How AI is boosting the power of robotic solutions
Author : Julian Ware, ABB Robotics
30 October 2023
The application of artificial intelligence to industrial robots is creating a new breed of solutions offering new levels of flexibility and productivity, whilst also answering industry challenges, especially labour shortages. Julian Ware, UK & Ireland Sales Manager of ABB Robotics, explains.
UK households and businesses are all facing many challenges, with the hangover from COVID, war in Europe, increased energy prices and inflation all having an impact.
For manufacturers, there are added pressures in the form of shortages of both skilled and unskilled labour and disruption in supply chains.
Businesses urgently need to improve their resilience, building flexibility and adaptability into their processes to enable them to weather the shocks caused by these disruptions.
Increasingly, manufacturers are looking to robotic automation, seeking to build resilience against any future shocks while also promising a boost to productivity.
Some of the trends encouraging this adoption include improving energy efficiency. Robots save energy in numerous ways, from reducing the need to heat production lines to using smart, power-saving modes of operation.
As companies strive to overcome tight labour markets and build more resilient supply chains, robots can support reshoring, bringing production closer to markets and ensuring better access to parts.
To help with the labour issues, robots are also becoming easier to use for non-experts, often offering simple graphical programming on straightforward user interfaces.
Refurbished robots are also lowering the barrier to using automation, while at the same time allowing a company to adopt more sustainable manufacturing processes.
Robotic AI comes of age
Robots are already very flexible and adaptable but combining them with artificial intelligence (AI) takes their utility to a whole new level.
The ability of AI systems to learn means they can be employed in a wide range of flexible production situations, for example in cell-based production systems where mobile robots need to respond appropriately to the various objects or people they encounter.
In fact, the greater the variability and unpredictability of the production environment, the more likely it is that AI algorithms can provide a more cost-effective and efficient solution than previously.
Most industrial applications so far have relied on analytical AI, which examines vast reservoirs of data to spot important patterns, making it ideal for applications such as predictive maintenance.
In the future, we can look forward to generative AI, which will make it easier to program robots for new tasks by, among other methods, simply talking to them.
AI is leading to robots being used in many more areas and for many more applications beyond the traditional heavy industry setting and smaller SMEs are using robotic automation in areas as diverse as healthcare, fast-moving consumer goods, retail, construction, and logistics.
The ease of use of AI-enhanced robotics is also seeing them employed in increasingly niche applications that were previously difficult to automate.
AI and machine learning play a growing role wherever robotic systems can benefit from optimised processes, predictive maintenance, or vision-based manoeuvring, for instance.
Pick and place
AI is already increasing the ability of robots to deliver more effective production solutions, transforming the packing and handling of goods, quality inspections and autonomous guided vehicles.
An example is ABB’s AI-enabled Robotic Item Picker. This uses a combination of machine vision and AI to decide the best way to pick up an item with suction grippers and place it into the designated bin. No human supervision or information about the physical attributes of the items it picks is required. Able to pick up to 1,400 items per hour, it can handle more orders without the need for extra people or spending more time.
Using proprietary machine vision software, the robot has the ability to conduct complex picking and placing tasks for items including cuboids, cylinders, pouches, boxes, polybags, and blister packs, matching the dexterity and flexibility of humans.
Quality inspection gets faster and more accurate
Inspecting parts for quality has always been a major challenge for manufacturers. As well as achieving high accuracy, the ideal inspection system must assess parts quickly. This is the job of the 3D Quality Inspection system from ABB.
Using the techniques of structured light and photogrammetry, 3D Quality Inspection can measure faults less than half the width of a human hair much more quickly than traditional measuring inspection tools. 3DQI not only offers quick and accurate quality checks, but also reduces expensive rework and scrappage.
Using a contactless method, 3DQI uses a 3D sensor to capture multiple images of the product to compare it to a master CAD model, allowing operators to test for quality much more quickly than traditional manual-based inspections.
Another advantage is that all the programming of the robot can be done offline using ABB’s RobotStudio, cutting the time and effort needed to commission the system on site.
3D vision on the move
Another use for AI-enhanced robotics is guiding Autonomous Mobile Robots (AMRs) more effectively and efficiently. Visual Simultaneous Localisation and Mapping (Visual SLAM) technology, based on AI-enabled 3D vision, uses cameras mounted on the AMR to create a real-time 3D map of all the objects in the surrounding area.
The cameras detect and track natural features in the environment, enabling the AMR to adapt to its surroundings and determine the safest and most efficient route to its destination.
No external navigation features such as magnetic tape or QR codes are required, which means Visual SLAM technology can reduce commissioning time by up to 20 percent compared to 2D SLAM. The technology can be used at scale with fleets updated remotely.
ABB’s Visual SLAM AMRs make production faster, more flexible, efficient, and resilient while taking on dull, dirty, and dangerous tasks so people can focus on more rewarding work.
Building resilience through education
One of the key strands of building resilience is to ensure that industry has a steady flow of skilled robotics engineers ready to help companies take advantage of these exciting new opportunities.
Increasingly, robot vendors are launching their own support schemes to help colleges and universities train these future engineers. An example is ABB, which is helping the University of Applied Sciences (UAS) at Wiener Neustadt with its new three-year bachelor’s degree in robotics and mechatronics.
Using ABB YuMi collaborative robots, students have designed applications that include solving a Rubik’s Cube puzzle, sorting coffee capsules into ‘good’ and ‘bad’ batches and a virtual application that can recognise human faces, giving students a thorough grounding in mechanics, electronics, computer science, sensors, processors and actuators.
Students learn how to program industrial robots in their first semester, and they will be able to develop and operate mobile, intelligent robots by the time they complete the course.
Accelerated development
The statistics on robotic deployments clearly demonstrate that the increasing versatility of AI-enabled systems is encouraging more companies to adopt robotic solutions to boost their resilience.
In 2021, according to the International Federation of Robotics, the global robot population reached almost 3.5 million.
More recently, AI has been adding game-changing new capabilities that generate rapid market expansion, with Germany installing around 26,000 units in 2022 alone, Italy a further 12,000 and France 7,400.
As competitors around Europe and beyond boost their resilience and productivity with robotic solutions, companies in the UK are recognising that they need to take advantage of these AI-based technologies to maintain competitiveness and avoid falling behind.
More information...
Contact Details and Archive...