Many assembly and disassembly tasks in manufacturing have small clearances and limited accessibility, such as shaft-hole insertion/separation and bolt-nut assembly/disassembly. Using robots in these contact-rich tasks is more complex than those having no physical contacts (e.g. computer visual inspection) or simple contacts (e.g. cutting, welding, pick-and-place). The deployment of robots in contact-rich tasks has been limited to date. The contact-rich tasks that involve complex shapes, small clearances or deformable materials are particularly challenging to robotise due to the likely events of jamming and wedging. Our previous research has investigated techniques that allow robots to learn contact-rich skills (e.g. complex motion plans and force control policies) using two main AI-based pathways: (1) self-learning from trial-and-error, and (2) learning from human demonstrations. The two participating universities, Birmingham and Sheffield, have research experiences in (1) and (2), respectively. A key challenge observed in the current research is that in many cases a robot's contact-rich skill cannot be performed by other robots of different motion properties (e.g. accuracy, precision and stiffness), or be applied to a new task with variations (e.g. differences in object geometry, shape, and materials). This is because a robotic contact-rich skill, i.e. control policies and motion plans, is usually acquired for a specific task and cannot be adopted by new robots or in new tasks. STAMAN's vision is to create AI-based mechanisms to allow robots to share and recreate obtained digital skills (e.g. motion and force/torque control strategies) to allow easy automation scale-up for contact-rich tasks. This includes considering two research questions: 1) For skill transfer - how can a contact-rich skill be quickly transferred to a different robot (e.g. transferring a bolt-nut separation skill from a high-precision robot to a low-precision robot)? 2) For skill augmentation - how can existing contact-rich skills be used to create new contact-rich skills (e.g. augmentation of rigid-material skills to deal with soft materials)? The project will develop a portfolio of research into the science of digital skills for contact-rich tasks, focusing on common manufacturing tasks such as bolt-nut assembly/disassembly, peg-hole insertion/separation, and shaft-ring assembly/disassembly. The ability to transfer and augment digital skills for contact-rich tasks will allow automation systems to be implemented on a larger scale, with minimal manual setting and fine-tuning required. STAMAN aims to create transferrable and augmentable digital skills that will underpin the development of mass machine skills for future manufacturing, similar to how industrial robots have contributed to modern mass production. The proposed research encourages more use of robots in assembly (e.g. automotive, aerospace, electronics, etc.) and disassembly (e.g. repairs, remanufacturing and recycling), and thus directly contributes to the UK's Made Smarter initiative and the circular economy goals.

Disassembly is an essential operation in many industrial activities including repair, remanufacturing and recycling. Disassembly tends to be manually carried out - it is labour intensive and usually inefficient. Disassembly requires high-level dexterity in manipulations and thereby can be more difficult to robotise in comparison to the tasks that have no physical contacts (e.g. computer visual inspection) or simple contacts (e.g. cutting, welding, pick-and-place). Robotic disassembly has the potential to improve the productivity of repair, remanufacturing, recycling, all of which have been recognised as key components of a more circular economy. The existing procedure and state-of-the-art techniques for disassembly automation usually require a comprehensive analysis of a disassembly task, correct design of sensing and compliance facilities, efficient task plans, and a reliable system integration. It is usually a complex, expensive and time-consuming process to implement a robotic disassembly system. This project will develop a self-learning mechanism to allow robots to learn disassembly tasks and the respective control strategies autonomously, by combining multidimensional sensing and machine learning techniques. This capability will help build a more plug-and-play disassembly automation system, and reduce the technical difficulties and the implementation costs of disassembly automation. It is expected the next generation industrial robotics can be adopted in more complex and uncertain tasks such as maintenance, cleaning, repair, remanufacturing and recycling, where many processes are contact-rich. Disassembly is a typical contact-rich task. The Principal Investigator envisages that self-learning robotic disassembly will provide key understandings and technologies that can be adopted to the automation of other types of contact-rich tasks in the future to encourage a wider adoption of robots in the UK industry.

High value manufacturing is an essential component of the UK economy, contributing strongly to our economic prosperity and engineering status around the world. The growth in high value manufacturing to support aerospace, nuclear and other high integrity engineering components, has placed huge pressure on the rapid delivery of reliable and high quality Non-Destructive Evaluation (NDE) to inspect these parts. Currently, much inspection of safety critical components (sometimes requiring 100% part inspection) is performed manually, leading to significant bottlenecks associated with the NDE. Existing robots typically follow pre-programmed paths making them unsuitable to handle, inspect and disassemble parts with a significant tolerance or variability. A new end-to-end approach is needed, embracing manufacture, transport through factory, parts alignment, parts tracking, and inspection (both surface form metrology and NDE) with the associated high volume data management feeding into the quality and assurance compliance processes. Exactly the same process bottlenecks occur when we translate the problem to the regime of Remanufacturing, hence the integrated approach taken through this proposal. Remanufacturing has been identified as being central to the creation of economic growth in the UK and global markets. With supplies of resources and energy limited, the transition to a low carbon economy with strong emphasis on resource efficiency is key to the UK's Industrial Strategy. Remanufacturing can support this transition by achieving significant impact in all industrial sectors through preventing waste, improving resource management, generating sustainable economic growth, increasing productivity and enhancing competitiveness. AIMaReM (Autonomous Inspection in Manufacturing& Remanufacturing) provides a unique combination of data collection, processing and visualisation tools combined with efficient robot path planning and obstacle avoidance, with a focus on manufacturing inspection (NDE and surface form metrology). The project will deliver an automated, systems integrated solution, that will be of direct benefit to the manufacturing sector to allow faster integrated inspection and parts handling, thus saving time, and reducing costs whilst enhancing quality and throughput.

