Public Funding for OXA Autonomy Ltd

Caterpillar, the world's leading supplier of off-highway equipment and leader of automation in the mining industry, will partner with Oxbotica, an innovation leader in the field of robotics and machine learning, to deliver a breakthrough in cost effective autonomous solutions for heavy duty off-highway equipment. This will enable the benefits in productivity, safety and well being of site operatives that have been demonstrated in high value ore mining to be expanded into newer industry sectors such as quarry and construction. Oxbotica's leading edge technology, currently in test in a number of automotive companies and in both on and off-highway CAV projects and in space exploration, offers the potential to use a significantly lower costs approach, whilst also offering the potential to deal with the much more dynamically changing environments of large construction projects. In this project we intend to develop a new drive-by-wire variant of a Caterpillar Articulated Truck and equip it with Oxbotica's Selenium autonomy system. We will benchmark capability in tough environments and identify technology components from other domains that translated readily to construction. At the end of the project we will run demonstrations on customer sites, investigating the incremental performance improvement that full autonomy would bring versus today's manually intense operations.

This project will take a crucial step towards enabling fully driverless autonomy - the removal of all human operators from an autonomous vehicle. Full autonomy (SAE Level 4/5), both technically and commercially, necessitates driverless operation without constant human supervision. This project aims to tackle the complex transitory step from the current reliance during field trials on an in-vehicle safety driver to fully remote operation where there is no vehicle occupant. It will build the foundations of fully autonomous operations in public environments, specifically in the domain of autonomous goods delivery. The project will be led by Oxbotica, whose innovative autonomy software has been extensively trialled on the streets of Birmingham, Oxford and London in previous Innovate UK projects. Our consortium also includes TRL, a global centre for innovation in surface transport and mobility, BSi, the leading UK national standards body, and UKAEA-RACE, a CCAV test bed in Culham, Oxfordshire, with which Oxbotica has a longstanding relationship. The project continues a successful partnership between these entities and introduces Ocado Group, UK based pioneering online grocery technology company, as a future AV fleet operator. The project has two essential paths of innovation - technical and safety assurance. These paths are of equal importance, both in achieving fully remote operation and in ensuring equivalent functional and operational safety. On the technical path, Oxbotica will be developing brand new redundant monitoring and fallback capabilities, which will allow an autonomous vehicle to run without real-time human supervision. On the safety assurance path, Oxbotica and its partners will develop new operational and safety assurance processes that will enable fully autonomous trials to be conducted. Oxbotica holds the distinction of being the first organisation to be audited against vehicle autonomy safety standard PAS1881, and will also refine its existing PAS1881-based safety case to address the removal of the safety driver, and the systems safety questions this introduces. With this project, Oxbotica and its industry-leading partners aim to continue their extensive history of technical achievement and industry-leading safety assurance mechanisms, and to take those first crucial steps towards true vehicle autonomy.

Oxbotica, an innovation leader in the field of robotics and machine learning will partner with QinetiQ a world leader in the provision of robotics and autonomous systems for complex environments, to deliver a breakthrough in cost effective self-driving solutions for heavy duty off-highway equipment. This will enable benefits in productivity, safety and well-being of operatives to be demonstrated in high value construction, mining and defence applications. Oxbotica's leading edge technology, currently under test with a number of automotive companies and in on-highway CAV projects offers the potential to use a low cost camera-based approach to self-driving, which enables the potential to deal with the much more dynamically changing environments of large construction projects. In this project QinetiQ will develop a conversion kit that enables drive-by-wire control for large off-highway vehicles, and will then integrate it with Oxbotica's Selenium autonomy system. As a part of the project we will run demonstrations that benchmark capability in tough off-road environments and explore deployment into industries ranging from airports to construction to defence. Finally the partners will integrate a fleet-level command and control system that enables many AV's to interact with other varieties of transportation. This will include a goal-based mission planning system that optimises the route the vehicle will take and will factor in dynamic route conditions and constraints to ensure the vehicle progresses safely and efficiently.

