Periodic Reporting for period 2 - RoBUTCHER (A Robust, Flexible and Scalable Cognitive Robotics Platform) Reporting period: 2021-07-01 to 2023-06-30 Summary of the context and overall objectives of the project The meat sector is one of the most important in EU. Automation is a key in meeting food security and sovereignty in Europe. Traditional robotics and automation systems are too expensive, non-flexible and lack both scalability and robustness. A new pioneering automation concept advanced by scientists in the RoBUTCHER project, the Meat Factory Cell (MFC), has demonstrated a way to address these issues. This project has successfully developed and tested a high autonomous prototype MFC using core robotic technologies based on Artificial Intelligence (AI) and cognitive robotics.RoBUTCHER is an innovative approach that gives an alternative to conventional line production in abattoirs via parallel production in autonomous MFCs. This is particularly relevant to small- and medium-scale producers, where it offers productivity scale-up and scale-down, based on demand. This technology is potentially disruptive, and the project has developed, produced and tested this innovation.The results of RoBUTCHER are important for society, as they will enable robots with a higher degree of competence to enter the manufacturing space. Global development has increased attention on flexibility in meat processing. As the market for meat becomes increasingly international, product portfolios increase to meet the demand of new consumers. This is challenging for conventional solutions to handle and emphasises the need for RoBUTCHER. The inability to access robotics and automation by small and medium producers also exacerbates another ticking time-bomb in Europe, that is, availability of labour. Apart from economic considerations, robots will be required to overcome labour shortfalls, as well as contributing to making food processing safer, cleaner, and more sustainable. The recent pandemic and geopolitical events that affected the movement of workers and the food supply chain, have further accelerated the acceptance, and prepared the sector for deployment of novel RoBUTCHER technology. The results may also, with time, have impact for other sectors (e.g. other species such as beef, other foodstuffs, or entirely different materials) where handling materials with high variation and flexibility is important.The overall objectives of RoBUTCHER were as follows:1. Assessment of social, legislative and best practice meat industry requirements2. Development of novel technology modules for autonomous cutting trajectory planning, and integration with human–robot interfaces which provides remote intervention and training opportunities3. Adaptation of cutting tools to incorporate cognitive sensing, and development of gripping tools for grasping and manipulation of muscle, bone and internal organs4. Implementation and demonstration of RoBUTCHER MFC in a pilot scale environment at Technology Readiness Level 6 (industrial prototype).RoBUTCHER met the stated objectives. In conclusion, the results of RoBUTCHER are even more important for society than when the action began. Specifically, global events like the Covid pandemic and war in Ukraine demonstrated that food supply security is of paramount concern for society. Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far Social, legislative and best practice meat industry requirements were assessed as planned. From a robotics perspective, the existing legislation or standards do not preclude MFC inception in an industrial environment. From the meat safety perspective, the project has performed a comprehensive study of legislative texts, with findings reflecting the need for so-called “functional demands” when developing such texts. Encouragingly, WHO is now using terminology in line with these principles. RoBUTCHER has been well grounded in terms of industrial needs and best practices, and included end users from across Europe as part of a reference group. This has ensured that the work of the project remained relevant, as well as ensuring good input to studies addressing the social impacts of automation in meat processing.RoBUTCHER has developed several new vision-based AI approaches; 2D only (trachea location); 2D and 3D data combined (one method for MFC cutting, as well as limb grasping); 3D and computed tomography (another, more customisable, method for MFC cutting); 3D and X-ray (for cutting). The solutions cover a broad range of scenarios, including cutting of hot and cold meat, as well as entire and half carcasses: all while accommodating the biological variability that this entails. The post-project activities already show action from the Consortium to broaden this learning into other species, for example beef and turkey. Virtual Reality (VR) has allowed, for example, a butcher to remotely verify and adjust AI cutting trajectories in a 3D environment, prior to execution. Digital twins have enabled offline system planning and testing; the Consortium recognises the need for new R&D, where flexible and varying materials are better modelled within those environments.RoBUTCHER identified a gap in tooling for robots working with meat, and the result has been the development of new intelligent grippers and cutting instruments, including the patent-pending smart knife. Further R&D will continue beyond the project. Notably, studies conducted indicate that consumers cannot distinguish between robot and human cut meat; some may even prefer the former.RoBUTCHER succeeded in developing two industrially relevant prototypes (i.e. at TRL6), for hot and cold cutting. Furthermore, the project has resulted in no less than 17 key innovations, ranging from TRL4-9 by the end of the project. Regarding dissemination, 316 activities were undertaken, including workshops, demonstrations, scientific publications and more. A further 44 actions are planned post-project. Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far) - Novel AI methodologies for meat cutting, capable of recognising and adapting to biological variability.- Prototype automatic systems for meat cutting, applying new robotic methodologies.- New gripping and cutting tools, including sensor enabling, to provide robotic feedback.- Novel implementation of integration via software platforms, include Node-Red and Ocellus.- Introduction of collaborative robot concepts to meat cutting.- Teleoperation of industrial robots via VR.RoBUTCHER has advanced research in core technologies, such as cognition and human-robot interfaces, and has produced economic impact with at least two key innovations already reaching the market. Overall, the level of innovation in the agri-food sector has been increased, particularly for meat processors. Leading meat processors and suppliers are aware of the novel RoBUTCHER approach. A goal of the Consortium, post project, is to broaden the applicability of RoBUTCHER’s results to sectors with similar functional demands. In the longer term, RoBUTCHER paves the way for automation which is more scalable (both physically and economically), robust and flexible than available today. According to end users, implementation of the project results would reduce or eliminate the risk of injuries to which workers are exposed in the traditional meat factories, as well as improve conditions in relation to working hours. Further, it is likely to offer some improvement in gender equality, job diversification, as well as making employment in the sector more attractive to young people. RoBUTCHER Meat Factory Cell Concept RoBUTCHER Title and Tagline
