Amazon's Warehouse Robots: Revolutionizing Efficiency, but Challenges Remain

As Amazon expands use of warehouse robots, what will it mean for workers?

Amazon has introduced a handful of robots in its warehouses that the e-commerce giant says will improve efficiency and reduce employee injuries. Two robotic arms named Robin and Cardinal can lift packages that weigh up to 50 pounds. A third, called Sparrow, picks up items from bins and puts them in other containers. Proteus, an autonomous mobile robot that operates on the floor, can move carts around a warehouse. The bipedal, humanoid robot Digit is being tested to help move empty totes with its hands. And there's also Sequoia, a containerized storage system that can present totes to employees in a way that allows them to avoid stretching or squatting to grab inventory. Amazon says Robin is currently being used in dozens of warehouses. The others are in a testing stage or haven't been rolled out widely. But the company says it's already seeing benefits, such as reducing the time it takes to fulfill orders and helping employees avoid repetitive tasks. However, automation also carries drawbacks for workers, who would have to be retrained for new positions if the robots made their roles obsolete. In October, Amazon held an event at a Nashville, Tennessee, warehouse where the company had integrated some of the robots. The Associated Press spoke with Julie Mitchell, the director of Amazon's robotic sortation technologies, about where the company hopes to go from here. The conversation has been edited for length and clarity. Q: When you're working on robotics, how long does it typically take to roll out new technology? A: This journey that we've been on has taken a couple of years. Luckily for us, we've been at this for over a decade. So we have a lot of core technology that we can build on top of. We started these particular robots - Cardinal and Proteus - in this building in November 2022. We came in and began playing around with what it would look like to pack and move a production order. Less than two years later, we are at scale and shipping 70% of the items in this building through that robotics system. Q: So, two years? A: We talk about "build, test and scale" and that's about a two-year cycle for us right now. Q: It's challenging to build robots that can physically grab products. How does Amazon work through that? A: As you can probably imagine, we have so many items, so it's an exceptional challenge. We rely on data and putting our first prototype in a real building, where we expose it to all the things we need it to do. Then we drive down all the reasons that it fails. We give it a lot of sample sizes in a very short period of time. For example, a couple of years ago, we launched our Robin robotics arm - a package manipulation robot - and we're at 3 billion picks. So the ability to launch into our network, rapidly collect data, scale and iterate has enabled us to go fast. The challenge itself can be boiled down to three simple things: you need to perceive the scene, plan your motion and then execute. Today, those are three different parts of our system. Artificial intelligence is going to help us change all of that, and it's going to be more outcome-driven, like asking it to pick up a bottle of water. We're on the verge, so that's why I'm personally excited to be here at the onset of generative AI and use it to dramatically improve the performance of our robotics. Q: How do you think about the impact of automation on Amazon's workforce as you're developing the technology? A: With the technology we've deployed here, we're creating new roles for individuals that can acquire new skills to fulfill those roles. And these new skills are not something that is too difficult to achieve. You don't need an engineering degree, Ph.D. or any really technical skills to support our robotics systems. We designed the systems so they're easy to service and train on the job to be a reliability maintenance engineer. We are working backwards from the idea that we want to employ more skilled labor. These opportunities are obviously higher paid than the entry level jobs in our buildings. And partnering with MIT has helped us understand what matters most to our team as we're deploying these technologies across our network. Q: Are you experiencing any challenges as you introduce these robots in your warehouses? A: Not in the adoption. We're integrating it. But these are complex systems and this is the real world, so things go wrong. For example, we had bad weather due to the storms in the Southeast. When I look at the robotics systems data, I can tell the weather is bad outside because that dramatically affects how the ship dock works. When trucks don't arrive on time or when they can't leave, you see bottlenecks in the building in strange ways. Containers build up, we have to put them in different places, and then humans need to recover them. So communication between what our robotics system is doing and what we need employees in the building to do to recover is important. It's a collaboration of automation and humans to deal with real-world problems. It's not a matter of having robotics take over but making it one system of humans and robotics working together to accomplish the goal of shipping the product.

As Amazon expands use of warehouse robots, what will it mean for workers?

