We are more than happy to continue the tradition of sharing with you the highlights of the previous year. Have a look at what we achieved in 2020 – it was another amazing and exciting year!
Let’s kick off our top 10:
1. The Intuition-1 mission hit some important milestones! We tested the mission-tailored data processing computer – Leopard – in near-real conditions (climate chamber, thermal vacuum chamber, vibration tests, functional tests). Based on these results, we have started working on the next generation of this computer and we are shortly starting assembly and alignment of the optical instrument. In addition, we have developed most of the software, including neural networks for hyperspectral image analysis. Thanks for all the amazing work in 2020 – Intuition-1 team! This year will be the year we release our first fully functional products!
2. We reached perfect product synergy by developing the Smart Mission Ecosystem (SME). SME is a set of hardware, software and AI-powered algorithms designed to bring autonomy into demanding space missions. It supports the complete lifecycle of advanced missions from analysis and design – through faster satellite integration thanks to the built-in algorithms, software and hardware-in-the-loop tests – to the increased reliability of operations in space and the on-board data processing supported by AI. We designed SME with a holistic approach to enable on-board data processing on the payload and satellite level, as well as to ensure safer and more fault-tolerant missions as it brings together the hardware, software and AI-powered algorithms to complete even the most demanding missions. Our Intuition-1 mission will be equipped with three components of SME: Leopard DPU enabling on-board data processing, a modular software programme Oryx and a group of on-board AI-powered algorithms –The Herd.
3. Little Oryx. We did it! The KP Labs Programming Team developed a new version of the software controlling the PW-Sat2 satellite – the fourth Polish object in space. A modular flight software – Oryx – was uploaded in the pre-existing PW Sat2 mission. Be sure to check out our case study.
4. We gained as many as 7 projects in 2020:
- Antelope. This is an intelligent on-board computer for nano- and microsatellites with increased reliability and computational power, enabling a satellite’s self-diagnosis in orbit using machine learning algorithms.
- Beetles. We will develop the methods and tools for making deep learning-powered techniques easier to adopt on board satellites in an extreme execution environment. Making deep networks more robust against noise and generally more precise in terms of unseen data of varying quality has never been more important. No matter what kind of application or Earth observation use case you are about to target.
- DeepSent. Thanks to the progress which has been made in image processing algorithms, zooming images on-board a satellite to discover more details is no longer science fiction. Super-resolution (SR) reconstruction will change the existing image processing techniques to support decision-making in areas such as land mapping, spatial planning, and rapid responses to emergencies. The European Space Agency (ESA) has awarded KP Labs a project aimed at improving the spatial resolution of Sentinel satellite images.
- Chameleon. The aim of this project is to develop a system that will allow us to not only automate the process of selecting sensors for a vehicle in the context of detecting objects in its close vicinity but also to understand the robustness of such sensory configurations. Furthermore, we will propose machine learning-powered techniques to fuse multi-modal sensory data. Chameleon is our step towards the autonomy of vehicles – ranging from cars through to satellites.
- RedKyte. What we are expecting from this project is an on-board AI capability that is optimally coupled with hardware that can support a broad range of space applications (e.g., autonomous space vehicle docking, decision support for autonomous probes or landers, autonomous robotic systems) and enhance decision-making applications in the future.
- Quasar. Together with our consortium member – the EIDEL company, our team will develop methods for reprogramming processing units that handle telecommands and telemetric data in satellites. Thanks to this, it will be possible to implement critical safety functions and algorithms in a reprogrammable in-orbit FPGA system.
- Phi sat 2. We are taking part in the development of the next-generation Artificial Intelligence (AI) satellite mission for the European Space Agency – ESA. A consortium led by Open Cosmos, of which KP Labs is a member, will create ɸ-sat-2 – a satellite which will further demonstrate the capabilities of AI technology for Earth observation. The ɸ-sat-2 satellite will be ready to launch mid 2022!
5. Our team won an award at the IEEE Geoscience and Remote Sensing Society 2020 Interactive Session Prize Paper Award at IEEE IGARSS. The article was submitted a year earlier – in 2019 at the IGARSS conference in Yokohama, Michal Kawulokł and Jakub Nalepa presented a poster concerning the publication: M. Kawulok, S. Piechaczek, K. Hrynczenko, P. Benecki, D. Kostrzewa, and J. Nalepa, “On training deep networks for satellite image super-resolution,” in IGARSS 2019- 2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2019, pp. 3125–3128. The GRSS established the Interactive Session Prize Paper Award to recognize the authors who posted at the GRSS Symposium (IGARSS) an exceptional paper in terms of content and impact on the GRSS. And… finally, out of over 1.5 thousand posters, ours was chosen!
8. Our COO Michal Zachara became a member of the Polish Space Agency (POLSA) Board.
9. We were nominated by the Polish Space Agency for the XVIII edition of the Presidential Economic Award! From hundreds of companies applying for the award, KP Labs was shortlisted among two other companies in the category Startup_PL. The winners will be announced during a gala in 2021.
10. Last year our team published 13 articles: additionally, there were 10 lectures at scientific and semi-scientific conferences.
One more extra piece of news! As many as 9 new people joined KP Labs. We are happy to have you all on board!