Artificial Intelligence and Industrial Robotics: Far Beyond the Hype

3DQI makes it possible to achieve high-level quality inspection during the manufacturing processes to control, detect, and correct the fault where it happens. (Image: ABB)

While there are concerned voices speaking of a certain disillusionment with AI, as with any potentially game-changing technology, the expectations and fears are often exaggerated. Specifically in relation to industrial robotics, the potential of AI’s impact has, if anything, been muted.

Accelerating progress in AI is redefining what is possible with industrial robotics, enhancing everything from robots’ ability to grip, pick and place as well as their ability to map and navigate through dynamic environments. From mobile robots to cobots, autonomous mobile robots (AMRs) and beyond, AI is giving robots unprecedented levels of speed, accuracy, and payload carrying ability, enabling them to take on more tasks in settings like flexible factories, warehouses, logistics centers, and laboratories.

In the past, robotics and automation have mainly benefited large organizations, while smaller companies have been put off by the complexity and cost. AI lowers the entry barrier into robotics and makes it more accessible: AI-enabled robots do not require extensive programming skills but perform tasks in response to voice commands. This means significant productivity gains for companies of all sizes and in all industries.

Accordingly, industries that have previously had a low robot density and many small and medium-sized companies will be able to utilize automation solutions cost-effectively, and thus increase their own competitiveness. In view of the increasing shortage of labor and skilled workers, industrialized countries can take advantage of the productivity growth that can potentially be achieved through robotics and AI.

“AI-enabled mobile robots can transform sectors like discrete manufacturing, logistics, and laboratories,” said Marc Segura, President ABB Robotics Division. “Robots equipped with ABB’s new Visual Simultaneous Localization and Mapping (Visual SLAM) technology, for example, have advanced mapping and navigation skills, granting new levels of autonomy, while greatly reducing the infrastructure needed by previous generations of guided robots. This paves the way for a shift from linear production lines to dynamic networks, creating significant efficiencies and taking on more dull, dirty and dangerous tasks, to enable workers to take up more rewarding jobs.”

There are four distinct areas for industrial applications of AI-powered robotics:

Generating Insights: AI analyzes large datasets and generates meaningful insights that form the basis for decision-making.
Optimization: From macro-level energy management to micro-level path planning for robot movements, AI optimizes operations and increases efficiency.
New Capabilities: Thanks to AI, robots can perform a broader range of complex tasks that were previously difficult to automate. By leveraging data and algorithms to optimize processes, robots execute tasks faster and more precisely, with greater autonomy and without human supervision in dynamic, uncontrolled, and unstructured environments.
Human-Machine Collaboration: AI makes robots and automation more accessible and user-friendly, enabling people without programming knowledge to guide and control a robot or machine. In the past, humans had to learn the language of robots and machines, but today, thanks to AI, they will learn the language of humans.

The potential offered by AI-enabled robotics is influencing sectors far beyond manufacturing, providing substantial efficiency improvements to more dynamic environments, such as healthcare and life sciences, as well as retail. Another example is the construction industry, where AI-powered robotics can make a material contribution to boosting productivity, enhancing safety, and sustainable construction practices.

“The construction industry is a great example of a sector where AI-powered robots will prove transformative, delivering real value by addressing many of the issues facing the industry today, including worker shortages, safety issues, and stagnant productivity,” said Segura. “Abilities such as enhanced recognition and decision-making offered by AI, coupled with advances in collaborative robots enable safe deployment alongside workers. These advances also enable robots to perform key tasks such as bricklaying, modular assembly and 3D printing with greater precision and speed, all while contributing to more sustainable construction by lowering emissions, such as concrete mixing on site, to reducing the need to transport materials across far distances with on-site assembly.”

Equipping mobile robots with 3D vision and intelligence allows them to navigate autonomously, reducing installation times from weeks to days and increasing speed and precision. Visual SLAM (Visual simultaneous localization and mapping) navigation, the industrial application of this technology, is a monumental step for the robotics industry.

Visual SLAM technology enables AMRs to make intelligent decisions, differentiating between fixed and mobile objects, and create a 360-degree point cloud of data. This enables safe, fully autonomous operation in highly complex, dynamic environments alongside people. This technology is already being used today in the logistics and automotive industries.

ABB Robotics has enhanced its logistics automation portfolio with the launch of the Robotic Item Picker — an AI and vision-based functional module that can accurately detect and pick items in unstructured environments in warehouses and fulfillment centers.

Using AI and real-time image recognition, the robot autonomously recognizes and picks items in an unstructured environment (up to 1,400 picks per hour with 99.5 percent precision). It helps customers automate order picking and sorter induction operations and is a central component to the goal of a fully automated warehouse, combining automated storage with automated order picking.

3DQI is capable of measuring faults that are less than half the width of a human hair at a pace 20× faster than traditional inspection tools. With accuracy below 100 micrometers, the technology combines the accuracy and repeatability of structured-light technology with speed and flexibility of robot to inspect 100 percent of the manufactured parts. It also makes it possible to achieve high-level quality inspection during the manufacturing processes to control, detect, and correct the fault where it happens.

The next frontier, ABB is working on a paradigm where people no longer need to learn the language of robots, but rather that robots learn the language of people. In a pick and place system, for example, instead of programming, people would instruct the robots with voice commands. This will allow SMEs without specific knowledge to use robots with minimal training. In the future, the robot will be able to ask questions in return in order to complete a task, progressing toward independent problem-solving intelligence.

This article was contributed by ABB (Auburn Hills, MI). For more information, visit here .