental value, and that value needs to be communicated to the people who will, ideally, benefit from it. But you have to be careful: “My paper also suggests this can be a risky move,” explains Beane. “Blowback can be pretty nasty if the systems aren’t in full-tilt, high-value use. In other words, it works only if the signal pretty closely matches the internal reality.”

There’s no way for us to know what the internal reality at Amazon is. All we have to go on is this blog post, which isn’t much, and we should reiterate that there may be a significant gap between what the post is showing us about Amazon’s mobile robots and what’s actually going on at Amazon Robotics. My hope is what we’re seeing here is primarily a sign that Amazon Robotics is starting to scale things up, and that we’re about to see them get a lot more serious about developing robots that will help make their warehouses less tedious, safer, and more productive.

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

“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