Amazon has introduced a handful of robots in its warehouses that the e-commerce giant says will improve efficiency and reduce employee injuries. Two robotic arms named Robin and Cardinal can lift packages that weigh up to 50 pounds. A third, called Sparrow, picks up items from bins and puts them in other containers. Proteus, an autonomous mobile robot that operates on the floor, can move carts around a warehouse. The bipedal, humanoid robot Digit is being tested to help move empty totes with its hands. And there's also Sequoia, a containerized storage system that can present totes to employees in a way that allows them to avoid stretching or squatting to grab inventory. Amazon says Robin is currently being used in dozens of warehouses. The others are in a testing stage or haven't been rolled out widely. But the company says it's already seeing benefits, such as reducing the time it takes to fulfill orders and helping employees avoid repetitive tasks. However, automation also carries drawbacks for workers, who would have to be retrained for new positions if the robots made their roles obsolete. In October, Amazon held an event at a Nashville, Tennessee, warehouse where the company had integrated some of the robots. The Associated Press spoke with Julie Mitchell, the director of Amazon's robotic sortation technologies, about where the company hopes to go from here. The conversation has been edited for length and clarity. Q: When you're working on robotics, how long does it typically take to roll out new technology? A: This journey that we've been on has taken a couple of years. Luckily for us, we've been at this for over a decade. So we have a lot of core technology that we can build on top of. We started these particular robots -- Cardinal and Proteus -- in this building in November 2022. We came in and began playing around with what it would look like to pack and move a production order. Less than two years later, we are at scale and shipping 70% of the items in this building through that robotics system. Q: So, two years? A: We talk about "build, test and scale" and that's about a two-year cycle for us right now. Q: It's challenging to build robots that can physically grab products. How does Amazon work through that? A: As you can probably imagine, we have so many items, so it's an exceptional challenge. We rely on data and putting our first prototype in a real building, where we expose it to all the things we need it to do. Then we drive down all the reasons that it fails. We give it a lot of sample sizes in a very short period of time. For example, a couple of years ago, we launched our Robin robotics arm -- a package manipulation robot -- and we're at 3 billion picks. So the ability to launch into our network, rapidly collect data, scale and iterate has enabled us to go fast. The challenge itself can be boiled down to three simple things: you need to perceive the scene, plan your motion and then execute. Today, those are three different parts of our system. Artificial intelligence is going to help us change all of that, and it's going to be more outcome-driven, like asking it to pick up a bottle of water. We're on the verge, so that's why I'm personally excited to be here at the onset of generative AI and use it to dramatically improve the performance of our robotics. Q: How do you think about the impact of automation on Amazon's workforce as you're developing the technology? A: With the technology we've deployed here, we're creating new roles for individuals that can acquire new skills to fulfill those roles. And these new skills are not something that is too difficult to achieve. You don't need an engineering degree, Ph.D. or any really technical skills to support our robotics systems. We designed the systems so they're easy to service and train on the job to be a reliability maintenance engineer. We are working backwards from the idea that we want to employ more skilled labor. These opportunities are obviously higher paid than the entry level jobs in our buildings. And partnering with MIT has helped us understand what matters most to our team as we're deploying these technologies across our network. Q: Are you experiencing any challenges as you introduce these robots in your warehouses? A: Not in the adoption. We're integrating it. But these are complex systems and this is the real world, so things go wrong. For example, we had bad weather due to the storms in the Southeast. When I look at the robotics systems data, I can tell the weather is bad outside because that dramatically affects how the ship dock works. When trucks don't arrive on time or when they can't leave, you see bottlenecks in the building in strange ways. Containers build up, we have to put them in different places, and then humans need to recover them. So communication between what our robotics system is doing and what we need employees in the building to do to recover is important. It's a collaboration of automation and humans to deal with real-world problems. It's not a matter of having robotics take over but making it one system of humans and robotics working together to accomplish the goal of shipping the product.

