Learning Topological Representations of Multi-Scale Environments

Context and Potential Impact
In many robotics applications, from indoor robots to autonomous vehicles, the robot needs to autonomously perform tasks in novel environments. To do so
successfully and efficiently typically demands some knowledge of the robot's surroundings, thus requiring the collection of a map or other representation of
the environment.
With the advent of learning-based localisation, planning, and navigation algorithms, the problem of using deep learning methods to learn meaningful maps
or other representations of agent environments has grown more important. While classical mapping algorithms such as Simultaneous Localisation and Mapping
(SLAM) have been successfully used in some settings, learned representations of an environment promise to be more memory-efficient and help other algorithms
(e.g. ones based on reinforcement learning) to more easily learn downstream tasks.

Aims and Objectives
In this DPhil project, we develop systems that learn representations of environments on multiple scales, explicitly enabling these systems to leverage fundamental concepts about space and scene geometry.
We hypothesise that, because they utilise concepts about the relations between information on large and small scales by design, the representations learned by these systems can naturally integrate information on different scales about the
environment and allow downstream planning algorithms to easily move between these scales.

Novelty of the Research Methodology
In the past, there have been a number of efforts to design learning algorithms that employ topological concepts to generate meaningful maps of environments. However, these methods were developed to accommodate only a single, fixed
scale on which the environment can be represented. This approach becomes inefficient when the scales on which the agent has to perform tasks span a wide range of scales, for example, when a robot has to find a specific location a
large distance away. In such a case, one either has to sacrifice resolution or accommodate a very detailed representation of the environment that can make planning computationally expensive.
To alleviate this issue, we focus on developing algorithms that integrate geometrical and spatial concepts to generate representations that expose information only on the scale required while also enabling smooth and natural changing of
scale. Integrating an end-to-end differentiable planning algorithm can enable us to meta-train the algorithm that extracts these representations as well as
demonstrate the applicability and versatility of such maps.
Alignment to EPSRC's Strategies and Research
Areas
Artificial Intelligence Technologies, Robotics, Information Systems, Image and Vision Computing.
Collaborators
At this stage, there are no industrial collaborator

AIMS's impact will be felt across domains of acute need within the UK. We expect AIMS to benefit: UK economic performance, through start-up creation; existing UK firms, both through research and addressing skills needs; UK health, by contributing to cancer research, and quality of life, through the delivery of autonomous vehicles; UK public understanding of and policy related to the transformational societal change engendered by autonomous systems.

Autonomous systems are acknowledged by essentially all stakeholders as important to the future UK economy. PwC claim that there is a £232 billion opportunity offered by AI to the UK economy by 2030 (10% of GDP). AIMS has an excellent track record of leadership in spinout creation, and will continue to foster the commercial projects of its students, through the provision of training in IP, licensing and entrepreneurship. With the help of Oxford Science Innovation (investment fund) and Oxford University Innovation (technology transfer office), student projects will be evaluated for commercial potential.

AIMS will also concretely contribute to UK economic competitiveness by meeting the UK's needs for experts in autonomous systems. To meet this need, AIMS will train cohorts with advanced skills that span the breadth of AI, machine learning, robotics, verification and sensor systems. The relevance of the training to the needs of industry will be ensured by the industrial partnerships at the heart of AIMS. These partnerships will also ensure that AIMS will produce research that directly targets UK industrial needs. Our partners span a wide range of UK sectors, including energy, transport, infrastructure, factory automation, finance, health, space and other extreme environments.

The autonomous systems that AIMS will enable also offer the prospect of epochal change in the UK's quality of life and health. As put by former Digital Secretary Matt Hancock, "whether it's improving travel, making banking easier or helping people live longer, AI is already revolutionising our economy and our society." AIMS will help to realise this potential through its delivery of trained experts and targeted research. In particular, two of the four Grand Challenge missions in the UK Industrial Strategy highlight the positive societal impact underpinned by autonomous systems. The "Artificial Intelligence and data" challenge has as its mission to "Use data, Artificial Intelligence and innovation to transform the prevention, early diagnosis and treatment of chronic diseases by 2030". To this mission, AIMS will contribute the outputs of its research pillar on cancer research. The "Future of mobility" challenge highlights the importance the autonomous vehicles will have in making transport "safer, cleaner and better connected." To this challenge, AIMS offers the world-leading research of its robotic systems research pillar.

AIMS will further promote the positive realisation of autonomous technologies through direct influence on policy. The world-leading academics amongst AIMS's supervisory pool are well-connected to policy formation e.g. Prof Osborne serving as a Commissioner on the Independent Commission on the Future of Work. Further, Dr Dan Mawson, Head of the Economy Unit; Economy and Strategic Analysis Team at BEIS will serve as an advisor to AIMS, ensuring bidirectional influence between policy objectives and AIMS research and training.

Broad understanding of autonomous systems is crucial in making a society robust to the transformations they will engender. AIMS will foster such understanding through its provision of opportunities for AIMS students to directly engage with the public. Given the broad societal importance of getting autonomous systems right, AIMS will deliver core training on the ethical, governance, economic and societal implications of autonomous systems.