This series of articles will discuss the benefits of AI in the drive for autonomy and BVLOS operations, initially in drones, and then in the broader commercial aviation environment. It will explore some of the benefits that can be gained, the challenges that are faced, and propose some solutions to solve the most persistent and challenging problems. It will further explore the role of drones in a broader ecosystem, and how essential it is for machines and people to work as coherent teams, identifying the challenges and opportunities that this presents.
BVLOS for Drones
Much has been written about the opportunities surrounding BVLOS (Beyond Visual Line of Sight) drone operations – covering activities as diverse as disaster recovery, medical deliveries and delivering parcels to your work or home. There is no doubt that the momentum towards this is unstoppable, and it’s definitely a question of when rather than if.
Today, unmanned aviation seems to involve an awful lot of people on the ground – the challenge to scale BVLOS operations is to reduce and ultimately remove the need for this by unlocking autonomy throughout the network. Mass-autonomy at the scale anticipated will require the entire system to work in sync, with human decisions largely removed from the loop.
It is clear is that there are pockets of amazing technology being developed, both by SMEs and by the larger traditional aerospace businesses. There is no single solution yet available also meets the needs for tomorrow. Instead, collaboration is the way forward, for example, Archangel have some incredible technology in advanced development, but without integrating that technology with complimentary innovation from elsewhere in the industry, there will be no compelling overall solution.
Navigation for BVLOS Unmanned Systems
Within the current aviation environment there is a very clear and mature regulatory framework surrounding operations and the role of technology within it. For example, large, trans-oceanic flights must have dual communications system to provide suitable redundancy should there be a failure of the hardware or even the network itself.
When considering the autonomous and BVLOS environment, it is clear that there will need to be a similar approach to system assurance. Much has been published about the need for resilient, assured and often low-latency communications on unmanned aircraft, indeed, a number of high-profile projects are underway to overcome this clear vulnerability. This is critical, but there has yet to be a similarly appropriate focus on the navigation elements.
GPS is ubiquitous and relied on every day for a multitude of uses, from guiding us in the air to geo-tagging our photographs. But what happens when that system is compromised?
Many of us rely on GPS to guide us when driving, and when that system fails in some way it immediately causes distraction to the driver. As a “squidgy computer”, the human driver can usually manage to maintain course and manage through other means, for example reading signposts. Now, imagine that driver was autonomous, how would an autonomous driver manage without accurate location information?
Is There a Backup to GPS for Unmanned Flying Platforms?
Now imagine that same GPS system was the sole input for the autonomous navigation system on a drone, and that drone was involved in a critical mission – delivering pathology samples to a remote test lab, or surveying critical infrastructure… How would the drone know if it was off course? How would it know that it was in the right location, or that the location data was not being spoofed?
Spoofing is a real problem today. Research has shown thousands of verified incidents either through malicious or accidental intent. There are reports of boats suddenly reporting locations up to two miles from their actual location.
The mandate is clear here – GPS needs a co-pilot; a backup to help in case it is spoofed, or in case of accidental or deliberate jamming. This is a problem that Archangel have been working hard to overcome, and Xnaut GENIE (GNSS Excluded Navigation Intelligent Enhancement) is the outcome.
Using a combination of visual, inertial and AI navigation techniques, it is now possible to navigate reliably and autonomously without GPS. When thinking about the three critical elements in commercial aviation; Communications, Navigation and Surveillance - the latter two become even more challenging without a pilot on board.
How AI Can Help
The fundamental challenge with machine visual navigation is that the environments in which the platforms will fly are incredibly dynamic – day/night, clear skies/cloud, shadows changing shape throughout the day, rain, reflections, etc. The reality is that any single alternative navigation method will come with inherent shortcomings. This is why Xnaut GENIE does not rely on a single method, but rather having a toolkit of options available. Think in terms of a screwdriver set – a collection of tools for the job to cover all bases.
This is where the AI becomes critical – Xnaut GENIE has been designed to select and combine the optimum set of methods to ensure reliability. This enables it to compare the platform’s location with the GPS location and warn of spoofing events, or take over the navigation inputs entirely in the case of a GPS failure. It sounds simple, doesn’t it? It also sounds like an obvious need when you think about it. Aviation doesn’t work well with single points of failure – it adds too much risk.
Trust
For BVLOS operations to become the norm rather than a pocket of edge cases, there must be appropriate trust in the systems, backed up by thorough testing and proven-in-use history. Combining Xnaut GENIE with a traditional GPS system onboard a BVLOS drone will help build that trust, and prove that part of the safety case required to unlock the huge potential of drones.
Summary
The path to routine BVLOS operation is full of challenges – one of which is outlined above, along with a potential solution. This is one piece of the jigsaw, across the world are similar solutions to other elements of the challenge. Unless the drone industry can share knowledge, collaborate and identify complimentary solutions, the future will continue to be just that, and the present will not evolve.
We would welcome the opportunity to discuss how Xnaut GENIE can help make the future the present, and equally to speak to companies that have complimentary solutions with who we can collaborate. In the next article we will talk about the benefits of autonomy for the environment, and how it can help with the drive towards Net Zero.
To start a conversation simply get in touch.