QinetiQ Selects Aonix PERC for Taranis UAV

Aonix, a provider of complete solutions for safety- and mission-critical applications, announced the selection of the PERC Ultra virtual machine for Taranis, a $166.6M UK technology demonstrator program for the next-generation of unmanned aerial vehicle (UAV) for the UK Ministry of Defence (MoD).
BAE Systems is the industry lead and prime contractor for the program and QinetiQ is providing the Reasoning Layer of the Autonomy Mission System making the high level plans which control the flight path and sensor usage to achieve a mission. Taranis will be the largest UAV yet built in the UK and, as part of the UK MoD’s Strategic Unmanned Air Vehicle (Experiment) SUAV(E) program, will explore and demonstrate how emerging technologies and systems can deliver battle-winning capabilities for the UK armed forces.
The Taranis Reasoning Layer needs to run complex decision-making and optimization algorithms on an embedded processor. QinetiQ chose PERC because PERC enables existing Java code and libraries to be used in an embedded environment while providing the necessary support for soft real-time operation. Following extensive evaluation, QinetiQ found PERC Ultra as the most practical solution to meet the project requirements on its chosen embedded processor and real-time operating system. QinetiQ needed access to PERC’s efficient AOT compilation and static loading capabilities as well as the ability to connect to existing libraries of C++ routines.
Taranis represents a significant step forward in UAV capability, with its focus being targeting and attack rather than the surveillance and reconnaissance roles for which previous UAV programs had been designed. Accomplishing these goals requires QinetiQ to do much more with the system, to ensure it is capable of high-level decision making to support deep operations. Named after the Celtic God of Thunder, Taranis will be an unmanned fast jet demonstrator the size of a Hawk trainer.
“We chose to develop the Taranis Reasoning Layer with Java due to the broad range of capabilities of that platform, but we needed PERC Ultra to support practical deployment in a real-time, embedded environment,” said Peter Baynham, managing director of QinetiQ’s Command & Intelligence Systems business. “Support for our chosen architecture and ability to integrate with existing libraries were also key factors.”
“Taranis is the latest win for PERC Ultra in the growing autonomous vehicle market, and it’s particularly exciting to be working with QinetiQ because the mission requirements of Taranis represents proof of the power and productivity that Java technology can bring to complex, high-intelligence embedded and real-time systems,” said Adrian Larkham, Aonix UK General Manager.
PERC Ultra has many competitive advantages that have made it the virtual machine of choice among mission-critical Java developers. PERC offers great flexibility to get the job done, with more execution modes, higher throughput, and better predictability than the nearest competitors. The PERC Ultra real-time garbage collection system is mature and proven through over a decade of use in critical applications worldwide, and the current PERC Ultra release supports versions of the Java JDK up to three versions more recent than competitive offerings.
With hundreds of thousands of deployments, PERC is the most widely used virtual machine technology for mission-critical applications. The PERC Ultra virtual machine offers rich JSE™-based capabilities, and predictable garbage collection, while PERC Pico provides the low-level access and small latencies that are often required for close-to-the-silicon applications. PERC technologies are more predictable and reliable than other Java solutions, while offering much higher productivity and lower lifetime costs than C/C++ applications development.