The future of space
AIKO is a deep tech software company specialized in the design and development of
Artificial Intelligence for the automation of space missions.
Automation will play a fundamental role
in enabling two major benefits in space mission engineering:
- reducing the costs of space missions
- increasing the efficiency and performances of satellites
In orbit, our technology enables new
capabilities on satellites, that become able to take the autonomous
decisions on how to carry out their mission goals, even if not in contact with ground. On ground,
our technology supports operators and engineering teams in optimizing how operations are
taking more informed decisions, discovering patterns and novel behaviours, and focusing on critical
Problems we focus on
Several problems are there to be solved in how operations are managed in a space mission, and in
AIKO we focus both on improving the flight-segment and ground-segment. For issues that we can solve
we focus on enabling:
On ground, our technology is deployed in the Mission Control Centre. It helps in:
- data understanding capabilities on the satellite, to prioritize and select data
based on information content.
- the recognition of observation opportunities, to enable new acquisition
strategies and improve how data is collected during a mission
- prediction and anticipation of failures, integrating predictive maintenance in how a
satellite is operated
- cooperation and coordination among satellites in a constellation
- supporting operators in analysing data, in detecting patterns, novel behaviours and
correlations, in order to take more informed decisions
- managing constellations made of hundreds of satellites
AIKO is currently negotiating the Seed Round, targeted at 2020. The
of the round are product finalization and space qualification, and business development.
Things we look for in an investor: smart money, strategy, network.
We put the dream team, the vision, the commitment.
Get in touch: drop us an email.
GEMINEA invests in AIKO
Milan-based VC focused on Artificial Intelligence startups, invests in AIKO and in its vision of
to enable autonomous space missions. The round is aimed at consolidating the team and the company to
higher level in the technology development. We look forward to a shared path of growth and success!
Autonomous operations library
Enabling e4 autonomy
MiRAGE is an innovative software library to enable fully autonomous space missions, making use of
state of the
Artificial Intelligence and is the result of years of research in Mission Autonomy.
The library has been co-funded by the H2020 program SME Instrument.
MiRAGE operates by analyzing the data made available during the mission
payload and external data) to generate and update the operations schedule. The satellites become
their surroundings, the internal health, and eventual commands provided by the Mission Control
library enables autonomous decisions during a mission, tailored to the needs of the end-users and
Planning and scheduling is a very resource-intensive activity during most
Performing schedule changes in reaction to unplanned mission events is even more challenging, due to
of these occurrences, to the necessity of having staff on-site 24/7, and to the quick reaction times
to reduce eventual mission outages.
By shifting the decision-making on-board the satellite,
the decision-making loop in the Mission Control Centre for all the events that were accounted for
spacecraft development, including failures, events related to mission objectives, or events
generated by other
elements in a constellation.
Operators still maintain highest priority in commanding the
spacecraft: they are
just focusing on more critical decisions that might still require ground intervention.
We implement the latest advancements in Artificial Intelligence research
to enable awareness on the satellite and to perform event detection. Our AIs are trained with
on purpose for each feature selected in MiRAGE: failure detection, payload analysis, pattern
detection. Moreover, predictions are enabled during the mission: if certain trends are likely to
result in a
future Out Of Limit alert, our AIs are able to warn operators ahead of time.
By using MiRAGE, more complex missions are at reach: tracking features on
enhanced acquisition modes, selecting and prioritizing payload downlinked data. The result is
efficiency, mission objectives are fulfilled sooner, and downlink bandwidth is occupied only with
Reducing operations costs
The real, long-term benefit of fully autonomous mission is the reduction
of the operations costs. This is particularly important for small satellite missions, where
operations costs have
shown not to scale with spacecraft size, and for constellations, where the high number of operators
cannot be afforded with hundreds, thousands of satellites.
TRL and Compatibility
MiRAGE, currently at TRL 6, is scheduled to reach TRL 7 by end of 2018.
The on-board version is compatible with Linux-based OS, while the
Win/Unix/Mac OS architectures.
We believe future space missions will be fully autonomous, and our technology is the enabler.
Interested in seeing MiRAGE live?
information or a demonstration tailored on your mission concept.
AIKO provides state of the art expertise and technology in three distinct areas related to the
development and operations of space missions.
State of the art AI-enabled automation
AIKO is an Artificial Intelligence and Automation company. For this reason, our core company
values revolve around
providing the most advanced, state of the art technology for the problems we set out to solve. Our
pipeline for designing, developing and deploying an AI algorithm is lean and efficient, and our
technology references are updated at least twice per year.
AI on the edge
AIKO’s unique expertise involves developing and deploying state of art AI to edge devices, including
recent releases of AI accelerators such as the Intel Myriad X, the NVIDIA Jetson, and the Google
Coral. We have successfully deployed AI algorithms to commercial processors (ARM and desktop architectures), to mobile GPUs, and to Accelerators.
From 2020, we started working on FPGAs too, to further extend our knowledge and capabilities in the embedded world.
AI for safety-critical applications
In addition to the expertise in quickly and reliably integrating state of art technologies upstream,
AIKO expertise is growing in the field of verification and validation of AI for safety-critical
applications, both in the field of supervised AI and in the field of robust and explainable AI.
