Periodic Reporting for period 3 - ACROBA (AI-Driven Cognitive Robotic Platform for Agile Production environments)
Período documentado: 2023-01-01 hasta 2024-12-31
The ACROBA project has successfully developed and validated a scalable, modular, and cognitive robotics platform designed to make automation more accessible for both small- and large-scale industrial applications. Traditionally, industrial robotics has been tailored for large-scale operations, making it costly and complex for SMEs. ACROBA overcomes these barriers by integrating plug-and-produce capabilities, artificial intelligence, and cognitive modules, enabling robotic systems to adapt to dynamic production environments while supporting mass customization and agile manufacturing.
The platform has been rigorously tested through five large-scale industrial pilots, demonstrating its ability to operate in diverse production settings. Additionally, twelve dedicated hackathons and two ACROBA On-Site Labs (AOSLs) facilitated technology transfer, validating the platform’s flexibility, efficiency, and seamless integration into cyber-physical systems. The project has also prioritized human-robot collaboration, ensuring compliance with safety standards and promoting a user-friendly approach to industrial automation.
ACROBA’s impact extends beyond technology, directly contributing to three United Nations Sustainable Development Goals (SDGs). By supporting SDG 9.2 the project promotes inclusive and sustainable industrialization, enhancing employment and economic growth in manufacturing. It also aligns with SDG 10.2 by fostering social and economic inclusion, making advanced robotics more accessible to businesses of all sizes.
The conclusions of the ACROBA action confirm the project’s success in delivering a cost-effective and flexible automation solution for agile production. Key technological advancements—including AI-driven cognitive capabilities, deep reinforcement learning for robotic task optimization, and modular sensor-based robotic cells—position ACROBA at the forefront of smart manufacturing innovation. By reducing technical and financial barriers, the project ensures long-term impact, paving the way for widespread industry adoption and continued development through a joint venture and the Single Entry Point (SEP) platform.
The platform has been rigorously tested through five large-scale industrial pilots, demonstrating its ability to operate in diverse production settings. Additionally, twelve dedicated hackathons and two ACROBA On-Site Labs (AOSLs) facilitated technology transfer, validating the platform’s flexibility, efficiency, and seamless integration into cyber-physical systems. The project has also prioritized human-robot collaboration, ensuring compliance with safety standards and promoting a user-friendly approach to industrial automation.
ACROBA’s impact extends beyond technology, directly contributing to three United Nations Sustainable Development Goals (SDGs). By supporting SDG 9.2 the project promotes inclusive and sustainable industrialization, enhancing employment and economic growth in manufacturing. It also aligns with SDG 10.2 by fostering social and economic inclusion, making advanced robotics more accessible to businesses of all sizes.
The conclusions of the ACROBA action confirm the project’s success in delivering a cost-effective and flexible automation solution for agile production. Key technological advancements—including AI-driven cognitive capabilities, deep reinforcement learning for robotic task optimization, and modular sensor-based robotic cells—position ACROBA at the forefront of smart manufacturing innovation. By reducing technical and financial barriers, the project ensures long-term impact, paving the way for widespread industry adoption and continued development through a joint venture and the Single Entry Point (SEP) platform.
The third reporting period (M25-M48) marked significant progress in the ACROBA project, ensuring the completion and validation of objectives. WP3 refined and tested sensorized robotic cells, improving setup times and optimizing bin-picking, inspection, and contour mapping, while validating human-robot collaboration (HRC) systems for safety. WP4 and WP5 deployed the ACROBA platform in real industrial settings, implementing fully automated "lights-out" lines in plastic and medical device industries and optimizing collaborative robotic cells for electronics and motor manufacturing. WP6 assessed the scalability and flexibility of the platform, conducting tests across five use cases and establishing ACROBA On-Site Labs (AOSLs) at ENSTO (Finland) and Croom Medical (Ireland) to validate complex tasks such as medical device inspection and bin-picking. WP7 focused on increasing project visibility through online content, hackathons, and major events such as Automatica 2023 and the European Robotics Forum 2024. WP8 finalized Exploitation and Sustainability Plans, initiated a joint venture, and refined standardization strategies, confirming that ACROBA has no direct competitors offering a similarly integrated solution. WP9 ensured efficient project management, with risk mitigation strategies, monthly coordination meetings, and financial forecasting, while WP10 maintained compliance with ethics and data protection regulations, performing a data protection impact assessment aligned with GDPR and AI Act.
