Dr-UBER: Drone Network for Medical Emergency Delivery in Essex
Small Business Research Initiative
Dr-UBER envisions establishing an urban multi-drone network for emergency medical and healthcare services, employing a "ride-hailing" concept to connect medical institutions, including hospitals, pharmacies, doctors/GPs, and medical laboratories. This innovative approach aims to facilitate the swift and secure delivery of emergency healthcare/medical services, such as defibrillators (AEDs) or blood, addressing availability and distribution challenges and, more importantly, increasing the survival rate of individuals experiencing out-of-hospital cardiac arrest (OHCA).
In pursuit of this goal, Airborne Robotics (AIRBORNE) and Anglia Ruskin University (ARU), as the subcontractor, propose a feasibility study to develop a multi-drone network providing "fly and deliver" services in Chelmsford, Essex. Chelmsford's strategic selection is based on its proximity to London and the challenges posed by congested roadways like the A12 and M11\. Identifying drone no-fly zones in and around the area serves as both a challenge to address and a practical context for the use-case study.
Beyond addressing service demands, the project will carefully assess and integrate regulations in aviation and medicine, ethical considerations, and the safe and secure operation of drones into the network architecture. The technical assessment will encompass factors influencing drone performance, including navigation systems, communication (speed, latency, data security), sensors, battery health, environmental conditions (weather), airspace access, detect and avoid (DAA) collision, and remote piloting and operation. Considering these intricate factors, a scalable, dynamic geofencing module and an Artificial Intelligence (AI)-driven "routing and scheduling" algorithm will be developed and integrated into the Dr-UBER urban multi-drone network. This integration presents an opportunity for nationwide implementation of Dr-UBER.
The study will evaluate the viability of the multi-drone network for operationalising emergency healthcare/medical services, thereby contributing to the support of the NHS. The data derived from the project will guide AIRBORNE in formulating a strategy for commercialisation, including seeking a particular CAA-Operating Safety Case permission. Given the surge in online prescriptions and the heightened demand for same-day delivery, exacerbated by the COVID-19 pandemic, there is a belief that Dr-UBER can significantly enhance healthcare logistics and bolster resilience within its supply chain.
Simulated Urban Environment for Last Mile Drone Logistics ("SimLogAI")
Last-mile deliveries play a crucial role for high-value manufacturing (HVM) in complex supply chains. Significant proportions of components are critical yet relatively lightweight (e.g.<10kg electronic components).
Drones will take a disruptive role in the near term as regulation has made a large step forward permitting beyond-line-of-sight(BLOS) flights under specific requirements, in a robust / controlled air and ground risk-mitigating environment. Using recent advances in IoT connectivity (5G/wifi) to control and optimize drone flight paths, coupled with data-driven AI simulation environment tools, it shall be possible to integrate a range of technologies to create autonomous new business models, which can be commercialized for the benefit of a number of sectors whereby time is of the essence. Logistics is seen as the largest and most promising subsegment in drone applications.
This study seeks to optimize the interplay between artificial intelligence and drone-supported last-mile delivery to improve supply chain efficiencies and create new, systematic, automated, airborne delivery systems. Through AI systems integrations, SimLogAI will be able to support manufacturing supply chains' on-time delivery while mitigating any posed risks of delays or financial penalties. Existing data suggests that although the frequency of such events vary, a single occurrence could have a devastating effect on production.
Many manufacturers are located in urban fringe sites because of expansive land requirements. Traditionally, logistics are confined to fossil fuel-powered land-based solutions, affected by increasingly congested road networks, and causing tailpipe emissions. Our advanced and sustainable AI drone solution will support longer flight paths with increasingly heavier payloads.
Coordinated AI-type inventories with supply chains across multiple locations using swarms of drones, innovative control and tracking systems and autonomous flight path optimization have the potential to revolutionize supply chains of HVM through digital technologies.
The project will address end-to-end challenges & opportunities for logistics supply chain stakeholders, providing enhancement to productivity, exploring the robustness & resilience of AI integrating drones in HVM supply chains. It will consider landing & delivery hubs as well as autonomous on-the-ground handling and transport systems (AGV/AutonomousGroundVehicle), low-carbon emissions delivery enhancements, simulation data validated path/ routing efficiency (air/ground) and regulation-compliant aerial safety assurance.
