Conquering Indoor Navigation: The Autonomous Warehouse

One click, and the next day it’s at my door courtesy of Amazon Robotics. Since acquiring, Kiva Systems in 2012 for $775 million, the retailer has led the way for automated fulfillment centers. Logistics represents a $30 billion market opportunity in the next few years as technologists look to conquer indoor autonomous navigation. Kiva has given birth to an array of creative solutions (discussed below), including copycats like Grey-Orange in India. Will the real Kiva please standup?

Earlier this week, the Wall Street Journal reported that Target Corp has engaged  Symbotic, an autonomous warehousing platform, to enable its distribution center of the future. Symbotic is the brainchild of billionaire grocery store scion Rick Cohen. Cohen’s sales pitch to fellow owners is simple, his robots save money and improve productivity. Big box chains and brands like Target, Wal-Mart and Coca-Cola are embracing his autonomous vision countrywide. Symbotic robots key is their ability to travel untethered among storage racks vs. other automated offerings that are bolted down and tied to fixed routes.

“What we’re doing with autonomous bots is not that dissimilar from what Google is doing with autonomous cars,” Mr. Cohen said in an interview at Symbotic’s Wilmington headquarters. “I think within five years, it’ll change distribution.”

E-commerce retailers have quickly embraced automation, but only recently have consumer-products companies begun to automate their procedures – such as as picking products off a rack and assembling odd-shaped containers on a pallet. Mostly, these tasks are still performed by more than 850,000 people in warehouses across the U.S. today. The last frontier for automation has been the food industry. In the food-and-beverage sector, where Mr. Cohen got his start, just 8% of distribution centers owned by the 75 largest North American grocers are partially or fully automated. Food wholesalers and distributors operate on thin profit margins—typically 1% to 2%—making them reluctant to invest in automation, which can cost up to $100 million for a warehouse. However, that attitude is shifting as rising labor and land costs threaten profits. And they face increased competition from Amazon.com Inc. and other technology firms that are overturning longstanding practices. In my opinion, labor unions would be smart to embrace automation and define new roles for their members now rather than fight an uphill battle against the inevitable.

Wai-Mart revealed that it is testing Symbotic’s system for use in up to two of its large distribution centers. Wal-Mart is interested in how the robots allow it to store more products in its warehouses. Symbotic said its system allows food retailers and wholesalers to cut distribution-center labor costs by 80% and operate warehouses that are 25% to 40% smaller. Cohen faces competition in the U.S. market from companies such as Atlanta-based Dematic Corp. and Austria’s Knapp AG, which have installed systems that use robots to store and retrieve cases of food and consumer products. A growing number of smaller companies are working on ways of using autonomous robots to pick and pack individual items to fulfill online-shopping orders directly to customers.

Last April, I met Melonee Wise of Fetch Robotics and learned that the company is as much of an indoor navigation company as it is a mechanical robot solutions provider. Fetch’s team came out of Willow Garage, which started together at the famed Unbounded Robotics. Today, the company has a number of targeted warehousing solutions to augment human tasks from a mobile manipulator (called “Fetch”) to a zippy base station (known as “Freight”). 

“In the process of designing Fetch, we had to narrow down to an application, and then we did the need-finding necessary to build a robot that had the right specifications for the application that we were going into,” explains Fetch Robotics CEO Melonee Wise. “The reason we’re doing two robots is because one of the big challenges in logistics is traversal of the warehouse. A mobile manipulator just can’t move as fast because it has a high center of gravity, and so we need a smaller, faster robot to zip around the warehouse and get stuff done. Because at some point, we have to be as fast as people, or faster.”

Fetch Robotics’ system uses a relatively large and capable mobile manipulator (Fetch) to pick items off of warehouse shelves, while Freight, a mobile base, acts as an autonomous cargo delivery cart (similar to Kiva or Symbotic). Freight can also be used by itself, following human pickers around a warehouse (using no beacons, only vision), allowing them the freedom from having to push carts around and to keep going back and forth to deliver items that they pick. Instead, the employees can pick continuously, relying on multiple Freight robots to make deliveries. Fetch Robotics calls this system “Follow Pick.” This is taking the idea of the automated distribution center to the next level. 

The costs of Fetch’s robots are under $100,000 and long-term offer the ability to save money in labor, real-estate, and increased productivity.  Fetch is currently in discussions with retailers and is conducting pilots across the country.

In addition to Fetch there are a handful of other startups going after warehouse gold, including: Adept, Clearpath, and Magazino.  One of the most interesting new companies in the field is Locus Robotics. Locus was born in the aftermath of Amazon’s acquisition of Kiva Systems. The Locus team was a former customer of Kiva and decided to develop their own solution in 2014 after Amazon dropped them as a customer.

“Locus was incubated inside of Quiet Logistics: originally they were the same company. The reason that we started the company was that Quiet was a user of Kiva’s robots, and when Amazon acquired Kiva, we decided we needed our own technology. We liked a lot of things about Kiva, but there were also a lot of things about Kiva that we didn’t like. So, we were always thinking about the next generation of robots.” says Bruce Welty, Locus CEO.

Like Fetch, Locus’ robot is designed to work collaboratively with humans to fill orders in a warehouse. It’s a mobile base that can navigate autonomously using lidar to track its location in a pre-mapped area, with cameras and 2D barcodes for verification. Each robot knows the location of every item in the warehouse, and when an item needs to be picked for an order, the robot will navigate to that item and wait.

Humans workers are assigned to patrol warehouse zones, and when they see a robot waiting, the worker reads the item that it needs off the screen, picks it, and moves on. The robot then drives to the location of the next item that it needs, or heads for a shipping station. It’s a very efficient system, since humans aren’t carrying anything or having to roam all over a warehouse to fulfill one order: instead, they’re doing what they’re best at, which is identifying and picking objects off of shelves.

While Locus, Fetch and others envision a world collaborating with humans, IAM Robotics, a Pittsburgh startup, is focused on completely taking the human out of the loop. Founded in 2012, they’ve developed an autonomous mobile picking robots called “Swift” that consists of a wheeled base and a Fanuc arm with a 15-lb payload and suction gripper that can reach 18 inches back into shelves. A height-adjustable carriage can access shelves between 3 and 85 inches, and an autonomously swappable tote carries up to 50 pounds of stuff. According to the company, the robot can autonomously navigate around warehouses and is “capable of picking at human-level speeds” of 200 picks per hour.

“A [human] pick worker on a sustained basis, really can’t pick more than 600 products per hour, and that’s without traveling much. I think we’ve done a demo of 1,100 products per hour with the robot sitting next to a shelf. We were very encouraged by that, and the fact that our robot has certain applications that work, and we can’t do it all, we’re fine with that,” says CEO Tom Galluzzo.

Looking a few years down the road, the only job left for the human to do in the ordering process will be to pay…