3D Modelling of Natural Structures

A core strand of research in robotics concerns itself with digitally modelling environments for navigation, task planning, and visual perception. Point clouds have become a method of geometry representation that are both fast and relatively inexpensive to acquire, making them ideal for applications in agri-food robotics.

At a high level, this project aims to enable the creation, manipulation, visualisation, and analysis of high-fidelity digital models of reality, with a specific emphasis on the modelling of natural structures. The PhD project will consider several technical challenges in relation to geometry processing, scene representation, and visual perception, leveraging point clouds as a primary modality of geometry representation. The PhD project itself will be split into several work packages, which aim to tackle different technical challenges in relation to the digital modelling pipeline.

The first work package will be concerned with the challenge of surface reconstruction. While point clouds offer a flexible and lightweight form of representation, their discrete nature makes representing fine detailed geometry in a digital model non-trivial; irrespective of a point cloud's density or resolution, the reconstruction of a continuous surface is mathematically ill-posed. Progress is achieved via regularisation, where typically hand-crafted conditions like local or global smoothness are introduced to reduce the space of possible solutions. In our approach we will leverage recurring geometry, along with the approximation power of neural networks, to implement a new algorithm that is able to produce high-fidelity reconstructions that combine local smoothness with globally learned features, for better reconstructions of natural structures.

The second work package will then move to consider the challenge of representation and reconstruction in large spatial domains, for example entire fields or forests. Generating point clouds with high enough density for reconstruction in large scales domains is challenging and scenes of this nature usually include occlusions. To overcome these limitations, this later work package will seek to consider fusing multi-view camera imagery, and geometry from point clouds, to produce neural implicit 3D representation models known as a neural radiance field (NeRF). NeRF models have been shown to give excellent results in generating novel views of complex scenes, ideal for scenes with occlusions. We will explore the technical challenges of using NeRFs for encoding large scenes that contain high-frequency features, for example, the leaves of trees.

Further work packages will also consider agri-food-specific extraction of semantic information, the ripeness of fruit for example, and other analysis of the digital models created within the project.

The proposed CDT provides a unique vision of advanced RAS technologies embedded throughout the food supply chain, training the next generation of specialists and leaders in agri-food robotics and providing the underpinning research for the next generation of food production systems. These systems in turn will support the sustainable intensification of food production, the national agri-food industry, the environment, food quality and health.

RAS technologies are transforming global industries, creating new business opportunities and driving productivity across multiple sectors. The Agri-Food sector is the largest manufacturing sector of the UK and global economy. The UK food chain has a GVA of £108bn and employs 3.6m people. It is fundamentally challenged by global population growth, demographic changes, political pressures affecting migration and environmental impacts. In addition, agriculture has the lowest productivity of all industrial sectors (ONS, 2017). However, many RAS technologies are in their infancy - developing them within the agri-food sector will deliver impact but also provide a challenging environment that will significantly push the state of art in the underpinning RAS science. Although the opportunity for RAS is widely acknowledged, a shortage of trained engineers and specialists has limited the delivery of impact. This directly addresses this need and will produce the largest global cohort of RAS specialists in Agri-Food.

The impacts are multiple and include;

1) Impact on RAS technology. The Agri-Food sector provides an ideal test bed to develop multiple technologies that will have application in many industrial sectors and research domains. These include new approaches to autonomy and navigation in field environments; complex picking, grasping and manipulation; and novel applications of machine learning and AI in critical and essential sectors of the world economy.

2) Economic Impact. In the UK alone the Made Smarter Review (2017) estimates that automation and RAS will create £183bn of GVA over the next decade, £58bn of which from increased technology exports and reshoring of manufacturing. Expected impacts within Agri-Food are demonstrated by the £3.0M of industry support including the world largest agricultural engineering company (John Deere), the multinational Syngenta, one of the world's largest robotics manufacturers (ABB), the UK's largest farming company owned by James Dyson (one of the largest private investors in robotics), the UK's largest salads and fruit producer plus multiple SME RAS companies. These partners recognise the potential and need for RAS (see NFU and IAgrE Letters of Support).

3) Societal impact. Following the EU referendum, there is significant uncertainty that seasonal labour employed in the sector will be available going forwards, while the demographics of an aging population further limits the supply of manual labour. We see robotic automation as a means of performing onerous and difficult jobs in adverse environments, while advancing the UK skills base, enabling human jobs to move up the value chain and attracting skilled workers and graduates to Agri-Food.

4) Diversity impact. Gender under-representation is also a concern across the computer science, engineering and technology sectors, with only 15% of undergraduates being female. Through engagement with the EPSRC ASPIRE (Advanced Strategic Platform for Inclusive Research Environments) programme, AgriFoRwArdS will become an exemplar CDT with an EDI impact framework that is transferable to other CDTs.

5) Environmental Impact. The Agri-food sector uses 13% of UK carbon emissions and 70% of fresh water, while diffuse pollution from fertilisers and pesticides creates environmental damage. RAS technology, such as robotic weeders and field robots with advanced sensors, will enable a paradigm shift in precision agriculture that will sustainably intensify production while minimising environmental impacts.