VIVAERO

Joby Aviation partners with NVIDIA to accelerate autonomous flight technology

Joby Aviation announced yesterday, October 28th, a collaboration with NVIDIA, marked by Joby's selection as the sole launch partner in the aviation sector for the new NVIDIA IGX Thor platform.

Powered by the NVIDIA Blackwell architecture, the industrial platform is designed to drive the next generation of AI physics applications. This exclusive collaboration will advance the development of Joby's autonomous flight technology, called Superpilot, on both military and civilian platforms.

Gregor Veble Mikić, Flight Research Leader at Joby, said: “The autonomous systems under development at Joby are poised to complement human intelligence, providing speed, precision, and endurance beyond what a person is capable of alone. To achieve this, an aircraft needs a powerful onboard computer capable of interpreting extraordinary amounts of information to make real-time decisions. By combining NVIDIA’s computing power with our world-class aircraft design, certification, and rigorous flight testing capabilities, we are enabling a new era of safety-prioritized autonomy in aviation.”

Joby is developing Superpilot to interact with the world through a continuum of autonomous functions. NVIDIA’s support for recognized functional safety standards on the IGX Thor platform allows Joby to move toward autonomy certification for short-term defense applications and long-term civilian applications, as the U.S. Federal Aviation Administration (FAA) enhances national airspace capabilities.

Integrating this level of advanced computing can transform operational safety and mission capability, enabling real-time onboard functionalities such as:

– Autonomous Mission Management: Allows the aircraft to determine, request, and follow optimal flight paths, adapt to changing weather conditions, air traffic control instructions, or unexpected events, with intuitive human-machine interaction to ensure mission success.

– Radar Processing and Perception: Onboard computing processes high-speed data from radar, LiDAR, and vision sensors to achieve rich environmental awareness, precise object perception and location, navigating airspace safely in all conditions.

– Sensor Fusion: High-performance integrated processing combines data from a wide range of sensors to provide a reliable and accurate estimate of aircraft status and situational awareness in the most challenging environments.

Integration also lays the groundwork for developing features that enhance operational awareness, reliability, and performance:

– Predictive System Health Monitoring: The aircraft will be able to refine models of its own functionality and reliability, predicting when system components may need attention and alerting crew members before the problem occurs.

– “Digital Twin” Modeling: With powerful and reliable computing capabilities, an aircraft can carry a “digital twin” model of itself and the world, gathering data from each flight to refine its fidelity. This information can then be integrated into mission control systems to optimize performance and efficiency.

Veble Mikić added: “Autonomous cars have demonstrated the ability to interpret large volumes of data to make split-second decisions. For an aircraft, the computing power required for autonomy is equally high, but it also needs to meet even more stringent design standards to achieve certification for operation in controlled airspace. In aviation, every calculation must be perfect, and every decision, infallible.”

Information from Joby Aviation