Robots struggle to match warehouse workers on 'Really Hard' jobs

NASHVILLE: In the outbound dock of an Amazon warehouse near Nashville, Tennessee, a robotic arm named Cardinal on a recent day stacked packages, Tetris-style, into 6 1/2-foot-high carts. Then Proteus, an autonomous platform, moved the carts to the loading bay, flashing electronic eyes designed to make the robot more appealing to human colleagues. As robots become more capable, they are performing an increasing number of tasks in warehouses and delivery centers with varying degrees of aptitude and speed. Machines can load and unload trucks. They can place goods on pallets and take them off. Robots can shift items around in inventory, pick up packages and move goods on warehouse floors. And they can do all this without a human minder guiding their every move. Yet, even though robots are starting to take over some repetitive and cumbersome jobs, there are still many tasks they are not good at, making it difficult to know when or if robots will be able to fully automate this industry. Despite the rise in automation, warehouses remain big employers of humans. Federal data show that nearly 1.8 million people work in this corner of the supply chain. While that number is down 9% from its peak in 2022, when logistics companies went on a hiring spree to handle the pandemic e-commerce boom, it is still up more than 30% since early 2020. There are many crucial, simple tasks that humans are far better at. They can reach into a container of many items and move some out the way to extract the piece they want, a task industry officials refer to as picking. Robotics engineers struggle to say when their creations will be able to do that fast enough to be viable replacements for human workers. Artificial intelligence companies such as OpenAI have served up impressive services that can quickly produce writing, images and videos that can seem to be the work of skilled professionals. But in warehouses brimming with the wares of the modern economy, advances in automation have been slower. There, robots often struggle to master skills most humans can do without much trouble. Sparrow, one of Amazon's most advanced robotic arms, performs "top-picking," taking the item at or near the top of a container. Amazon says that Sparrow can manipulate over 200 million items of different sizes and weights, but that it is not adept at "targeted picking" -- rummaging around many items to get one that might be buried or obscured. "That's a really hard job," said Tye Brady, chief technologist at Amazon Robotics. "I'm not saying it's impossible. That's kind of the next frontier." And sometimes companies find that the robots put through tests outside the lab are not ready. There are "more that we have not adopted than ones that we have," said Sally Miller, the global chief information officer at DHL Supply Chain, referring to robots. The DHL division she works for operates warehouses for other companies and has deployed 7,000 robots globally. Among the rejected: an autonomous forklift capable of stacking boxes at heights that DHL, which is based in Bonn, Germany, decided was too slow. Miller said she was frustrated to see venture capital recently rushing into robots that resemble people, a category of machines known as humanoids. Such machines have long been the robotic holy grail in science fiction and in the visions of some technology executives. But to Miller, they aren't ready for warehouse work, and she would prefer that engineers develop devices that can handle specific tasks well, quickly and affordably. One big motivation to automate is the high turnover of warehouse employees. The work is often physically demanding and pays modest wages. Less-skilled warehouse workers earn around $16 to $17 an hour. Among the lower-paid jobs are truck unloaders, who grab boxes and move them onto conveyor systems. That job can now be done with a robotic arm called Stretch, developed by Boston Dynamics, an automation company. A Stretch working at an inbound dock of a DHL-run facility in Columbus, Ohio, recently reached deep into the back of a tightly packed truck and steadily removed boxes filled with apparel. A warehouse employee who oversees Stretch referred to it as "he" and spoke fondly of his ability to pick up dropped packages. Miller said Stretch can unload roughly twice as many boxes per hour as humans. She declined to say how much Stretch cost, but said: "It doesn't call in sick, and it can work for several hours. It's a great solution." Stretch can do the work of four to six workers over two shifts, DHL said, and the company has moved workers whose tasks are now being done by the robot to other jobs in different parts of the warehouse. Some executives said their aim was to have robots do all the monotonous tasks. "Menial, mundane, repetitive tasks will be replaced by automation," Brady said. "That may freak people out, but it's going to allow people to focus more on what matters." Amazon has over 750,000 robots in its operations. While it does not disclose a specific number for warehouse employees, the company had 1.55 million employees at the end of September, up from 800,000 in 2019. Many work in fulfilment centres. In the outbound dock in Nashville where Cardinal and Proteus operate, there were still scores of employees at work. But Amazon did not say how many people worked in the bay before the introduction of the two robots and how many work there today. Amazon says deploying robots creates new jobs that involve overseeing and maintaining the machines. But the number of such workers does not appear to be large. On a recent tour of the company's Nashville facility, a manager said there were around 100 such jobs, out of 2,500 people at the centre. An Amazon spokesperson said such facilities typically had 200 robot maintenance employees. Amazon's robots do seem to be helping it process more parcels with fewer employees. Brady said a new Amazon warehouse in Shreveport, Louisiana, using its latest technology, including an automated inventory management system called Sequoia, appeared capable of processing packages 25% faster and 25% more cheaply than the one in Nashville. Like Nashville, Shreveport will have 2,500 employees. The structured, predictable environment of a warehouse makes it easier for robots to operate. Devising a robot that can find its own way around a warehouse at relatively slow speeds is easier than building autonomous cars that have to navigate ever-changing city streets. At DHL's delivery centre in Columbus, bin-carrying robots called Locus had no trouble sidling up to human pickers, who handed pieces of apparel to the machines, which transported them to the packaging station. Miller said Locus and similar devices were designed to reduce the amount of walking pickers do. Robotics engineers say AI technologies have helped them make progress. Marc Segura, president of the robotics division at the Swiss company ABB, said a client wanted to enable a goods-sorting robot to identify and avoid bulky items. Using AI, the machine taught itself what such items looked like and now avoids them, he said. Sometimes the advances don't rely on cutting-edge technologies. Fox Robotics makes autonomous forklifts that can unload pallets from trucks and place them on the loading dock floor. Customers wanted the forklifts to be able to place pallets on rolling conveyors so they could be moved more quickly to their destination. But the pallet created a blind spot that prevented the forklift from seeing whether a conveyor had enough open space. On its latest machines, the company overcame that problem by adding more sensors, effectively expanding the forklift's vision. "Once we had those sensors, doing the actual placing on conveyor was trivial," said Peter Anderson-Sprecher, chief technology officer and a co-founder of Fox Robotics.

