Our Black Friday Week sale is now live! Take 30% off ISA training, standards, and print books. Use code BFCM22 at checkout.

  • By Lourenço Castro
  • Digital Transformation

Artificial intelligence and strategically placed cameras function as extended robot sensors for automated assembly or logistics applications.

Strategically placed static cameras, such as the MiR AI Camera, enable mobile robots to foresee obstacles on their routes and reroute themselves for optimized navigation. Source: MiR

In today’s competitive and expensive business environment, autonomous mobile robots (AMRs) are increasingly being used to transport materials within warehouses and manufacturing facilities. Elsewhere, particularly in hospitals, airports, and schools, AMRs disinfect public places or deliver medicine and food to patients. The digital transformation of manufacturing, automated assembly, logistics, and more is being enabled by fleets of robots made ever-smarter through a combination of Industry 4.0/Industrial Internet of Things technology, including artificial intelligence (AI).

A significant aspect of AMRs compared to conventional logistics solutions like forklifts, conveyor belts, and automated guided vehicles (AGVs) is their built-in intelligence. Rather than moving along a set of tracks or sensors built into the infrastructure, like an AGV requires, AMRs autonomously move along the factory floor track-free, bypassing obstacles in their path and even finding new paths on their own.

How smart are current-generation autonomous mobile robots? With a fleet management system installed, multiple robots can be controlled centrally from a single station, and the most advanced systems can eliminate any bottlenecks and downtime to mobile robot operation. Once an AMR is programmed, the fleet management system manages the priorities and selects the most suitable robot to the operation at hand, based on position and availability. It also monitors robot battery levels, automatically manages the recharging, and controls the robots’ traffic patterns by coordinating critical zones with multiple robot intersections.

Some AMRs are taking those smarts to the next level with artificial intelligence coupled with strategically placed cameras that function as extended robot sensors. Without AI, AMRs react the same way to all obstacles, slowing and attempting to navigate around a person or object, if possible, or stopping or backing up if there is no safe way to maneuver around it. With AI, AMRs can learn to adapt their behavior appropriately, even before they enter an area. This means they can avoid high-traffic areas during specific times, including when materials are regularly delivered and transferred by fork truck, or when large crowds of workers are present during breaks or shift changes.

How do AI-powered AMRs work?

Today, mobile robots use sensors and software for control (to define where and how the robot should move) and perception (to allow the robot to understand and react to its surroundings). Data comes from integrated laser scanners, 3D cameras, accelerometers, gyroscopes, wheel encoders, and more to produce the most efficient decisions for each situation.

The AMRs can dynamically navigate using the most efficient routes. They also have environmental awareness so they can avoid obstacles or people in their path, and can automatically charge when needed. AI technology for AMRs is now focused primarily on machine learning (ML) and vision systems, which are dramatically extending earlier sensor-based capabilities. Advances in sensor technology, cloud computing, broadband wireless communications, and new AI-focused processor architectures are more widely available at lower costs. This makes it easier than ever to pull data from a robot’s immediate, extended, and anticipated environment, as well as to monitor its internal conditions.

The technology advances enabling smarter robots, as mentioned, include:

  • Small, low-cost, and power-efficient sensors. These allow mobile and remote devices to capture and transmit huge amounts of data.
  • Faster cloud computing algorithms and broadband wireless communications allow organizations to store, process, and access huge amounts of sensor data almost instantly, from any access point. Secure virtual networks can adapt to dynamic requirements and nearly eliminate downtime and bottlenecks.
  • AI-focused processor architectures are widely available from both traditional semiconductor companies, such as AMD, Intel, NVIDIA, and Qualcomm, as well as from new players in the field including Google and Microsoft. While traditional broad-use semiconductors are facing the limits of Moore’s Law, these new chips are purpose-designed for artificial intelligence calculations. This is driving up capabilities while driving down costs. Low-power, cost-effective AI processors can be incorporated into even smaller mobile or remote devices, allowing onsite computation.
  • Sophisticated software algorithms analyze and process data in the most productive locations—in the robot, in the cloud, or even in remote, extended sensors that provide additional intelligence data for the robot to anticipate needs and proactively adapt its behavior.