This project seeks to validate, investigate and test the fragmented approaches to this subject, unifying digital technologies, connectivity and policy areas to develop nationally relevant and scalable business models to transform logistics, creating an actionable roadmap to combine these elements together whilst also ensuring confidence, trustworthiness & reliability remains at its core.
Drone Swarm for Unmanned Inspection of Wind Turbines (Dr-SUIT): Battery Health Management, Hybrid Comms Systems and Operational Platform for Autonomous Offshore Windfarm Inspection
Airborne Robotics (AR), Ocean Infinity (Ocean) and Bentley Telecom (Bentley) are working in partnership with the University of Portsmouth (UoP) to develop drone swarming capabilities and an operational platform for an autonomous inspection in offshore windfarms (OWF). Utilising a system-of-systems approach, the project entitled “Dr-Suit”, focuses to build in drone swarm resilience and safety especially when facing the challenges including access and environment hazards, increased Operations and Maintenance (O&M) costs, and drones’ battery life limitation.
Although drones have been used for WT inspection, a drone swarm deployment offers benefits of larger/further coverage and reduced inspection time. Since drones are currently not designed for swarm operation at a standard use, Dr-SUIT will develop an algorithm to interplay, therefore progressively shift the design from a single pilot controlling a drone to a single pilot controlling multiple drones, optimised by the hybrid communication system (4G, 5G, satellite) integration. The 5G network will reduce the latency and increased bandwidth size and speed. The utilisation of satellite communications extends the coverage to the communication industries and cost-effective backhaul services. The hybrid system will address issues of latency, redundancy, and bandwidth size for detection’s continuous/big data relay, thus enhancing drone-to-drone, drone-to-operator and sensing performance during swarming operation.
Battery life is another issue when calculating power and flight time required for an entire operation (accounting flying to above ~200m turbines and inspecting ~70-90m long blades). A novel swarm-aware battery health management system with predictive analytics will be developed along with a battery recharging/swapping system which is needed for more realistic drone swarming missions. A barge with a small power unit will be utilised as a platform for drones to recharge/swap batteries, for a timely operation, and for a 5G mast and satellite. Essential to the swarm safe operation, a real time inspection scheduling and routing will be mathematically modelled factoring drone’s performances, turbine positions, and environment. A live demonstration of an optimised drone swarm deployment performing blades inspection will conclude this Phase 2 project.
RootDetect: Remote Detection and Precision Management of Root Health
Oilseed rape and canola are two closely related _Brassica_ crops which are widely grown in Europe and Canada, with a market size measured in the tens of billions of US dollars. The oil-rich seeds produced by both crops are consumed in multiple ways, as a source of food (oil with omega 3 fatty acids), animal feed (seed cake as a protein source) and industrial use (such as renewable energy and detergents). Clubroot disease caused by the soil borne root pathogen _Plasmodiophora brassicae_ is threatening production. Disease management depends on early detection of the disease followed by rapid treatment of affected areas of the field with soil products such as lime. However, clubroot disease occurs in patches across the field. Traditional scouting relies on crop walking and clubroot patches can easily be missed in large fields. Furthermore, when clubroot is emerging it rarely causes above-ground symptoms which are visible to the naked eye.
The RootDetect project will develop a semi-autonomous remote sensing tool that will efficiently scout large areas and 'see' clubroot symptoms earlier than the grower or agronomist. Affected areas in the field will then be mapped and linked to precision farming technology which will allow targeted treatment of infested patches. This will be cost effective for the grower and will minimise wastage and thus lower carbon emissions.
AIRBORNE ROBOTICS will build a specialized UAV prototype for the agricultural environment. ADAS will validate data from the UAV with in-field assessments of clubroot disease and SII Canada will develop the algorithms necessary for machine learning for identification/diagnostics purposes. The product/service enabled by this project will be an integrated, data driven clubroot management tool. This will combine UAV capability with on-farm software which optimises the long- and short-term economics of clubroot management, based on remotely-sensed spatial data. The RootDetect smart tool will be competitively priced to ensure it is accessible to end users and maximise uptake of its use.