Robots Struggle to Match Warehouse Workers on 'Really Hard' Jobs

In the outbound dock of an Amazon warehouse near Nashville, a robotic arm named Cardinal on a recent day stacked packages, Tetris-style, into six-and-a-half-foot-high carts. Then Proteus, an autonomous platform, moved the carts to the loading bay, flashing electronic eyes designed to make the robot more appealing to human colleagues. As robots become more capable, they are performing an increasing number of tasks in warehouses and delivery centers with varying degrees of aptitude and speed. Machines can load and unload trucks. They can place goods on pallets and take them off. Robots can shift items around in inventory, pick up packages and move goods on warehouse floors. And they can do all this without a human minder guiding their every move. Yet, even though robots are starting to take over some repetitive and cumbersome jobs, there are still many tasks they are not good at, making it difficult to know when or if robots will be able to fully automate this industry. Despite the rise in automation, warehouses remain big employers of humans. Federal data show that nearly 1.8 million people work in this corner of the supply chain. While that number is down 9 percent from its peak in 2022, when logistics companies went on a hiring spree to handle the pandemic e-commerce boom, it is still up more than 30 percent since early 2020. There are many crucial, simple tasks that humans are far better at. They can reach into a container of many items and move some out the way to extract the piece they want, a task industry officials refer to as picking. Robotics engineers struggle to say when their creations will be able to do that fast enough to be viable replacements for human workers. Artificial intelligence companies like OpenAI have served up impressive services that can quickly produce writing, images and videos that can seem to be the work of skilled professionals. But in warehouses brimming with the wares of the modern economy, advances in automation have been slower. There, robots often struggle to master skills most humans can do without much trouble. Sparrow, one of Amazon's most advanced robotic arms, performs "top-picking," taking the item at or near the top of a container. Amazon says that Sparrow can manipulate over 200 million items of different sizes and weights, but that it is not adept at "targeted picking" -- rummaging around many items to get one that might be buried or obscured. "That's a really hard job," said Tye Brady, chief technologist at Amazon Robotics. "I'm not saying it's impossible. That's kind of the next frontier." And sometimes companies find that the robots put through tests outside the lab are not ready. There are "more that we have not adopted than ones that we have," said Sally Miller, the global chief information officer at DHL Supply Chain, referring to robots. The DHL division she works for operates warehouses for other companies and has deployed 7,000 robots globally. Among the rejected: an autonomous forklift capable of stacking boxes at heights that DHL, which is based in Bonn, Germany, decided was too slow. Ms. Miller said she was frustrated to see venture capital recently rushing into robots that resemble people, a category of machines known as humanoids. Such machines have long been the robotic holy grail in science fiction and in the visions of some technology executives. But to Ms. Miller, they aren't ready for warehouse work, and she would prefer that engineers develop devices that can handle specific tasks well, quickly and affordably. One big motivation to automate is the high turnover of warehouse employees. The work is often physically demanding and pays modest wages. Less-skilled warehouse workers earn around $16 to $17 an hour. Among the lower-paid jobs are truck unloaders, who grab boxes and move them onto conveyor systems. That job can now be done with a robotic arm called Stretch, developed by Boston Dynamics, an automation company. A Stretch working at an inbound dock of a DHL-run facility in Columbus, Ohio, recently reached deep into the back of a tightly packed truck and steadily removed boxes filled with apparel. A warehouse employee who oversees Stretch referred to it as "he" and spoke fondly of his ability to pick up dropped packages. Ms. Miller said Stretch can unload roughly twice as many boxes per hour as humans. She declined to say how much Stretch cost, but said: "It doesn't call in sick, and it can work for several hours. It's a great solution." Stretch can do the work of four to six workers over two shifts, DHL said, and the company has moved workers whose tasks are now being done by the robot to other jobs in different parts of the warehouse. Some executives said their aim was to have robots do all the monotonous tasks. "Menial, mundane, repetitive tasks will be replaced by automation," Mr. Brady of Amazon said. "That may freak people out, but it's going to allow people to focus more on what matters." Amazon has over 750,000 robots in its operations. While it does not disclose a specific number for warehouse employees, the company had 1.55 million employees at the end of September, up from 800,000 in 2019. Many work in fulfillment centers. In the outbound dock in Nashville where Cardinal and Proteus operate, there were still scores of employees at work. But Amazon did not say how many people worked in the bay before the introduction of the two robots and how many work there today. Amazon says deploying robots creates new jobs that involve overseeing and maintaining the machines. But the number of such workers does not appear to be large. On a recent tour of the company's Nashville facility, a manager said there were around 100 such jobs, out of 2,500 people at the center. An Amazon spokesman said such facilities typically had 200 robot maintenance employees. Amazon's robots do seem to be helping it process more parcels with fewer employees. Mr. Brady said a new Amazon warehouse in Shreveport, La., using its latest technology, including an automated inventory management system called Sequoia, appeared capable of processing packages 25 percent faster and 25 percent more cheaply than the one in Nashville. Like Nashville, Shreveport will have 2,500 employees. The structured, predictable environment of a warehouse makes it easier for robots to operate. Devising a robot that can find its own way around a warehouse at relatively slow speeds is easier than building autonomous cars that have to navigate ever-changing city streets. At DHL's delivery center in Columbus, bin-carrying robots called Locus had no trouble sidling up to human pickers, who handed pieces of apparel to the machines, which transported them to the packaging station. Ms. Miller said Locus and similar devices were designed to reduce the amount of walking pickers do. Robotics engineers say A.I. technologies have helped them make progress. Marc Segura, president of the robotics division at the Swiss company ABB, said a client wanted to enable a goods-sorting robot to identify and avoid bulky items. Using A.I., the machine taught itself what such items looked like and now avoids them, he said. Sometimes the advances don't rely on cutting-edge technologies. Fox Robotics makes autonomous forklifts that can unload pallets from trucks and place them on the loading dock floor. Customers wanted the forklifts to be able to place pallets on rolling conveyors so they could be moved more quickly to their destination. But the pallet created a blind spot that prevented the forklift from seeing whether a conveyor had enough open space. On its latest machines, the company overcame that problem by adding more sensors, effectively expanding the forklift's vision. "Once we had those sensors, doing the actual placing on conveyor was trivial," said Peter Anderson-Sprecher, chief technology officer and a co-founder of Fox Robotics. Karen Weise contributed reporting from Nashville.

