Longlab - Robomate

Challenge

The societal challenge is to maintain and grow the Irish manufacturing sector in the face of labour shortages and an aging workforce and thus improve economic prosperity. The manufacturing sector is critical in Ireland, contributing up to 37% of GDP and employing 12% of total working population. In particular, the Northern and Western region, the only Irish region classed as “in transition” as opposed to “developed” by the EU commission, has a strong manufacturing presence and is a significant regional employer. SMEs are pivotal in the manufacturing eco-system and are technologically advanced within their core business. Yet, many rely on flexible labour contracts for order fulfilment. Such roles are physically demanding, repetitive with unsatisfactory working conditions and hence are unattractive for new workforce entrants. Workers in physical roles retire earlier due to strain and acquired disability. Therefore, there is a growing labour shortage in manufacturing with lack of both skilled and unskilled labour, particularly affecting SMEs and threatening their future success. We believe flexible automation can undertake many of these repetitive tasks, thus improving conditions and creating knowledge economy roles. Investment in flexible automation will allow Ireland to maintain a thriving manufacturing sector robust to competition from low labour cost countries. Moreover, this will position the economy to profit from a renewed EU focus on reshoring and indeed a shift to make supply chains more robust and less dependent on external partners.

Solution

The solution is a software application that connects to any collaborative robot (Cobot) and 3D vision system. The software enables a human to teach robots manufacturing operations in minutes. It reads the robot’s state and vision data during teaching and controls the robot’s motion based on vision feedback during execution. To teach, the human physically guides the robot through the task. Our software extracts key points, matches them with the state and constructs a task model. During execution, the robot exploits this model to repeat the task compensating for position differences and environmental changes. Through a single demonstration, a non-expert user can automate manufacturing tasks using this software much faster than classical approaches. We envisage the solution on a passive mobile base, brought to location by a human, who teaches the task then commissions the system. As the solution executes the task, the human leaves to conduct other activities returning later to check progress or redeploy the system to a new operation.

Impact

The increased adoption of automation and robotics in SMEs will enhance international competitiveness by improving labor productivity, ultimately driving economic growth. By reducing production costs through labor savings and optimizing human resource utilization in core activities, businesses will achieve greater efficiency and profitability. Additionally, providing low-volume, high-complexity jobs to multinational corporations will contribute to their expansion.

Workforce transformation will also be evident, with employees shifting from manual labor to knowledge-based roles, leading to higher job satisfaction and improved retention rates. The Northern Western region, in particular, will benefit from increased high-value employment opportunities, further stimulating economic growth. Moreover, the transition from transient labor to more stable employment will be reflected in a higher ratio of permanent to temporary employees.

Upskilling initiatives will result in better pay for unskilled workers, as measured by an increase in promotions. Improved ergonomic conditions in factories, facilitated by reduced repetitive tasks and the implementation of safe collaborative robot (Cobot) systems, will contribute to fewer occupational injuries. Additionally, aging workers and those with physical limitations will benefit from better working conditions and increased job opportunities, leading to a decline in work-related disabilities and fewer forced retirements in the manufacturing sector.

Funding

This project is being conducted with the financial support of the EU Commission Recovery and Resilience Facility under the Research Ireland (Science Foundation Ireland) Future Digital Challenge Grant Number 22/NCF/FD/10929G’,