37 www.drivesncontrols.com February 2024 ROBOTICS AND AUTOMATED MANUFACTURING n What’s the future for piece-picking robots? What news can there possibly be on piece-picking robots? Arm nds item, picks it up, manipulates or orients it, puts it in the right place – end of. It’s a classic application of industrial robotics and has been so for four decades – at least on high-volume production lines. But in a sense, that application is barely robotics at all – functionally, an old-fashioned juke box did much the same thing, and the machines can typically only work with a limited set of items (often just one), presented to it in a structured way. As early investors in robotics discovered to their cost, these “general-purpose” robots were, in practice, highly task-speci c. Although they have become essential in highvolume production, they have been of limited use in warehouses and similar situations where the need is to pick from a wide range of items varying in shape, size, robustness and orientation. Now, however, advances in sensors, vision systems, handling devices and the means of controlling them, including the beginnings of Machine Learning (ML) and Arti cial Intelligence (AI), are making general-purpose picking robots a practical reality. Presented with a mixed selection of items, robots can now identify the correct piece, either by analysing the input from a vision system, or by scanning a barcode or RFID signal. Either way, algorithms can work out the current and required orientation. The robot can handle the piece according to parameters“attached”to the identity of the piece, including what tool to use to pick the piece up, and how much force is appropriate – or, in the case of increasingly popular manipulation by vacuum suckers, which elements from an array of suckers to use, and how much suction to apply. Using developing forms of ML/AI, the robot can be “trained”to deal with novel items, and even to optimise its own operations. This is important for many industries because until now, piece-part-picking has tended to be highly labour-intensive and stubbornly resistant to automation. Many parts were awkwardly shaped, too fragile, too small or there was too large a range of sizes/weights. Also, they might need prior operations to present them in the right orientation for the robot, or there may be quality issues which require pre-screening, and so on. In these circumstances, any return-oninvestment in automation has often seemed nebulous, and manual labour has often been preferred. But now, not only is human labour scarce and increasingly expensive, but manual pick rates may be slow by comparison with more advanced forms of automation, and errorprone – often exacerbated by illness or fatigue. A business operating in, for example, directto-consumer pharmaceuticals, cannot tolerate less than 100% accuracy. Similarly, there is no “acceptable”level of damage to electronic components. This cannot be guaranteed relying on manual handling. However, the good news is that item-picking technology is moving ahead rapidly and is fast becoming aordable to SMEs, with reasonable ROIs. So, as labour continues to be scarce and costly, piece-picking robots are likely to become increasingly attractive, and when allied with scalable AMRs (autonomous mobile robots), can represent signi cant de-risking. There are several options for deploying picking robots. The arms may be in xed locations with goods reaching them on conveyors, AMRs, mobile racks, carousels or other technologies – with the completed picks being removed using similar options. Or they may rove the shop oor mounted on AMRs. They may be cobots, designed to work safely alongside people, or they may be fenced o physically, or through software and safety functions. Previous piece-picking robots have often required goods to be presented in de ned orientations so that a barcode can be scanned, or a shape recognised, or so that they don’t overlap. This can require either manual intervention or an array of handling devices that together may be as complex and expensive as the robot itself – as well as taking up space. It is increasingly likely that with advanced, AIenabled vision and other technologies, much or all of this preparation can be avoided. Piece-picking robots are becoming far more dextrous, quick-learning and adaptive. But, of course, we still need to train them with the right images and algorithms. Suppliers and integrators are working out the most eective ways of organising this. What is evident however is that, at this stage in the development and adoption of the technology, there is a real need for open collaboration between all of the travellers on this journey into robotic picking. n Piece-picking robots are making big strides and with the aid of AI could soon be within the grasp of SMEs. Dan Migliozzi, head of sales at the systems integrator, Invar Group, sets out where we are on the journey. Piece-picking robots are becoming far more dextrous, quicklearning and adaptive.
RkJQdWJsaXNoZXIy MjQ0NzM=