UAVenture and Daedalean have published a teaser video announcing a new guidance system for professional UAVs. The system is called Magpie and provides unrivaled AI-powered functions – vision based identification of emergency landing sites during flight, as well as visual navigation that helps sustain GPS outages – in a less than 500g package, and completely integrated with the AirRails flight controller: no additional complex setup & coding required. No pre-marking of landing spots is required, Magpie is able to operate without pre-surveying of the area and recognise dynamic obstacles on the ground. The product will be available soon for the users of AirRails, UAVenture’s flight control system for professional drones.
Watch to learn the features of the AI-autopilot for the autonomous flight – computer vision-based flight control – already demonstrated: situation awareness and perception, detecting flying obstacles, GPS-independent simultaneous localisation and mapping, recognizing obstacles on the ground and safe landing advisory. On the roadmap: wire detection and more.
This additional round brings the total amount of the company funding to CHF 11.8 million (nearly $12 mln). The funding round is led by Carthona Capital. Other investing VCs are Redalpine and Amino Capital. Along with them, three former engineering managers of Daedalean’s founder and CEO, Dr Luuk van Dijk, back in his times at Google, are investing as business angels. Dr Harald Nieder, Partner at Redalpine, is joining Daedalean’s board as an observer.
On 8 May 2019 Daedalean and EASA concluded a fruitful 3 day workshop to kick off their Innovation Partnership Contract (IPC).
The project titled “Concepts of Design Assurance for Neural Networks” aims to examine the challenges posed by the application of Neural Networks in aviation,
in the broader context of allowing Machine Learning and more general Artificial Intelligence on board aircraft.
Experts from EASA and Daedalean are bundling their expertise to create concepts and safety standards for the application of
this branch of Artificial Intelligence in safety critical avionics. The project is expected to run through January 2020 when a final report will be presented.
Daedalean and Volocopter conducted joint flight tests on Wednesday 27th March 2019 at the airfield in Bruchsal (D) in order to test Daedalean’s Visual situational awareness system
(“Raven”) on board an experimental Volocopter.
The tests demonstrated crucial environmental perception capabilities for visual navigation and collision detection in landing and en-route scenarios, using 3 high definition cameras
mounted outside the fuselage of the aircraft, the data from which are fed to the on-board computer vision and artificial intelligence (AI) algorithms.
A comprehensive GPGPU compute platform addressing all aspects of GPGPU computing for safety critical aerospace applications using the family of certifiable embedded AMD GPU devices. Xenon includes the standalone OpenCL 1.1 runtime software stack as well as the complete compiler toolchain supporting both OpenCL and AMD assembler languages. The OpenCL runtime is OS-agnostic, has no external dependencies and can run on barebone hardware. Supported AMD GPU devices currently include Radeon E8860, E9171, and E9260. The cross-platform software development kit for Linux is available.
CES/Mercury Mission Systems Inc invited Daedalean AI to demonstrate their Computer Vision and AI software running on the MSSI Rock2 platform at the 2018 Farnborough Airshow, as reported by Intelligent Aerospace magazine.
This video demonstrates some of the current product features being developed by Daedalean as well as gives a glimpse into the roadmap of the product, paving a way to the future autopilot with the highest level of autonomy. The video is a mix of real demos and computer graphics.