As Amazon expands use of warehouse robots, what will it mean for workers?

Amazon has introduced a handful of robots in its warehouses that the e-commerce giant says will improve efficiency and reduce employee injuries. Two robotic arms named Robin and Cardinal can lift packages that weigh up to 50 pounds. A third, called Sparrow, picks up items from bins and puts them in other containers. Proteus, an autonomous mobile robot that operates on the floor, can move carts around a warehouse. The bipedal, humanoid robot Digit is being tested to help move empty totes with its hands. And there's also Sequoia, a containerized storage system that can present totes to employees in a way that allows them to avoid stretching or squatting to grab inventory. Amazon says Robin is currently being used in dozens of warehouses. The others are in a testing stage or haven't been rolled out widely. But the company says it's already seeing benefits, such as reducing the time it takes to fulfill orders and helping employees avoid repetitive tasks. However, automation also carries drawbacks for workers, who would have to be retrained for new positions if the robots made their roles obsolete. In October, Amazon held an event at a Nashville, Tennessee, warehouse where the company had integrated some of the robots. The Associated Press spoke with Julie Mitchell, the director of Amazon's robotic sortation technologies, about where the company hopes to go from here. The conversation has been edited for length and clarity. A: This journey that we've been on has taken a couple of years. Luckily for us, we've been at this for over a decade. So we have a lot of core technology that we can build on top of. We started these particular robots - Cardinal and Proteus - in this building in November 2022. We came in and began playing around with what it would look like to pack and move a production order. Less than two years later, we are at scale and shipping 70% of the items in this building through that robotics system. A: We talk about "build, test and scale" and that's about a two-year cycle for us right now. A: As you can probably imagine, we have so many items, so it's an exceptional challenge. We rely on data and putting our first prototype in a real building, where we expose it to all the things we need it to do. Then we drive down all the reasons that it fails. We give it a lot of sample sizes in a very short period of time. For example, a couple of years ago, we launched our Robin robotics arm - a package manipulation robot - and we're at 3 billion picks. So the ability to launch into our network, rapidly collect data, scale and iterate has enabled us to go fast. The challenge itself can be boiled down to three simple things: you need to perceive the scene, plan your motion and then execute. Today, those are three different parts of our system. Artificial intelligence is going to help us change all of that, and it's going to be more outcome-driven, like asking it to pick up a bottle of water. We're on the verge, so that's why I'm personally excited to be here at the onset of generative AI and use it to dramatically improve the performance of our robotics. A: With the technology we've deployed here, we're creating new roles for individuals that can acquire new skills to fulfill those roles. And these new skills are not something that is too difficult to achieve. You don't need an engineering degree, Ph.D. or any really technical skills to support our robotics systems. We designed the systems so they're easy to service and train on the job to be a reliability maintenance engineer. We are working backwards from the idea that we want to employ more skilled labor. These opportunities are obviously higher paid than the entry level jobs in our buildings. And partnering with MIT has helped us understand what matters most to our team as we're deploying these technologies across our network. A: Not in the adoption. We're integrating it. But these are complex systems and this is the real world, so things go wrong. For example, we had bad weather due to the storms in the Southeast. When I look at the robotics systems data, I can tell the weather is bad outside because that dramatically affects how the ship dock works. When trucks don't arrive on time or when they can't leave, you see bottlenecks in the building in strange ways. Containers build up, we have to put them in different places, and then humans need to recover them. So communication between what our robotics system is doing and what we need employees in the building to do to recover is important. It's a collaboration of automation and humans to deal with real-world problems. It's not a matter of having robotics take over but making it one system of humans and robotics working together to accomplish the goal of shipping the product.