"Project Apollo will deliver a new mobility service: autonomous ride-sharing vehicles in the London Borough of Greenwich. This service is for residents or workers in areas which are poorly served by existing public transport and driven services. The Apollo pilot will be led by Addison Lee, Britain's largest-scale and most trusted private-hire operator, which carries 10million passenger a year in 350 cities around the world. The consortium includes Oxbotica, which has clocked up more autonomous vehicle miles than any other company in Britain, Nominet which is a world-leader in cybersecurity, Immense which is the UK's expert in fleet simulation and DG Cities, which brings the essential understanding of city needs. Apollo's pilot will be the largest in Europe, operating over 12 months with a fleet of 15 Ford vehicles, capable of SAE Level 4\. The aim is to carry out 25,000 passenger trips, covering 300 million kms and prepare to launch a service which is viable commercially, for customers and for the city. Once tried and tested in London, the full-scale CAV passenger service will be rolled-out to other UK cities and exported. Combining the UKs largest-scale service provider with the leading developer of autonomous technology and strong city leadership, means Apollo will be able to create a service with excellent customer experience, which connects people in transport-poor areas. The on-demand ride-sharing service will be affordable and inclusive, and will be demand-led -- with an ability to flex the area covered, dependent on customer needs. Autonomous ride-sharing offers multiple advantages. The ""sharing"" aspect helps tackle congestion by incentivising people out of private cars. Electrification means that the service will be environmentally sustainable. And by addressing an existing transport need current driven modes do not address, the project will contribute to social inclusion and economic regeneration. As well as informing potential service operators, this project will aim to inform regulators and policy makers as they deliver the Future of Mobility vision and ensure future policy benefits from the latest CAV knowledge. Through this approach we believe that we will help shape and build the market (the demand side) for the CAV sector in the UK and beyond. The Apollo project presents an unprecedented opportunity to demonstrate UK Connected and Autonomous capabilities and technologies to a global audience and will pave the way for leading UK service operators, technology providers and cities to set the global standard for next-generation mobility services."

"The potential economic and societal benefits of autonomous vehicles are vast, with the market expected to boom within the next three years. However, there is a critical limitation to the currently adopted sensing technologies which is being widely ignored within the industry. The current state-of-the-art sensors suffer significant degradation in poor weather and adverse conditions, a fact has not been addressed as most testing is carried out in research locations such as perpetually balmy California. However, the impediment to deployment will become apparent when these technologies experience the poor weather and adverse conditions typically found in other parts of the world and in off-road environments and where, arguably, autonomy is needed most. To address this challenge, Oxbotica has partnered with Navtech Radar to investigate the feasibility of developing a radar-based system for autonomous vehicle sensing and perception, which will be robust and suitable for use in all weather and all conditions. This project will bring together two innovative companies, Oxbotica and Navtech, who are leaders in their field. The output of this project will be a technology demonstrator that shows the feasibility of radar-based 3D object detection and tracking. This unique combination of leading-edge hardware and software will significantly boost the UK's competitive position in a massive global market."

"_Shift -_ a collaboration between aiPod, Oxbotica, Transport for London, Gordon Murray Design, Innogy, Bosch and Imperial College, and seeks to catalyse a radical mode _shift_ from cars to integrated mobility as a service (MaaS) using autonomous pods. aiPod proposes a city-friendly urban mobility service based on fleets of small self-driving pods, that are safe, predictive, convenient, comfortable, inexpensive, road efficient, zero emission, 100% renewable energy, public transport integrated and city friendly. _Shift_ will trial a commercial city-friendly, subscription-based, MaaS offering, based on SAE Level 4 small self-driving pods, in a London Borough, delivering a safe, zero emissions solution, focused on improving transport options and utility, reducing vehicle ownership and congestion, encouraging city-friendly transport outcomes. The project will involve 10 Connected Autonomous Vehicles and 10 Families who will have access to a low cost MaaS subscription - similar to an autonomous car club that is integrated with London public transport. The trial will explicitly share data with the city and use simulation to model the impact of predictive autonomous pods on city transport, congestion and mode-shift away from car ownership. The users experience and feedback will then inform the design of the optimal citizen and city centric pod by iconic British vehicle designer - Gordon Murray Design."

