Easy configuration of collaborative robots
In the Industry 4.0 factories of the future, we will meet robots that are collaborating with humans to solve a range of different manufacturing tasks. The vision is that by combining the power, precision and stamina of a robot, with the creativity, flexibility, and cognitive abilities of a human, it becomes possible to solve applications, which cannot be solved with traditional technologies.
Much research has been done in this area and a number of robots enabling human-robot collaboration are today commercially available.
In this talk, I will give a general overview of the state-of-art of collaborative robots.
In particular, I will focus on Human-Robot Interfaces, which makes it possible for non-robot experts to instruct and operate the robots.
Here, I will present a framework we have developed at Aalborg University for easy configuration of robots to new tasks. The framework applies a modular approach, which enables an operator to configure the robot hardware and to instruct the robot to match the specific manufacturing needs by combining and instantiating a number of predetermined hardware and control (or skill) modules. The configuration tasks are supported by a number of technologies (e.g. mobile devices, kinesthetic teaching, projection mapping).
A range of different users in different industries has tested the framework. The tests indicate that the framework really enables non-robot experts to instruct robots, paving the way for further application of collaborative robots in manufacturing industries.
MANTIS project: Cyber Physical System based Proactive Collaborative Maintenance
MANTIS’ proactive service maintenance platform and its associated architecture draw inspiration from the Cyber Physical System approach.
Physical systems (e.g. industrial machines, vehicles, renewable energy
assets) and the environment they operate in are monitored continuously by a broad and diverse range of intelligent sensors, resulting in massive amounts of data that characterise the usage history, operational condition, location, movement and other physical properties of those systems. These systems form part of a larger network of heterogeneous and collaborative systems (e.g. vehicle fleets or photovoltaic and windmill parks) connected via robust communication mechanisms able to operate in challenging environments.
Sophisticated distributed sensing and decision making functions are performed at different levels in a collaborative way ranging from (i) local nodes that pre-process raw sensor data and extract relevant information before transmitting it, thereby reducing bandwidth requirements of communication, (ii) over intermediate nodes that offer asset-specific analytics to locally optimise performance and maintenance, (iii) to cloud-based platforms that integrate information from ERP, CRM and CMMS systems and execute distributed processing and analytics algorithms for global decision making.
In this talk, I will describe the last updates from the project with a broad perspective, covering the data lyfe-cicle from the sensors that monitor the machine or equipment wear to the visualization of the intelligent conclusions obtained in the MANTIS-related intelligent and cloud-based platform.
Challenges and solutions for Internet of things in the industry
Industry 4.0 increasingly demands solutions for traditional embedded systems connected to digital platforms on the Internet. In this context, the Internet of Things poses a series of challenges in several areas: communications, encryption, low-cost hardware among other technological challenges like Big Data. The application of Big Data Analytics allows us to develop efficient, large-scale and heterogeneous attack detection systems for complex cyber-physical environments, such as smart factories.
This talk will give an overview of applications, the state of the art and the state of the practice in the Industrial Internet of Things era. It will also present some new techniques, tools and use-cases that leverage Big Data Analytics to efficiently detect large-scale and heterogeneous attacks in complex cyber-physical environments (smart factories), tackling the heterogeneity of the data created in modern plants or the time constraints of manufacturing plants.