As Amazon expands use of warehouse robots, what will it mean for workers?

Amazon is deploying robots like Robin, Cardinal, and Sparrow to handle packages and sort items. Proteus moves carts, while Digit handles totes. These robots aim to speed up order fulfillment and reduce worker strain. Amazon is retraining workers for new roles. The company says robots and humans will collaborate. This two-year project involves building, testing, and scaling the technology.Amazon has introduced a handful of robots in its warehouses that the ecommerce giant says will improve efficiency and reduce employee injuries. Two robotic arms named Robin and Cardinal can lift packages that weigh up to 50 pounds. A third, called Sparrow, picks up items from bins and puts them in other containers. Proteus, an autonomous mobile robot that operates on the floor, can move carts around a warehouse. The bipedal, humanoid robot Digit is being tested to help move empty totes with its hands. And there's also Sequoia, a containerized storage system that can present totes to employees in a way that allows them to avoid stretching or squatting to grab inventory. Amazon says Robin is currently being used in dozens of warehouses. The others are in a testing stage or haven't been rolled out widely. But the company says it's already seeing benefits, such as reducing the time it takes to fulfil orders and helping employees avoid repetitive tasks. However, automation also carries drawbacks for workers, who would have to be retrained for new positions if the robots made their roles obsolete. In October, Amazon held an event at a Nashville, Tennessee, warehouse where the company had integrated some of the robots. The Associated Press spoke with Julie Mitchell, the director of Amazon's robotic sortation technologies, about where the company hopes to go from here. The conversation has been edited for length and clarity. Q: When you're working on robotics, how long does it typically take to roll out new technology? A: This journey that we've been on has taken a couple of years. Luckily for us, we've been at this for over a decade. So we have a lot of core technology that we can build on top of. We started these particular robots - Cardinal and Proteus - in this building in November 2022. We came in and began playing around with what it would look like to pack and move a production order. Less than two years later, we are at scale and shipping 70% of the items in this building through that robotics system. Q: So, two years? A: We talk about "build, test and scale" and that's about a two-year cycle for us right now. Q: It's challenging to build robots that can physically grab products. How does Amazon work through that? A: As you can probably imagine, we have so many items, so it's an exceptional challenge. We rely on data and putting our first prototype in a real building, where we expose it to all the things we need it to do. Then we drive down all the reasons that it fails. We give it a lot of sample sizes in a very short period of time. For example, a couple of years ago, we launched our Robin robotics arm - a package manipulation robot - and we're at 3 billion picks. So the ability to launch into our network, rapidly collect data, scale and iterate has enabled us to go fast. The challenge itself can be boiled down to three simple things: you need to perceive the scene, plan your motion and then execute. Today, those are three different parts of our system. Artificial intelligence is going to help us change all of that, and it's going to be more outcome-driven, like asking it to pick up a bottle of water. We're on the verge, so that's why I'm personally excited to be here at the onset of generative AI and use it to dramatically improve the performance of our robotics. Q: How do you think about the impact of automation on Amazon's workforce as you're developing the technology? A: With the technology we've deployed here, we're creating new roles for individuals who can acquire new skills to fulfil those roles. And these new skills are not something that is too difficult to achieve. You don't need an engineering degree, PhD or any really technical skills to support our robotics systems. We designed the systems so they're easy to service and train on the job to be a reliability maintenance engineer. We are working backwards from the idea that we want to employ more skilled labour. These opportunities are obviously higher paid than the entry-level jobs in our buildings. And partnering with MIT has helped us understand what matters most to our team as we're deploying these technologies across our network. Q: Are you experiencing any challenges as you introduce these robots in your warehouses? A: Not in the adoption. We're integrating it. But these are complex systems and this is the real world, so things go wrong. For example, we had bad weather due to the storms in the Southeast. When I look at the robotics systems data, I can tell the weather is bad outside because that dramatically affects how the ship dock works. When trucks don't arrive on time or when they can't leave, you see bottlenecks in the building in strange ways. Containers build-up, we have to put them in different places, and then humans need to recover them. So communication between what our robotics system is doing and what we need employees in the building to do to recover is important. It's a collaboration of automation and humans to deal with real-world problems. It's not a matter of having robotics take over but making it one system of humans and robotics working together to accomplish the goal of shipping the product.