DRIVEN aims to remove fundamental barriers to real-world commercial deployment of autonomous vehicles, by addressing the need for real-time risk assessment frameworks to authorise engagement of Level 4 autonomous driving sessions and provide pro-active connected insurance. This integration of risk and dynamic authorisation into a L4 autonomous vehicle control system is transformative, underpinned by distributed data sharing, learning and connected real-time risk management to optimise overall autonomous fleet safety and operation. To realise these developments, Oxbotica, a market leader in the deployment of real-world autonomy solutions in the UK, will lead a consortium including Oxford Robotics Institute, XL Catlin, Nominet, Telefonica, Transport Research Laboratory, RACE, Oxfordshire County Council and Westbourne Communications. The ambitious trials programme culminates in 6 co-operative L4 CAVs performing mixed urban and motorway driving routes in a live-traffic environment between Oxford and London. DRIVEN demonstrates autonomy as a viable service, unlocking new service models that enable widespread autonomy for UK plc and accelerate market implementation in UK and globally.

Next-generation connected and autonomous vehicles (CAV) hold huge potential gains and benefits for the transport industry and are fundamental to realising smart mobility and cities of the future. It is predicted that the CAV market could deliver cumulative benefits to the UK of £51bn by 2030, but there is significant development to be completed before this can be realised. More accurate and efficient lidar solutions are needed for object perception and planning and will directly contribute to the substantial reductions of fatal accidents with an estimated 2500 lives saved by 2030. However these same lidar solutions can be used effectively before full autonomy to prevent accidents, both on cars and in other environments. To achieve a commercially viable solution, software must be able to run in real-time with extremely high accuracy, on low cost hardware. The Vote3Deep project intends to assess the feasibility of transferring a research solution that meets this brief from server-grade to portable systems ready for integration in CAV. The translation of this research solution into a commercially viable product will be enabled through a detailed test programme at RACE (UKAEA) Culham where it will be trialed extensively both statically and in-car in a secure environment.

Being able to precisely answer the question of "Where am I?" is critical for autonomous vehicle navigation - a function known as "localisation". There are a number of ways that a vehicle can localise: while GPS is an example of a localisation system, it is insufficiently accurate for autonomous driving systems, as well intermittently available and susceptible to jamming and interference. Lidar, a laser-based scanning technique, is commonly used to provide estimates of localisation to driverless cars, but lidar sensors are too costly for mass market vehicles. Cameras are significantly cheaper than lasers, but image-based localisation is challenging because of changes in lighting, weather, and scene structure. Taking into account the pros and cons of each of the above methods, this joint Ford-Oxbotica project utilises a suite of innovative techniques to perform camera-only localisation in spite of these environmental changes. The project will trial the software using low cost hardware to demonstrate the performance of affordable technology for mass market adoption.

Autonomous vehicles have vast economic potential for UK plc. Like any new technologies, the adoption curve can be dramatically accelerated by improving the balance between cost and benefit. However this delicate balance is often overlooked in many studies and sensor costs currently limit any reasonable business case. This proposal is about inducing a step change in the affordabililty of autonomous vehicles that will accelerate this nascent technology to deployment. The Feasibility Study will combine new, ground-breaking Intellectual Property in 3D dense vision into a road-going prototype and assess the performance of this radical low-cost alternative to laser localisation over many thousands of miles of testing. The outcome will be an analysis of the performance of a new Hybrid Dense Vision approach - leading to a reference design for an ultra-low cost sensor system for autonomous vehicles that could reduce existing sensors costs for autonomous systems by over an order of magnitude.