Using these advanced technologies and AI-focused cameras, fleets of AMRs can learn while they are online, but then perform without constant access to online content. Low-power, AI-capable devices and efficient AI techniques support new robotic systems with low latency and fast reaction times, high autonomy, and low power consumption—key capabilities for success.

How AI plus vision improves operation

Including a dedicated AI processor in an external, low-cost camera device means it is now possible to extend existing autonomous mobile robots with AI capabilities without modifying their hardware. It is also possible to combine AI-based advanced-learning algorithms with remote but connected stationary cameras. These cameras, mounted in high-traffic areas or in the paths of fork trucks or other automated vehicles, help improve efficiency in path planning and environmental interaction and help maintain the robots’ safety protocols.

The cameras come with small, efficient embedded computers that can process anonymized data and run sophisticated analysis software. This analysis can be used to identify whether objects in the area are humans, fixed obstacles, or other types of mobile devices, such as AGVs. The cameras then feed this information to the robot, extending the robot’s understanding of its surroundings.

Dynamically understanding its surroundings lets a robot adapt its behavior appropriately, even before it enters an area. If an AMR detects a person, for example, it can continue driving; if it detects an AGV, it can park so the AGV can drive by. The robot can also predict blocked areas or highly trafficked areas in advance and reroute, instead of entering the blocked area and then rerouting.

While the AMR’s built-in safety mechanisms will always stop it from colliding with an object, person, or vehicle in its path, other vehicles like forklifts may not have that capability. This puts the AMR at risk of being run over. Because the AI-powered AMRs can detect high-traffic areas before they arrive and identify other vehicles and behave appropriately to decrease the risk of collision, they are improving their own behavior and adapting to other vehicles’ limitations.

Application example: Whirlpool

Whirlpool, one of the world’s largest manufacturers of home appliances, produces dryers and freestanding cookers in a plant in Poland. Whirlpool has manufacturing plants in three locations in the country, including Łódz, Radomsko, and Wrocław. The company implemented three MiR200 autonomous mobile robots that transport components between the preassembly and assembly lines in the Łódz plant in 2018.

To boost effectiveness at its appliance assembly plant in Poland, Whirlpool implemented three MiR200 autonomous mobile robots to transport components between the preassembly and assembly lines. Source: MiR

“At our factory, a dryer leaves the production line every 15 seconds. This requires transporting a huge number of components,” says Szymon Krupinski, site leader at one Whirlpool plant in Poland. “Mobile robots provide us with a completely new way of delivering parts without human involvement. This enables employees to focus on higher value-added areas. Collaborative mobile robots also significantly improve safety, allowing us to avoid all potential collisions between people and devices such as forklifts or tuggers.”

The autonomous robot transports dryer doors between two production lines, from the preassembly to the assembly line. On every run, it carts 12 doors at a time and on the way back transports the empty packaging. The full loop is about 130 meters and takes 3 minutes and 50 seconds. The robot rides up to the preassembly line, moves under a loaded cart and hooks it up. During the unloading, the empty boxes slide back on to the cart under gravity. After that, the robot returns to its starting point and the next transportation cycle begins.

During plant operation, two MiR200 robots with a load capacity of up to 200 kilograms are transporting the components while the third is docked in a charging station, as a backup.

Whirlpool installed a robot fleet management system, MiR Fleet, which allows the robots to properly queue the requests from the line and monitors their battery charge levels to ensure continuous work.

Whirlpool’s implementation and configuration of the robots at the plant was supported by Polish distributor ProCobot, and since the robots were implemented in 2018, the layout of the plant—and thus the route the robots take—has changed several times. Programming the MiR devices consists of specifying the points the robot has to travel through. The simplicity of operation, programming, and advanced navigation technology allow the robots to quickly adapt to changes in the production area layout.

“The ease of operation of MiR robots allows them to be used by staff without any engineering or programming background. This enables us to effectively utilize the robots without making big investments in training the employees in the context of the new technology,” said Paolo Aliverti, logistic program manager, Industry 4.0, for Whirlpool.