As Amazon expands use of warehouse robots, what will it mean for workers?

Amazon has introduced a handful of robots in its warehouses that the e-commerce giant says will improve efficiency and reduce employee injuries Amazon has introduced a handful of robots in its warehouses that the e-commerce giant says will improve efficiency and reduce employee injuries. Two robotic arms named Robin and Cardinal can lift packages that weigh up to 50 pounds. A third, called Sparrow, picks up items from bins and puts them in other containers. Proteus, an autonomous mobile robot that operates on the floor, can move carts around a warehouse. The bipedal, humanoid robot Digit is being tested to help move empty totes with its hands. And there's also Sequoia, a containerized storage system that can present totes to employees in a way that allows them to avoid stretching or squatting to grab inventory. Amazon says Robin is currently being used in dozens of warehouses. The others are in a testing stage or haven't been rolled out widely. But the company says it's already seeing benefits, such as reducing the time it takes to fulfill orders and helping employees avoid repetitive tasks. However, automation also carries drawbacks for workers, who would have to be retrained for new positions if the robots made their roles obsolete. In October, Amazon held an event at a Nashville, Tennessee, warehouse where the company had integrated some of the robots. The Associated Press spoke with Julie Mitchell, the director of Amazon's robotic sortation technologies, about where the company hopes to go from here. The conversation has been edited for length and clarity. A: This journey that we've been on has taken a couple of years. Luckily for us, we've been at this for over a decade. So we have a lot of core technology that we can build on top of. We started these particular robots - Cardinal and Proteus - in this building in November 2022. We came in and began playing around with what it would look like to pack and move a production order. Less than two years later, we are at scale and shipping 70% of the items in this building through that robotics system. A: We talk about "build, test and scale" and that's about a two-year cycle for us right now. A: As you can probably imagine, we have so many items, so it's an exceptional challenge. We rely on data and putting our first prototype in a real building, where we expose it to all the things we need it to do. Then we drive down all the reasons that it fails. We give it a lot of sample sizes in a very short period of time. For example, a couple of years ago, we launched our Robin robotics arm - a package manipulation robot - and we're at 3 billion picks. So the ability to launch into our network, rapidly collect data, scale and iterate has enabled us to go fast. The challenge itself can be boiled down to three simple things: you need to perceive the scene, plan your motion and then execute. Today, those are three different parts of our system. Artificial intelligence is going to help us change all of that, and it's going to be more outcome-driven, like asking it to pick up a bottle of water. We're on the verge, so that's why I'm personally excited to be here at the onset of generative AI and use it to dramatically improve the performance of our robotics. A: With the technology we've deployed here, we're creating new roles for individuals that can acquire new skills to fulfill those roles. And these new skills are not something that is too difficult to achieve. You don't need an engineering degree, Ph.D. or any really technical skills to support our robotics systems. We designed the systems so they're easy to service and train on the job to be a reliability maintenance engineer. We are working backwards from the idea that we want to employ more skilled labor. These opportunities are obviously higher paid than the entry level jobs in our buildings. And partnering with MIT has helped us understand what matters most to our team as we're deploying these technologies across our network. A: Not in the adoption. We're integrating it. But these are complex systems and this is the real world, so things go wrong. For example, we had bad weather due to the storms in the Southeast. When I look at the robotics systems data, I can tell the weather is bad outside because that dramatically affects how the ship dock works. When trucks don't arrive on time or when they can't leave, you see bottlenecks in the building in strange ways. Containers build up, we have to put them in different places, and then humans need to recover them. So communication between what our robotics system is doing and what we need employees in the building to do to recover is important. It's a collaboration of automation and humans to deal with real-world problems. It's not a matter of having robotics take over but making it one system of humans and robotics working together to accomplish the goal of shipping the product.

