The Hivemind system has already flown aircraft autonomously without GPS, communications, or a human pilot in the cockpit. This could potentially be a huge bonus when utilized by warfighters during unmanned missions.

The announcement was made at the recent Air Force Association Warfare Symposium, where both companies expressed optimism about their collaborative efforts moving forward.

The partnership between Shield AI and Boeing’s Phantom Works division will leverage their respective expertise in artificial intelligence and autonomous capabilities.

Boeing Aircraft And Shield AI’s Autonomous Pilots

“AI pilots are the most strategic deterrent technology since the introduction of stealth aircraft and have proven successful in flying air-combat scenarios,” said Ryan Tseng, president and co-founder of Shield AI and a former Navy SEAL.

“Integrating Boeing aircraft with our AI pilot would redefine what large aircraft, crewed or uncrewed, could do. As the world leader in aerospace technology, Boeing has been exceptionally easy to engage with, so we are excited to expand our scope of work to co-develop, productize and bring to market the world’s best AI pilot for large aircraft,” Tseng added.

As Shield AI looks forward to working with Boeing Phantom Works to bring advanced autonomy into existing programs and develop new capabilities for the company, Boeing is equally optimistic about the partnership.

“Boeing continues to leverage talent from across the enterprise to make great strides in autonomous capabilities and programs in recent years,” said Steve Nordlund, vice president, and general manager for Boeing’s Air Dominance organization. 

“Collaborating with Shield AI, the leader in AI pilots, will accelerate our ability to deliver these capabilities to the warfighter,” Nordlund said.

Experts from Shield AI said that the company would provide its Hivemind AI pilot system, designed to enable swarms of drones or aircraft to operate autonomously without GPS, communications, or a human pilot in the cockpit. 

The Hivemind system uses machine learning algorithms to identify features on the ground that are useful for navigation, such as roads, buildings, trees, rivers, and other landmarks. 

This helps it create an internal map from sensor data, which it uses to navigate unfamiliar terrain without external guidance.

Introducing Hivemind:
Shield AI’s Software Ecosystem Enabling “Autonomy on the Edge”

Hivemind is leading in the aerospace defense industry as the first and only autonomous AI pilot deployed since 2018.

Like a human pilot, Hivemind reads and reacts on the battlefield and does not rely on GPS, waypoints, or communications when making decisions. It enables intelligent teams to perform missions ranging from room clearance with Novas to air defense system entry with V-BATs to dogfighting F-16s.

“When people ask me why we need AI and autonomy for aircraft, my answer is simple: to tackle problems humans cannot,” shares Alex Burtness, Hivemind Product Director. “At Shield AI, we build edge software that delivers intelligent autonomy and human-machine teaming capabilities for the most challenging missions in data-denied, GPS-denied environments.”

“We have constructed a software ecosystem called Hivemind that not only encompasses the edge-level autonomy software but also the tools around it to enable rapid development and fielding. Hivemind bolsters confidence in the autonomy capabilities by leveraging high-fidelity simulation and historic flight data to test algorithmic performance across complex analyzers.”

Burtness said that Shield AI builds autonomous systems to “achieve extremely high levels of performance in consistency, reliability, and robustness, “so the company created Hivemind to meet these requirements.

He further enumerated the three core components of Hivemind:

• Software modules running on the edge, performing core functions of cognition, action and perception
• Human-machine interface: Shield AI’s platforms work on their own without human input yet require human touch for intent and re-tasking systems
• Configuration and testing tools for the launch and analysis of the platforms “at various levels of abstraction.’

 The complexity of running software at the edge stems from the time-critical nature of the decisions and the platforms’ size, weight, power, and cost (SWaP-C) constraints, says Burtness. 

Shield AI uses well-tested and hardened software modules with artificial intelligence in key areas to create a resilient autonomous system.

Beginning with the perception stack, the company employs cutting-edge optimization frameworks to handle a plethora of sensors to estimate the robot’s state and surroundings in various challenging environmental conditions, such as GPS denial.

To determine the following action, the cognition stack employs the world model — comprised of the perception stack’s state estimates and map representations — and planning components that explain the intended objectives and safety. Once decided, the agent modifies its actions to achieve the goal.

“All this happens hundreds of times per second, all without constant human control,” explains Burtness.

The Goal Of Advanced Aircraft Autonomy

Burtness further underscored its goal of advanced aircraft autonomy, with its aerospace defense projects all leading to advancing technology solutions for warfighters.

“Our work with the Department of Defense allows us access to some of the world’s most skilled pilots. We wish to leverage this experience in developing our aircraft autonomy behaviors to develop interfaces for humans to interact with our AI. They can fly against it and fly with it as a teammate, observing how it reacts to various operational environments.”

“This is useful in two ways. First, it gives the human operator trust in the AI agent because they can see it perform in a variety of situations and react the same in the real world. Second, we can learn from every single human-agent interaction and use the information to feed our algorithms to make them better.”

“This work with human pilots also reminds us of the importance of intuitive operator interfaces during missions. The most advanced autonomy platforms will not be useful if human commanders are unable to easily relay intent and goals. While reducing cognitive load with minimalistic design, we utilize expert knowledge from our close customer relationships to understand the key insights to show at what time.” 

“Looking longer term, the powerful part of Hivemind is not just the autonomy itself, but also the way each system integrates with other autonomous systems, and the test and validation capabilities it offers.”

“Hivemind lets us take systems from simulation into the real world, where they must deal with all the accompanying complexities. The total solution space we’re working with involves a massive number of parameters and it would be impossible for a human engineer to do this without an ecosystem like Hivemind.”

Win-Win Solutions For  Boeing- Shield AI Partnership

The partnership between Shield AI and Boeing’s Phantom Works division will leverage their respective expertise in AI and autonomous capabilities to create solutions for warfighters.

Shield AI has successfully demonstrated its ability to fly aircraft using its Hivemind system. At the same time, Boeing provides decades of experience in designing advanced unmanned aerial systems (UAS) for military use.

By combining these two forces, they hope to develop cutting-edge autonomous capabilities much more quickly than either company could do alone.

In addition to developing new capabilities, the companies plan to explore ways to reduce costs and improve safety through automation technologies. Automating specific tasks can reduce labor costs and increase security by reducing human error or fatigue during long missions.

The partnership between Shield AI and Boeing offers numerous advantages to both companies. For Boeing, it provides an opportunity to leverage Shield AI’s advanced artificial intelligence technologies as part of its defense contracts.

For Shield AI, it provides access to Boeing’s extensive resources, including its expertise in engineering, manufacturing, test & evaluation, program management, logistics support services, training development & delivery capabilities, as well as its global sales channels for potential customers worldwide looking for cutting-edge solutions like those offered by Shield AI.

The partnership also opens up opportunities for additional joint investments into further research & development initiatives related to autonomous capabilities & artificial intelligence technologies being developed by both companies.