According to Aliverti, before the robots were put into use, the transportation of components was performed solely with the use of vehicles operated by specifically trained employees—forklifts and tuggers. Three autonomous mobile robots can replace one such operator-driven vehicle. Thanks to the implementation of the robots, forklift and tugger operators may focus on other tasks in the organization. The expected return on investment in mobile robots at the plant is maximum two years, he said.

“By changing the system from human-operated to automated delivery we can boost productivity and engage employees to final product manufacturing,” said Adam Bakowicz, process technology senior engineer, Industry 4.0, Whirlpool. “The MiR robots provide us with low cost of automation and flexibility in changing the plant layout. We consider the two-year return on investment as attractive.”

Application example: Ford Spain

Ford Spain optimizes intralogistics in its car body and stamping plant in Valencia, Spain, using three AMRs. That plant manufactures 2,000 vehicles a day in a space that covers an area of 300,000 square meters. Pepe Pérez, corporate communications manager at Ford Spain, says, “We are proud to have one of the most innovative factories in Europe that pioneers in the use of collaborative mobile robots for the distribution of industrial materials.”

Ford’s body and stamping plant in Valencia, Spain, adapted MiR robots to its needs by equipping them with an automated shelving system. Plant manager Helios Alvarez said, “The incorporation of the three MiR robots has allowed us to turn a routine distribution of spare items into a highly qualified job.” Source: MiR

The delivery of fresh industrial and welding materials to the different stations of the plant is essential for keeping the production of different Ford models running. Tests conducted by Ford showed that one mobile robot alone frees up to 40 manhours per day, allowing workers to dedicate themselves to more complex tasks.

To adapt the collaborative mobile robots to their needs, Ford decided to equip them with an automated shelving system with 17 slots to accommodate materials of different weights and sizes. To avoid errors, the opening and closing of these slots is automated, meaning that operators in each area only have access to the materials assigned to them. Helios Alvarez, manager of the body and stamping plant says, “The incorporation of the three MiR robots has allowed us to turn a routine distribution of spare items into a highly qualified job.” There are numerous other application examples, including Novo Nordisk’s pharmaceutical plant in China, which uses five MiR500 AMRs to improve warehouse logistics. 

The future of AI-powered AMRs

So what comes next? As AI advances, so will AMRs, making them increasingly smarter and more empowering. Deploying AMRs in a new environment can be a lengthy and delicate process where specific map zones need to be carefully designed to extract the most value from a fleet of robots. In the future, robots should be able to do most of the heavy lifting by recognizing floor markings, busy intersections, narrow passages, and other distinct conditions. Although mobile robots will still be a controllable tool with emergency stop buttons, they will not require constant human intervention. Knowing which side of the track they should navigate or where they should adjust their maximum speed will be a normal part of their operation.

This exciting functionality would not be so impressive, however, if the complexity of the setup surpassed the added benefits. As a result, the process of extending workflows with AI needs to be simple and intuitive, based on concepts such as example-based training and rule-based setup. Setting up intelligent AMRs should not be harder than showing AI algorithms what objects they should detect, or rotating a dial or two to adjust a robot’s behavior.

Lastly, robots are constantly generating a gold mine of data that can be used to monitor their uptime and network connectivity, among other things, but it can also be the starting point for an efficient technical support intervention. Users managing AMRs will be greatly empowered with personalized information and predictions about necessary actions. This means getting recommendations to improve specific robots’ deployments or anticipating when a component needs to be replaced ahead of time.

In summary, AI will become an integral part of setting up and using AMRs, simplifying their deployment process and improving their workflow; AMR users will be empowered to make more informed decisions, even without technical expertise, and robots will become the first line of support, predicting when intervention is needed or automating troubleshooting. That is how AI will bring AMRs into the future.

Reader Feedback


We want to hear from you! Please send us your comments and questions about this topic to InTechmagazine@isa.org.



Like This Article?

Subscribe Now!

About The Authors


Lourenço Castro joined Mobile Industrial Robots in early 2018 to help build its AI team at its headquarters in Odense, Denmark. As AI developer and project manager, he focuses on computer vision, natural language processing, and data science. Previously, he spent five years working on indoor positioning technologies at Fraunhofer Institute in Portugal, his home country, where he also received a master’s degree in biomedical engineering from the University of Porto.