Robot skills for manufacturing: From concept to industrial deployment
Reference: http://www.sciencedirect.com/science/article/pii/S0736584515000575
Due to a general shift in manufacturing paradigm from mass production towards mass customization, reconfigurable automation technologies, such as robots, are required. However, current industrial robot solutions are notoriously difficult to program, leading to high changeover times when new products are introduced by manufacturers. In order to compete on global markets, the factories of tomorrow need complete production lines, including automation technologies that can effortlessly be reconfigured or repurposed, when the need arises. In this paper we present the concept of general, self-asserting robot skills for manufacturing. We show how a relatively small set of skills are derived from current factory worker instructions, and how these can be transferred to industrial mobile manipulators. General robot skills can not only be implemented on these robots, but also be intuitively concatenated to program the robots to perform a variety of tasks, through the use of simple task-level programming methods. We demonstrate various approaches to this, extensively tested with several people inexperienced in robotics. We validate our findings through several deployments of the complete robot system in running production facilities at an industrial partner. It follows from these experiments that the use of robot skills, and associated task-level programming framework, is a viable solution to introducing robots that can intuitively and on the fly be programmed to perform new tasks by factory workers.
In order to remain competitive in a globalized environment, manufacturing companies need to constantly evolve their production systems and accommodate the changing demands of markets. Currently, production is experiencing a paradigm shift from mass production to mass customization of products. The impact of this trend on production systems is that they should adapt to handle more product variation, smaller life cycles, and smaller batch sizes – ideally batch size 1. Today, robot-based production is an essential part of the industrial manufacturing backbone. However, the concept of an industrial robot statically placed in a cell and continuously repeating a carefully predefined sequence of actions has remained practically unchanged for many decades. Contrary to traditional robot macros, our skills are characterized as being general, in that they can handle a variety of objects, and self-asserting, in that they contain pre- and postcondition checks. Finally, this set of skills for a given industry can be naturally extracted from a careful analysis of industrial standard operating procedures (SOP).
Robotics is expected to be one of the main enablers of this transition to the transformable factory of tomorrow. To reach the demanded level of flexibility robots, or more generally mobile manipulators, need to be able to move autonomously, cope with uncertainty in interactions with humans and partially known environments, handle a variety of different tasks, and be able to be reprogrammed fast by non-robot experts when a new task in the factory arises.
As mentioned earlier, mobile manipulators can be one of the enablers in robotics to accommodate the higher demand for flexibility in future industrial production. We argue that the use of robot skills is the key to making this happen. We will begin by showing how robot skills have been identified from the current work procedures in the industry.
This work has been focused on developing robotic systems suitable for the envisioned transformable factories of tomorrow. We have presented a conceptual model for object-centered robot skills that are similar to the abstraction level used when instructing tasks to human workers. We have shown how task-level programming can be combined with our notion of robot skills. This combination effectively acts as a higher abstraction layer, freeing the user from having to specify details such as cartesian coordinates, reference frames, or action specific parameters. The fact that skills are applied on objects, coupled with condition checks in our skills, makes it possible to use very intuitive HRI interfaces, such as kinesthetic teaching and gesture-based teaching for the definition of tasks. As a result, the notion of skills, the way we described and tested it in this work, allows non-robot experts to intuitively interact with and program a complex robotic system, such as an industrial mobile manipulator, with only minor training. Finally, as any other system intended for industrial use, robots equipped with our skills have been deployed and tested in real industrial scenarios, showing their robustness and effectiveness. We believe that our robot skills constitute a significant step towards achieving transformable robots, and that such an approach can ultimately increase competitiveness of manufacturing companies.