Advanced Flight Software
Mission specific Command and Data Handling algorithms for E4-level autonomy.
Artificial Intelligence for Mission Replanning, Failure Detection, Isolation and
Big Data applications for space missions
Analysis algorithms for Mission Data. Feature Extraction, Image Classification, Pattern Recognition.
Expert Systems for Space Engineering
Employing Case-Based Reasoning to perform System Diagnosis, Design and Decision-Making, Project
We make of Artificial Intelligence our flagship technology:
- Deep Learning
- Expert Systems
adapting the technology to Space Systems (C&DH, AOCS, GNC, EPS) and to Space Missions. Out team
between Space Systems Engineering knowledge and Artificial Intelligence state of the art. We know
to use depending on what data is analyzed and where this data comes from.
Years of research on autonomous operations for space missions ensure our work reflects most recent
Our team has research published in important peer-reviewed international journals (Mechanical
Systems and Signal
Robotics and Autonomous Systems, Journal of Guidance, Control, and Dynamics), and several
aerospace congresses (IAC, AIAA Space, IEEE Aerospace, ESA 4S, European CubeSat Symposium).
At AIKO, we develop embedded software for most typical satellite COTS processors:
- ARM family, MSP family
Development heritage on the flown
e-st@r I and II satellites.
Who we are
Legal and Business
Doctor in Law
Space Science Institute
Machine Learning algorithms for Mars Event Detection on a SmallSat mission
AIKO signs a collaboration with the
Space Science Institute,
The collaboration will be focused on evaluating the implementation of Machine Learning
algorithms for a Mars
The Space Science Institute (SSI) is a nonprofit research and education corporation based in
a vision to expand humankind's understanding and appreciation of planet Earth, our Solar System, and
SSI is home to more than 60 scientists carrying out cutting edge research in astrophysics, planetary
physics. It is also a leader in translating science into education and outreach projects, and it was
home to the
Imaging Science Subsystem Ops team, which provided the best pictures of Saturn, its rings, and moons
until the end
NASA's Cassini mission.
The project opens an important commercial direction for AIKO, with the first collaboration aimed at
AI-based algorithms for interplanetary missions. Small Satellites are characterized by severe
their utilization in interplanetary missions challenging. AIKO algorithms are an enabling technology
future Small Satellites missions to other planets possible.
ESA Advanced Concepts Team
Deep Learning for spacecraft applications
AIKO starts a collaboration with ESA
Advanced Concepts Team, ESTEC, The
The collaboration will focus on developing a tool for evaluating the computational requirements
of the art algorithms for embedded applications.
The outcome of the project will allow an user to estimate, given a specific or custom
architecture of Deep
the computational requirements of the algorithm. In particular, information such as operation
and inference time for each processor will be displayed. The tool represents an initial step towards
and utilization of Artificial Intelligence in space applications and will be provided as a freely
on AIKO website.
Advanced Concepts Team
(ACT) is part of the ESA’s Directorate of Technical and Quality Management (TEC-SF). The team is
the study of technologies and ideas that are of strategical importance in the long term planning of
the Agency. It
the function of a think tank providing decision makers the support of a highly multidisciplinary
at ESTEC, they carry out research work on advanced topics and emerging technologies and perform
on a wide range of topics.
AIKO does not handle personal data.
For additional enquiries, please
In-orbit demonstration agreement
Deep Learning for Earth Observation applications
AIKO signs an agreement with Satellogic (satellogic.com), an Earth Observation satellite company to validate Deep
Learning technology. The activity will be carried out within Satellogic's Software and Hardware
Hosted Payloads Program during 2019.
Why this is important for us
In-orbit validation is a key step in order to improve AIKO heritage. The Technology Readiness Level
technology will reach the status of TRL 9: demonstrated in real mission scenario.
AIKO's technology enables more ambitious commercial and scientific goals for Earth
Observation missions, as an increased degree of on-board autonomy helps in implementing more
mission operations. In particular, functionalities like event detection, autonomous planning and
goal management, if implemented on-board, introduce several benefits to the way operations are
The deep learning opens new possibilities and horizons, such as:
- Prioritization and payload data selection
- Onboard data enhancing
In addition to the activities carried out during the program, AIKO will further improve its internal
procedures for implementing and optimizing Deep Learning software in the context of space systems
Given this opportunity, AIKO further consolidates its role in the Space industry, as provider of
automation and Artificial Intelligence solutions, dramatically expanding its know-how and expertise.
A sincere thank you to Satellogic for the opportunity!
AIKO premises are located in the I3P
Politecnico di Torino, Italy, ranked in 2014 among the top 25
best incubators in the world. AIKO offices are equipped with the needed infrastructure to carry out
engineering activities related to AIKO background. This includes, Artificial Intelligence design and
software R&D, teleconferences and concurrent engineering. AIKO makes use of state of the art cloud
infrastructure provided by Google, NVIDIA and Microsoft, in addition to local GPU-enabled resources
each AIKO engineer.
AIKO offices are located in Torino, in a central location fully connected to train and bus station,
walking distance from the Politecnico di Torino.
Our Team -
Corso Castelfidardo 30/A, 10129, Torino, Italy