focus

Unlocking the potential of AI

Discover how we are collaborating with partners to develop AI-enabled technologies that enhance safety, reduce pilot workload and introduce new capabilities for operators.

A search and rescue crew scours remote mountainous terrain for a walker reported missing in sub-zero temperatures. Thanks to an AI-driven object detection system, they pinpoint the casualty in a matter of minutes.

Meanwhile, thousands of miles away, a crew operating in congested urban airspace receives an automated alert warning of a conflict with drone traffic. The alert allows the pilot to take immediate evasive action and safeguard the aircraft.

These two very different scenarios (described in the case studies below) are practical examples of how we are collaborating on potential applications in AI to real-world operations.

Focus on real-world challenges

In the past three years, across Leonardo Helicopters we have accelerated our efforts in the field of AI.

We recognise that AI can help to address some of the most critical challenges faced by our customers: How to enhance safety. How to reduce pilot workload. Finding smarter ways to minimise the time and cost of maintenance.

The pace of progress with AI is exciting. And already what is possible today would have been unimaginable only a few years ago,” says Emanuele Bezzecchi, Leonardo Helicopters’ AI Roadmap Manager. “However, it’s also clear that we are at the start of the journey, not the end.

"We are focused on where AI can bring the most value. There are two main areas. Firstly, integrating AI-based technologies within our product line and secondly, using AI to enhance our processes and the services we will offer in future in areas such as support and training.

"Our Diagnostic Service Tower is a good example on the services side. It’s the place where we collect all the HUMS data coming from our customers’ operations. Analysing these data using AI techniques is an important step in enabling predictive maintenance where we can be much more targeted in our maintenance activities to save operators time and money.”

How we’re collaborating on AI

We recognise the importance of partnerships in maximising the potential of AI. So, we are collaborating with operators and external partners to trial emerging AI capabilities.

Soccorso Alpino (Valle d’Aosta): AI in search and rescue missions

When helicopter search and rescue crews attempt to locate a casualty in inhospitable terrain, every minute counts. Crews could soon have a powerful ‘extra pair of eyes’ to help them – with AI at the heart of the technology.

We have been collaborating with the Italian mountain rescue service Soccorso Alpino (Valle d’Aosta) and our colleagues in the Artificial Intelligence Research Centre (AIRC) of Leonardo’s Cyber and Security business.

The result is an AI-driven object detection and tracking solution called G4SAR. It uses a 4K camera augmented by AI software. While initial testing has taken place using drones, the system is also capable of being integrated into the belly of a helicopter or connected to Uncrewed Air Systems (UAS).

G4SAR allows an operator to view a live video stream of the search activity. If the software detects a person on the ground, it captures an image, which can then be enhanced for the crew to assess.

The software can also detect a human being even they are only partially visible – for example, by recognising a limb or part of their torso.

One challenge was the lack of a detailed dataset for mountainous terrain – tree cover, rock formations, boulders, shrubs and other objects needed for the AI model.

Soccorso Alpino (Valle d’Aosta) found a novel way to address this. They recruited volunteers to act as mock casualties, hiding themselves away in the mountains of the Italian Alps to mimic real-life rescue scenarios. Aerial images could then train the AI system to distinguish human casualties on the ground.

In October 2024 we took the next development step by completing successful flight trials in southern Italy with G4SAR integrated into an AW189 helicopter. The platform is the ideal testbed because of its pedigree in SAR missions. The integration allows us to propose G4SAR on all helicopters equipped with the same cabin computer as the AW189 testbed. In future, customers will then be able to use existing AI models, develop their own models, or provide us with data to train an AI model specific to their use case.

Francesco Calabrò, Head of the AIRC

“This was an opportunity to apply our expertise in developing security solutions for the urban environment to an entirely different challenge – locating casualties in the mountains of the Alps.

"In these scenarios, finding people quickly is incredibly important, but narrowing the search area can often be difficult. Even with the use of drones, it might still require a human to spend hours looking at a screen to pinpoint the location of a casualty.

"We built an AI algorithm that reduces search time dramatically. It is able to process a search area that might usually take two teams of people half a day to analyse in just 15 minutes. The aim is to get the rescue team to the right place in a fraction of the time by using the power of AI in real-time in a search and rescue scenario.

"We also needed make everything smaller because space and weight are precious commodities on board a helicopter. The G4SAR solution is capable of operating on a laptop and it’s also flexible. We can train the algorithm to detect humans, or other objects, so there are many other potential security and safety applications.”

Daedalean: using AI to improve situational awareness

AI holds huge potential to improve pilots’ situational awareness and enhance flight safety. We have partnered with Daedalean, which is pioneering safety-critical and certifiable AI systems, to flight test its AI-enabled avionics on two of our platforms.

Daedalean – A Swiss company that also has operations in the U.S. – has developed a visual awareness system that uses AI in the form of machine learning. The system is designed to give pilots better "situational intelligence" by understanding the environment around them and, eventually, the ability to anticipate and react to potential threats.

