The AI-PRISM consortium holds the necessary expertise to strategically improve the EU Smart manufacturing value chain in four domains: collaborative environment, robot perception and recognition, robot programming and human factors. We are working to achieve a suitable trade-off between complementary and overlapping among the industrial partners.
The essence of our project is social human-agent-robot teams’ collaboration with human-centred as its core, where all human behavioural (physical and verbal, psychological) developed models guarantee intuitive, safe, and ethical interactions in industrial workspaces. We have our expert English partner Cranfield University (CRAN) and their Structures, Assembly, and Intelligent Automation department to make this possible and shift the paradigm. They will lead the work on scientifically establishing human responses and requirements that need to be applied in designing and implementing AI-PRISM solutions and provide qualitative and quantitative data to demonstrate the impacts and improvements of the new solutions.
CRAN is an exclusively postgraduate university that creates leaders in technology and management. They work closely with businesses, industries, and governments across the world. Through their industry partnerships, applied research projects such as AI-PRISM, executive education, and professional development programmes, they work with over 1,500 companies and organisations. Therefore, their extensive experience is precious for our Human-robot collaboration behavioural analysis and modelling and a framework for assessing and developing human skills and abilities for working with robots.
Today the CRAN team is sharing a video introducing their Intelligent Automation Lab, which is twelve of the UK’s top robotics research centres and cutting-edge research in Robot Lab Live, presented by our colleague Iveta Eimontate, a research psychologist. The unique facility is well-equipped with various industrial robots, including a FANUC CR-35iA collaborative robot that can be configured in individual and collaborative cells. The physical elements are supported by software resources allowing research solutions to be investigated virtually.
UPV has already worked on the AI-PRISM architecture, including usage models and functional and technical specifications, and is working on AI-enhancing tools regarding reasoning, acting, and control. They are focusing on coordinating different agents and ensuring smooth control of operations in a dynamic manufacturing environment. Challenges addressed by UPV include path planning for mobile robots, task planning, and optimal task assignment for human and robotic agents.
Furthermore, UPV is working on AI-enhancing tools regarding reasoning, acting and control. At the AI-PRISM collaborative ambient level, the focus is to coordinate different agents, ensuring a smooth control of operations in a dynamic manufacturing environment. Challenges addressed by UPV include path planning for mobile robots and task planning and optimal task assignment for human and robotic agents. By using model-driven methods based on industrial process models and the capabilities of agents for rapid response reprogramming, where events related to human-robot collaboration and different elements of manufacturing will be coordinated, we will allow production replanification and product specifications changes, including batches, materials, and robot-human tasks rescheduling.
Environment-reactive methods are developed for smooth control of collaborative tasks without complex reprogramming or reunification for large and complex scenarios. Also addressed is operations execution control, ensuring that the target objectives are met through centralised coordination mechanisms using iterative control methods or hybrid coordination mechanisms, which combine centralised and distributed (agent level) control mechanisms.
UPV is also the research partner and technology provider with the Institute of Informatics and Technology (ITI) in the furniture manufacturing industrial case. Their objective is to introduce a system that allows the collaborative robot to learn from humans and perform different tasks of a more repetitive nature, such as painting or sanding, so that human operators can focus on tasks that provide more significant added value to the company. AI-PRISM estimates this will increase process productivity by 20% and halve manufacturing defects.
Do you want to learn more about AI-PRISM and the team behind the project? Subscribe to our newsletter and follow us on LinkedIn and Twitter, so you don’t miss a thing!