This collaborative research proposal between the Oxford Robotics Institute (ORI) and the ETH extends themes of embodied robotic intelligence outlined in Oxford's ongoing Programme Grant "Embodied Intelligence: From Sensing to Collaboration" to include physical intelligence - specifically dynamic manipulation in contact-rich environments and perception suitable for autonomy in wild, natural environments. We propose a strategic collaboration with Prof. Dr. Hutter and Dr. Cadena of ETH Zurich who are world leaders in dynamic locomotion, manipulation and navigation and ETH's Center for Robotics - a coordinated ETH initiative to grow robotics in ETH and Switzerland. Their Robot Systems Lab (RSL) regularly receives plaudits and recognition and has created 6 spin-outs. Interaction with other academics within the Center (e.g. soft robotics, autonomy, controls) is also envisaged. ORI brings expertise in perception for state estimation and navigation, deep learning for locomotion and manipulation and decision making, while ETH has a strong track record in mobile robotics, dynamic locomotion and control. Together, we will develop new approaches to address the challenges of autonomous manipulation and navigation with dynamic robots. Our proposed project is organised into two research strands, which will use the ANYmal quadruped robot as a common platform. The first strand will focus on 'Data-Driven Perception and Navigation ', while the second strand will focus on 'Contact Rich Manipulation for Mobile Platforms'. Together with ETH we have designed an exciting exchange programme that will strengthen our collaboration and benefit from substantive industry support. In addition, we plan to host a standalone symposium to promote the common research links between Oxford and ETH, and another public outreach event linked with one of the main robotics conferences (IEEE ICRA, RSS). In summary, the proposed collaboration presents a unique opportunity to collaboratively explore the challenges of unstructured autonomy and contact-rich manipulation by pairing advances from the first half of our programme grant with expertise from ETH's world class faculty and laboratories. Our proposed collaboration is timely, given the growing importance of the proposed research, while our unique combination of expertise has the potential to have significant impact both in UK academia and in a range of business sectors. We propose a clear research and demonstration plan involving collaborations with several companies in the nuclear sector and the manufacturer of a leading quadruped robot. The project will conclude with live on-site trials at a real nuclear facility.

Robots with legs and arms are likely replace most manual labour, especially in environments that are dangerous for humans, and revolutionize multiple services domains in the long-term. One of the main advantages of legged robots is that they can discretely make and break contact with the environment, in contrast to wheeled or tracked systems that require continuous contact with the ground. This way, robots with legs can modify their area of support from step to step, a requirement when negotiating challenging terrain and environments primarily built for humans. Also, the use of legs decouples the body from the robot's foot-print. This allows for wide areas of support with only small footprints, a major advantage when navigating passages, tight spaces, cluttered environments, etc. The high articulation of legged systems also allows them to manipulate their center of mass, so that the system's dynamics can be exploited for the task at hand, and to dynamically reconfigure their workspace for the benefit of their payload, i.e., increase a manipulator arm's reach or position a sensor suite in a preferred pose. The autonomous locomotion framework that we will develop will enable current technology to be used in industrial scenarios, especially in hazardous environments that are primarily built for humans. Examples of such places are nuclear power plants, factories, oil & gas facilities, etc., where typically industrial stairs are used and a system will need to overcome various terrain difficulties, such as step over pipes, gaps, climb up/down stairs, manoeuvre through narrow passageways. Legged systems in such settings can have a large variety of roles; starting from inspection, automated monitoring of the condition of a facility; maintenance, periodic recurring tasks that need to be performed typically by a human, to intervention when an anomaly is detected.