As Amazon Expands Use of Warehouse Robots, What Will It Mean for Workers?

Amazon has introduced a handful of robots in its warehouses that the e-commerce giant says will improve efficiency and reduce employee injuries. Two robotic arms named Robin and Cardinal can lift packages that weigh up to 50 pounds. A third, called Sparrow, picks up items from bins and puts them in other containers. Proteus, an autonomous mobile robot that operates on the floor, can move carts around a warehouse. The bipedal, humanoid robot Digit is being tested to help move empty totes with its hands. And there's also Sequoia, a containerized storage system that can present totes to employees in a way that allows them to avoid stretching or squatting to grab inventory. Amazon says Robin is currently being used in dozens of warehouses. The others are in a testing stage or haven't been rolled out widely. But the company says it's already seeing benefits, such as reducing the time it takes to fulfill orders and helping employees avoid repetitive tasks. However, automation also carries drawbacks for workers, who would have to be retrained for new positions if the robots made their roles obsolete. In October, Amazon held an event at a Nashville, Tennessee, warehouse where the company had integrated some of the robots. The Associated Press spoke with Julie Mitchell, the director of Amazon's robotic sortation technologies, about where the company hopes to go from here. The conversation has been edited for length and clarity. Q: When you're working on robotics, how long does it typically take to roll out new technology? A: This journey that we've been on has taken a couple of years. Luckily for us, we've been at this for over a decade. So we have a lot of core technology that we can build on top of. We started these particular robots - Cardinal and Proteus - in this building in November 2022. We came in and began playing around with what it would look like to pack and move a production order. Less than two years later, we are at scale and shipping 70% of the items in this building through that robotics system. Q: So, two years? A: We talk about "build, test and scale" and that's about a two-year cycle for us right now. Q: It's challenging to build robots that can physically grab products. How does Amazon work through that? A: As you can probably imagine, we have so many items, so it's an exceptional challenge. We rely on data and putting our first prototype in a real building, where we expose it to all the things we need it to do. Then we drive down all the reasons that it fails. We give it a lot of sample sizes in a very short period of time. For example, a couple of years ago, we launched our Robin robotics arm - a package manipulation robot - and we're at 3 billion picks. So the ability to launch into our network, rapidly collect data, scale and iterate has enabled us to go fast. The challenge itself can be boiled down to three simple things: you need to perceive the scene, plan your motion and then execute. Today, those are three different parts of our system. Artificial intelligence is going to help us change all of that, and it's going to be more outcome-driven, like asking it to pick up a bottle of water. We're on the verge, so that's why I'm personally excited to be here at the onset of generative AI and use it to dramatically improve the performance of our robotics. Q: How do you think about the impact of automation on Amazon's workforce as you're developing the technology? A: With the technology we've deployed here, we're creating new roles for individuals that can acquire new skills to fulfill those roles. And these new skills are not something that is too difficult to achieve. You don't need an engineering degree, Ph.D. or any really technical skills to support our robotics systems. We designed the systems so they're easy to service and train on the job to be a reliability maintenance engineer. We are working backwards from the idea that we want to employ more skilled labor. These opportunities are obviously higher paid than the entry level jobs in our buildings. And partnering with MIT has helped us understand what matters most to our team as we're deploying these technologies across our network. Q: Are you experiencing any challenges as you introduce these robots in your warehouses? A: Not in the adoption. We're integrating it. But these are complex systems and this is the real world, so things go wrong. For example, we had bad weather due to the storms in the Southeast. When I look at the robotics systems data, I can tell the weather is bad outside because that dramatically affects how the ship dock works. When trucks don't arrive on time or when they can't leave, you see bottlenecks in the building in strange ways. Containers build up, we have to put them in different places, and then humans need to recover them. So communication between what our robotics system is doing and what we need employees in the building to do to recover is important. It's a collaboration of automation and humans to deal with real-world problems. It's not a matter of having robotics take over but making it one system of humans and robotics working together to accomplish the goal of shipping the product. Copyright 2024 The Associated Press. All rights reserved. This material may not be published, broadcast, rewritten or redistributed.