“I want to live in a vibrant community with easy access to work, leisure, family and entertainment and to my local towns and the countryside. I want to be independent and mobile in my old age. I want to live well and I want my great grandchildren to be able to live well too.” Technology will play a key role in delivering these aspirations. Connected autonomous vehicles will be part of the solution. Culham City is a new test site that will be used explore how smart technologies can improve how we live by enabling the safe and controlled testing of the next generation of transport solutions. In the process we will generate the evidence, to convince users, regulators, insurers and investors alike, that autonomous vehicles are a benefit to society. Culham City puts real people at the heart of CAV research and will create a world leading facility that will anchor CAV research in the UK for decades to come.

The GATEway project seeks to establish Greenwich as a leading venue for the testing and development of automated transport systems, showcasing their effectiveness for implementation in London, the UK and beyond and enhancing the global competitiveness of UK businesses. Led by the Transport Research Laboratory (TRL), we will fulfil this vision by delivering a convincing demonstration of driverless vehicles in the UK. We will create interoperable, scalable testing environments, protocols and standards guidance that will attract research and development investment in this area. Testing will include automated electric shuttle vehicles, M1 vehicles, a demonstration of teleoperated driving and a simulated 3D model of the Greenwich peninsula. The project focus is understanding engagement and interaction with automated vehicles, their local, national and international implications, effectively disseminating the results and providing routes to exploitation. The project legacy will be a driverless vehicle test environment in Greenwich, generating tangible business outcomes for consortium partners and attracting international OEMs and associated industries to the UK.

"Oxbotica (www.oxbotica.com) is a new spin-out from Oxford University’s internationally acclaimed Mobile Robotics Group (mrg.robots.ox.ac.uk), specialising in mobile autonomy, navigation and perception. We enable smart adoption of mobile autonomy, by drawing on world leading research into autonomous robotics. Our solutions allow robots, vehicles, machinery and people to precisely map, navigate and actively interact with their surroundings, delivering added functionality, capability and precision to a wide range of applications. Our 3D imaging and localisation solutions operate indoors and outdoors and are seamlessly scalable. Our core technology is suitable for use in numerous applications including hand held survey devices and autonomous vehicles Our primary business model is to commercialise University IP and creation of new application-specific IP to support implementation. In this proposal we are seeking Innovate UK support to help us develop an IP Management Strategy that will help us maximise return on our technology investments, and enable our University inventors to be rewarded for their creativity. "

Oxbotica is a new spin-out from Oxford University’s internationally acclaimed Mobile Robotics Group (mrg.robots.ox.ac.uk), specialising in mobile autonomy, navigation and perception. We enable smart adoption of mobile autonomy, by drawing on world leading research into autonomous robotics. Our solutions allow robots, vehicles, machinery and people to precisely map, navigate and actively interact with their surroundings, delivering added functionality, capability and precision to a wide range of applications. Our 3D imaging and localisation solutions operate indoors and outdoors and are seamlessly scalable. Our core technology is suitable for use in numerous applications including hand held survey devices and autonomous vehicles In this project we will develop a concept NAvigation Base Unit into a production-feasible prototype. NABU is a disruptive technology and introduces a low cost, infrastructure free (without GPS), 3D imaging device which uses patented laser and vision integration to rapidly scan an indoor or outdoor environment and translate this into information that can be deployed in survey, simulation or mobile autonomy applications - see Appendix A for details of NABU The know-how in NABU is a cornerstone of Oxford’s RobotCar programme (www.robotcar.org.uk), and elements of the IP have also been licensed to ESA’s ExoMars programme . The device is based on over 100 person years of Oxford University research into combining machine vision and laser scanning to form 3D scene models. This project will ruggedize a proof of concept device, add a user interface and develop significant postprocessing capabilities that can be tailored to fit applications across multiple domains. Proof of concept and early user testing has already been undertaken with support by EPSRC Impact Acceleration funding. End user feedback has been overwhelmingly positive. This funding will enable the development of a fully robust prototype, suitable for early commercialisation.