We worked together on a year-long project under a Eureka Eurostars grant, equipping both our SW-4 and SW-4 Solo Optionally Piloted Helicopter/Rotary Uncrewed Air System (OPH/RUAS) with Daedalean’s technology.

The visual awareness system includes aircraft-mounted cameras, computer and interface display. It enables the crew to identify the presence of aerial objects including noncooperative traffic such as drones or flocks of birds that could pose a danger to the aircraft. It also provides the ability to determine the location of the aircraft in GPS-denied environments.

The successful flight trials mark another important milestone in maturing the integration of AI solutions into our platforms. The collaboration with Daedalean continues, with the aim of testing new capabilities including remote landing site finding and wire detection.

Bas Gouverneur, Daedalean CEO

“Working with Leonardo offered us the opportunity to demonstrate how AI technology immediately and significantly improves safety and efficiency across a range of scenarios. It was also a chance to find out from seasoned pilots how this powerful technology can be deployed.

"We know that in some countries, up to 80% of air traffic doesn't use ADS-B, which means collision avoidance is left entirely to looking out the window. But recognizing an imminent collision is among the most difficult things for a human eye to do because the threatening aircraft seems like just a dot in the sky, displaying very little change in appearance. We’ve developed AI-enhanced systems that can perceive minute variations and communicate to the pilot distance to the threatening aircraft and time to collision.

"We also recognize that one of the most persistent threats pilots face worldwide today is the inherent vulnerability of GPS. By tracking hundreds of thousands of features across the landscape, an AI-enhanced system serves as a ready standby back up in case GPS is jammed, or worse, spoofed, since a pilot would not even know she was off course.

  "We were delighted to discover with Leonardo’s test pilots that the function would prove useful in even more use cases than we had considered. They highlighted our systems’ effectiveness during high hovers, where visibility beneath the helicopter is minimal, and for landing in tight spaces like on small ships. Additionally, they proposed that the VPS could serve as the main navigational tool for lightweight drones delivering shipments in urban areas."

 

Safety and regulatory challenges

In May 2023 EASA published its Artificial Intelligence Roadmap 2.0. It sets out the challenges and opportunities ahead for the aviation sector and explore key issues around AI deployment such as safety, security and public perception.

Guillaume Soudain, Programme Manager - Artificial Intelligence EASA

“EASA has been working with stakeholders since 2020 to develop an 'AI trustworthiness framework' aligned with the EU AI Act (Regulation (EU)2024/1689). The Agency has published two concept papers, which have paved the way for the approval and deployment of safety-related AI systems in aviation.

"In 2024, EASA entered the AI Roadmap consolidation phase, focusing on two priorities: rulemaking and further exploration.

"The rulemaking priority (under task RMT.0742) involves adopting a risk-based approach for Level 1 and Level 2 AI applications, with a focus on safety, ethics, and human factors. The agency plans to translate its AI Concept Paper into rules and Acceptable Means of Compliance (AMC) and Guidance Material (GM), with a proportionate approach to the criticality of AI applications and the specificities of each aviation domain.

"The further exploration priority will involve broadening the scope to include topics such as reinforcement learning and hybrid AI, as well as investigating the challenges of human oversight in advanced automation (Level 3 AI). EASA aims to ensure safe and responsible integration of AI into the aviation industry, with the next concept paper expected by the end of 2025.

"While progressing on this further exploration and rulemaking activities, certification projects are already on-going involving Level 1 AI applications, which are managed thanks to a Special Condition leveraging the objectives from the EASA AI Concept Paper.”

Potential for AI in training

We continue to invest in the latest training technologies that offer immersive blended training for operators. Our VXR (Virtual and Extended Reality) Enhanced Training Device and the MITHOS (Modular Interactive Trainer for Helicopter Operators) offer a highly realistic training experience.

AI could add an extra dimension to our training services in future. “For example, we are developing a chatbot linked to the AW139 flight manual,” says Bezzecchi. “After a first proof of concept developed using High Performance Computing, this year we aims to enhance its performance and make it available through a mobile app to our customers.

"We’re also developing a data-driven training programme that will create an individual training history for each pilot. AI and Big Data tools could enable us to combine simulator and live flying data to create a personalised record that can go with a pilot throughout their career."

Computing power: The davinci-1

The davinci-1 is one of the most powerful supercomputers in the aerospace, defence and security sector. Developed by Leonardo as an integrated supercomputing and cloud computing platform, it adds more ‘firepower’ to our AI activities.

AI needs computational power to deliver value,” says Bezzecchi. “We are able to tap into davinci-1 and also the wider work of the Leonardo Labs, the company’s network of research and development laboratories, which are dedicated to developing breakthrough technologies. One of the labs is specifically focused on AI, giving us valuable know-how and expertise to supplement our own work.”

Visit the AW Vertical View homepage