Joby Aviation to test NVIDIA’s IGX Thor platform for AI-powered autonomous flight
October 29, 2025
Joby Aviation has been named the aviation launch partner for NVIDIA’s new IGX Thor platform, a powerful on-board computing system designed to enable the next era of safety-critical autonomous flight.
Announced on 28 October, the collaboration will see Joby integrate IGX Thor into its development of Superpilot™, the company’s advanced autonomy system for both civil and defence applications.
“The autonomous systems under development at Joby are poised to complement human intelligence by providing speed, precision, and stamina beyond what a person alone is capable of,” said Gregor Veble Mikić, Flight Research Lead at Joby. “To achieve this, an aircraft needs a powerful onboard computer that can interpret extraordinary amounts of information to make decisions in real-time.”
The agreement makes Joby the first aviation company to test and validate NVIDIA’s latest industrial-grade compute architecture, tailored for real-time, mission-critical environments.
What is NVIDIA’s IGX Thor platform?
IGX Thor is the latest member of NVIDIA’s IGX family, built on the company’s new Blackwell architecture. It is designed for applications that demand extreme reliability and real-time processing, such as robotics, manufacturing, and autonomous transport.
Integrating this level of advanced onboard computing can transform operational safety and mission capability, enabling real-time capabilities such as:
- Autonomous mission management – enables the aircraft to determine, request and follow optimal flight paths, adapt to changing conditions, and coordinate with human pilots or operators to ensure mission success.
- Radar and perception processing – processes high-rate data from radar, LiDAR and vision sensors to build detailed environmental awareness and precise object localisation.
- Sensor fusion – combines data from multiple sensors to deliver reliable aircraft state estimation and situational awareness, even in complex environments.
It also establishes a foundation for new features that enhance reliability and performance:
- Digital-twin modelling – creates a real-time virtual model of the aircraft and its environment that improves with every flight and feeds back into mission control for continual optimisation.
- Predictive system health monitoring – refines models of system performance to anticipate maintenance needs before failures occur.
NVIDIA describes IGX Thor as a “physically aware” AI platform — one capable of interpreting and reacting to its environment with the precision required for autonomous flight.
“Autonomous cars have showcased the ability to interpret large volumes of data to make split-second decisions,” added Veble Mikić. “For an aircraft, the compute power needed for autonomy is similarly high, but also needs to meet even higher levels of design rigor to achieve certification for operation in controlled airspace. In aviation, every calculation must be perfect, and every decision infallible.”
Why NVIDIA’s IGX Thor matters for Joby’s eVTOL and autonomy roadmap
For Joby, the partnership adds crucial computing depth to its long-term ambition of fielding fully autonomous electric vertical take-off and landing (eVTOL) aircraft.
The company’s Superpilot™ technology is being designed to handle high-volume sensor data, perform complex perception tasks, and make real-time flight decisions that comply with aviation safety standards. The US Air Force recently tested Superpilot on board Joby’s autonomous Cessna Caravan around the Hawaiian Islands.
“An aircraft needs a powerful onboard computer that can interpret extraordinary amounts of information to make decisions in real time,” said Gregor Veble Mikić, Joby’s Flight Research Lead. “The IGX Thor platform will provide the safety-capable performance necessary for us to reach that goal.”
While Joby is currently focused on certifying its piloted eVTOL for commercial service, autonomous flight remains a core part of its future roadmap. The partnership with NVIDIA represents a foundational step in building the computing framework that such autonomy will eventually require.
Next steps for Joby and NVIDIA in autonomous flight development
NVIDIA emphasises that IGX Thor is built for certifiable autonomy; hardware that can underpin systems subject to rigorous regulatory approval. However, Joby has not yet indicated when the platform might transition from development testing to use in a certified aircraft.
The collaboration also highlights a broader trend: the convergence of AI and aviation. As aircraft become more data-driven and autonomous functions expand, high-integrity computing platforms like IGX Thor will be central to ensuring that decisions made by AI systems meet the safety standards demanded by regulators.