Construction is significantly behind other UK sectors in productivity, speed, human safety, environmental sustainability and quality. In addition to inadequate building supply and affordability in the UK, humanitarian demand and economic opportunity for construction is set to increase substantially with global population growth over the next 40 years. However, with an aging work-force and construction considered to be one of the most dangerous working environments, the industry needs to explore radically new approaches to address these imminent challenges. While increased off-site manufacturing provides a partial solution, its methods are not easy to automate. Where individual mass-produced parts can be moved efficiently through production assembly lines that separate workers from dangerous machinery, building manufacturing involves mass-customisation or one-off production at a larger scale. This requires machinery and people to move around, and potentially work inside of a fixed manufacturing job e.g. a prefabricated or on-site house, as various independent and parallel tasks are undertaken in safety-compromised, overlapping work-zones. To address these issues, this project investigates fundamentally new operational and delivery strategy for automation to offer new ways of working with robots. Automation of shared construction environments requires robotic capabilities to be flexible and adaptive to unpredictable events that can occur (indoors or outdoors). Social insects such as termites, despite their small size and individual limitations, show an ability to work collectively to design and build structures of substantial scale and complexity; by quickly and efficiently organising themselves while also providing flexible, scalable coordination of many parallel tasks. Inspired by this model of manufacture, this project will develop an innovative multi-agent control framework that enables a distributed team of robots to operate in a similar way for the manufacture and assembly of buildings undertaken by off-site manufacture, on-site construction, or hybrid solutions using on-site factories. This requires the enhancement of existing robots, and development of new capabilities for collision avoidance and collaborative working. As many building tasks require specialist equipment, heterogenous teams comprised of different robot platforms such as agile mobile ground vehicles (UGVs), aerial vehicles (UAVs), alongside larger scale industrial robot arm, track and gantry systems, will be able to collaborate, and collectively undertake tasks beyond the capabilities of each individual robot such as lifting objects heavier than any one robot's payload capacity. To address construction relevant challenges, we will integrate capabilities for additive manufacturing, manipulation and assembly for building and building-component scale manufacture, in addition to computational means for individual robots to make local decisions. The final research deliverable will be the demonstration of the world's first collective multi-robot building manufacturing system that can autonomously build parts such as a façade or roof, assemble a structure, or construct a freeform building pavilion. We will also integrate these technologies within prototype building systems themselves, to create a new type of 'active' building that can use a multi-agent system to self-regulate energy and harvest data to provide a closed operational ecology between design, manufacturing, construction and building use, revolutionizing the way we manufacture, operate and use buildings. Further, evaluation frameworks will be developed to assess multi-robot construction and obtain objective measures for collective systems to deliver greater resource efficiency, quality, speed, safety and up-time compared with established construction methods. In doing so, we will establish new metrics quantifying the impact of these technologies from both economic and environmental perspectives.

The use of autonomous robotic technologies is increasingly common for applications such as manufacturing, warehousing, and driverless vehicles. Automated robots have been used in chemistry research, too, but their widespread application is limited by the cost of the technology, and the need to build a bespoke automated version of each instrument that is required. We have developed a different approach by using mobile 'robotic chemists' that can work within a relatively standard laboratory, replicating the dexterous tasks that are carried out by human researchers. These robots can operate autonomously, 24/7, for extended periods, and they can therefore cover a much larger search space that would usually be possible. Also, the robots are driven by artificial intelligence (AI) and can search highly complex multidimensional experimental spaces, offering the potential to find revolutionary new materials. They can also carry out multiple separate experiments in parallel, if needed, to make optimal use of the available hardware in a highly cost-effective way. Our proposal is to establish a globally unique user facility in Liverpool that covers a broad range of materials research problems, allowing the discovery of useful products such as clean solar fuels catalysts, catalysts for plastics recycling, medicinal materials, and energy materials. This facility will allow researchers from both academic teams and from industry to access this new technology, which would otherwise be unavailable to them. Because the automation approach is modular, it will be possible for users to bring along specific equipment for their experiments to be 'dropped in' temporarily to create new workflows, greatly expanding the possible user base. The scope here is very broad because we have recently developed methods that give these robots have very high placement precision (+/- 0.12 mm): to a large extent, if a human can use the instrument, then so can the robot. We have identified, initially, a group of 25 academic users across 12 universities as 'day one' prospective users, as well as 7 industrial organisations with a specific interest in this technology. The potential user base, however, is far broader than this, and we will solicit applications for access throughout the project and beyond. This will be managed by a Strategic Management Team and an Operational Management Team that involves academics as well as permanent technical, administrative, and business development staff in the Materials Innovation Factory in Liverpool. Our overall objective is to build a sustainable AI-driven robotic facility that will provide a unique competitive advantage for the UK to discover new functional materials on a timescale that would be impossible using more conventional research methodology. In addition to focusing on excellent science, we will also consider diversity and career stage when prioritising access; for example, even a short, one-week visit to this autonomous facility might lead to 100's or even 1000's of new materials with associated property measurements, which might radically transform a PhD project or the change the direction of the research programme for an Early Career Researcher. This facility will therefore build the base of the UK research pyramid, as well as supporting activity that is already internationally leading, and our day-one user base includes researchers at all career stages.