<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-06-03T15:52:43Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/5A677244-7457-4563-8403-D92F44663BC9" ns1:id="5A677244-7457-4563-8403-D92F44663BC9"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/1C7CFB7F-DAB5-4892-99ED-6CCE82B2E71C" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/D9AE38A2-AFD3-4F24-9812-22B4BFD57D18" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/D9AE38A2-AFD3-4F24-9812-22B4BFD57D18" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2026-04-29T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/FE7D9D83-7C09-446B-BE5C-D3E8197DF833" ns1:rel="FUND" ns1:start="2025-11-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10172270</ns2:identifier></ns2:identifiers><ns2:title>LYRA - Learning and Yielded Reconfigurable Autonomy</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Fast Start Response</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>Ross Innovation Ltd. is developing **LYRA --- Learning and Yielded Reconfigurable Autonomy** --- an advanced robotic system designed to perform tasks in highly confined, complex and hazardous environments. At its core is **Re-Vector**, a new type of modular robotic arm that exploits novel, patent-pending joint geometries to move with exceptional flexibility and precision in 3D space.

The system is particularly well suited for environments such as the inside of aircraft wings, nuclear decommissioning cells and space-based platforms --- where human access is impossible or extremely challenging, and unsafe.

The LYRA project will take Re-Vector to the next level by integrating intelligent control. This includes enabling the robot to interpret its surroundings in real time, adapt its movement by means of a process of trial-and-error learning, and learn how to perform tasks effectively --- even in unfamiliar or unpredictable settings. The goal is a smart, reconfigurable robot that not only reaches into tight or cluttered spaces, but also understands how to act once it gets there.

Robots that combine this level of mechanical flexibility with intelligent behaviour do not currently exist. Most are either physically limited --- unable to reach the full workspace --- or rely on extensive pre-programming and ideal conditions. LYRA aims to change that by combining extreme manoeuvrability with new forms of learning and environmental awareness.

The project focuses on three core developments:

1. **Enhancing the robot's motion planning and adaptability** using reinforcement learning
2. **Teaching core tasks through demonstration** and sensor-based feedback
3. **Laying the foundations for context-aware behaviour**, where the robot can recognise features in its environment and respond accordingly.

LYRA is built on a modular design approach, enabling multiple robotic formats to be assembled from a common set of parts. This reduces cost, reduces training requirements and maintenance complexity. Target use cases include inspection, repair, decontamination and servicing in sectors where access is difficult and safety is critical.

With support from Innovate UK, LYRA will demonstrate its potential across aerospace, nuclear, space, and industrial automation --- unlocking new capabilities for UK industry and enabling safer, more sustainable ways of working in the most challenging environments.</ns2:abstractText></ns2:project>