The ACROBA project successfully demonstrated its cognitive robotic platform in multiple industrial applications, validating flexibility, scalability, and safety while achieving significant reductions in hardware, software engineering, and commissioning costs. Advanced safety measures for HRC were implemented, ensuring compliance with international standards. ACROBA also contributed to standardization efforts by defining methodologies for workplace safety and HRC process descriptions. From an exploitation perspective, the project laid the foundation for commercialization through the formation of a joint venture and the establishment of the Single Entry Point (SEP) web platform to facilitate future adoption. Several companies, including ENSTO and Croom Medical, have already expressed interest in integrating ACROBA into their manufacturing processes. Dissemination efforts included six mini-hackathons and one mega-hackathon with over 150 participants, as well as extensive industry visibility through scientific publications, presentations, and events such as Automatica 2023 and ROSConFr 2024. With successful validation across diverse industrial environments, ACROBA is positioned for future adoption. Its strong exploitation strategy and continued engagement with industry stakeholders will drive advancements in intelligent robotic automation and ensure a lasting impact in agile production.
The ACROBA project successfully demonstrated its cognitive robotic platform in multiple industrial applications, validating flexibility, scalability, and safety while achieving significant reductions in hardware, software engineering, and commissioning costs. Advanced safety measures for HRC were implemented, ensuring compliance with international standards. ACROBA also contributed to standardization efforts by defining methodologies for workplace safety and HRC process descriptions. From an exploitation perspective, the project laid the foundation for commercialization through the formation of a joint venture and the establishment of the Single Entry Point (SEP) web platform to facilitate future adoption. Several companies, including ENSTO and Croom Medical, have already expressed interest in integrating ACROBA into their manufacturing processes. Dissemination efforts included six mini-hackathons and one mega-hackathon with over 150 participants, as well as extensive industry visibility through scientific publications, presentations, and events such as Automatica 2023 and ROSConFr 2024. With successful validation across diverse industrial environments, ACROBA is positioned for future adoption. Its strong exploitation strategy and continued engagement with industry stakeholders will drive advancements in intelligent robotic automation and ensure a lasting impact in agile production.
ACROBA aims to progress beyond the state of the artin in the following points:
1) ACROBA aims to evolve the current software architectures for advanced robotic systems by adding different functionalities of vital importance in the development of robotic integrated systems, i) innovative definition of the semantic, ii) direct integration of the ACROBA platform with virtual simulation environments (Virtual Gyms) and iii) smooth transition from training environment to real environment
2) ACROBA will allow robots to be embedded neatly in the existing workflows of SMEs, improving robots autonomy (execution of sensor-based robotic skills), its programming (use of dummy tools & automatic generation of paths from CAD files) and its productivity and adaptability (new cognitive capabilities for the planning module)
3) ACROBA will ensure quick autonomous and collaborative cognitive robotic capabilities through the adoption and combination of complementary AI approaches, e.g. Deep Learning , Deep Reinformed Learning, Deep Imitation Learning and Evolutionary Computing.
During the first year, the framework to achieve this has been defined.
ACROBA expected impacts are as follows:
1) Demonstration of the potential for robotics to impact at scale in Agile production
2) Reduction of technical and commercial risk in the deployment of services based on robotic actors within Agile production
3) Greater understanding from the application stakeholders of the potential for deploying robotics
4) Demonstration of platforms operating over extended time periods in near realistic environments and promotion of their use
5) Develop the eco-system around the Agile Production to stimulate deployment
6) Contribution to the development of open, industry-led or de facto standards
1) ACROBA aims to evolve the current software architectures for advanced robotic systems by adding different functionalities of vital importance in the development of robotic integrated systems, i) innovative definition of the semantic, ii) direct integration of the ACROBA platform with virtual simulation environments (Virtual Gyms) and iii) smooth transition from training environment to real environment
2) ACROBA will allow robots to be embedded neatly in the existing workflows of SMEs, improving robots autonomy (execution of sensor-based robotic skills), its programming (use of dummy tools & automatic generation of paths from CAD files) and its productivity and adaptability (new cognitive capabilities for the planning module)
3) ACROBA will ensure quick autonomous and collaborative cognitive robotic capabilities through the adoption and combination of complementary AI approaches, e.g. Deep Learning , Deep Reinformed Learning, Deep Imitation Learning and Evolutionary Computing.
During the first year, the framework to achieve this has been defined.
ACROBA expected impacts are as follows:
1) Demonstration of the potential for robotics to impact at scale in Agile production
2) Reduction of technical and commercial risk in the deployment of services based on robotic actors within Agile production
3) Greater understanding from the application stakeholders of the potential for deploying robotics
4) Demonstration of platforms operating over extended time periods in near realistic environments and promotion of their use
5) Develop the eco-system around the Agile Production to stimulate deployment
6) Contribution to the development of open, industry-led or de facto standards