Connected and equipped with sensors and AI capabilities, machines can cooperatively work with people. Together, they can increase productivity and sustainability.
Robots need freedom. At least if they are working intelligently with humans. Out of the cage, into the open shop floor of a factory. However, with freedom, great challenges await robots, which previously only knew their small world behind protective grids and their highly specialized activities. Here they have to cope with humans who are vulnerable, sometimes unpredictable, but in any case always more important. The laws that Isaac Asimov formulated for robots 1942 in a short story still apply, especially the first one: a robot must not hurt a human.
To comply with this law, robots must be able to respond to human actions, in real time – just as we humans respond when we interact with others. What humans is given by nature must be made possible for robots with sensors that let them hear, smell, see and feel what is happening around them. These sensing capabilities are also prerequisite for collecting data and taking appropriate actions. Nevertheless, that is not enough. To enable continuous machine learning, data must be understood, combined, shared and interpreted. As a machine, they have to learn what data mean. Typically, this is done today via a data connection to a powerful cloud service. Big data applications analyze large amounts of data, recognize patterns and derive instructions for action, which are sent back to the robot or machine and implemented by actuators.
This bears some risks: Like any digital network, the connection from the robot sensor via its data link to the cloud service can be attacked and manipulated by cyberattacks. Security must be integrated into the solution from the beginning as all data loses its value if its authenticity and integrity cannot be assured. Ideally, this is done according to recognized security standards that ensure the interoperability of machines without tearing a hole into the security concept. And finally, sending data back and forth takes time; even if it is only a fraction of a second, it can make or break a human's safety when in direct contact.
That is why robots and especially those working cooperatively with humans, also known as ‘cobots’, need intelligence right up to their tips. Directly in the sensor, or at least in the immediate vicinity, the machine must recognize whether or not it counteracts the manufacturing process or poses a danger to a human. This decision has to be made in real time. In practical collaboration, the robots needs to know immediately what to do – without having to wait for data from the network. Meanwhile, continuous learning, such as how to train the robot's intelligence, can be done via powerful cloud services.
Whether in an industrial robot, or mobile robots for customer services, smart home or medical healthcare, semiconductors are the key enablers for all major robotic functions. They give machines human-like senses and real-time control. They connect them to the internet and energy-efficiently power their actions. And, they protect their identities, digital data and hence the network from unauthorized access. Interaction of all these components - from hardware to software - are perfectly coordinated in order to be able to react as a system with the required intelligence.
They will enable smart value chains and product lifecycles, from development to manufacturing and assembly, product delivery and predictive maintenance, and recycling. The aim is to make manufacturing processes more flexible, scalable and efficient to support the people who work with them and conserve scarce resources.
Discover the future of industrial IoT that is full of new opportunities to develop better processes and deliver better products to customers.
We make IoT work.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.