DARKO, Safe robotics and ntralogistic processes

The international research project on dynamic agile production robots that learn and optimize operations

Agile production crucially depends on the effectivity of intralogistics processes. Robots as components of these processes have the potential to be a game changer — provided they are highly flexible, capable, cost- and energy-efficient, safe and able to operate in work environments shared with humans. However, the current state of the art falls short of providing these capabilities given the requirements for future production systems.

DARKO proposes a new generation of agile robots that have energy-efficient elastic actuators that are able to:

  • Execute highly dynamic motions.
  • Operate safely within unknown, changing environments.
  • Are easy (cost-efficient) to deploy.
  • Apply predictive planning capabilities to decide for most efficient actions while limiting associated risks.
  • Understand humans and their intentions to smoothly and intuitively interact with them.

DARKO, elevating intralogistics, made safe

Name of project:

DARKO platform – Dynamic Agile Production Robots That Learn and Optimize Knowledge and Operations


4 years and 6 month



Target markets:

Industrial technology


Örebro University, TUM, Bosch, Università degli Studi di Pisa, EPFL, University of Lincoln.


Fondi Europei CE – Horizon 2020

Overall project investments:




Our solution

DARKO has as its main overarching objective to research and innovate for efficient and safe intralogistics robots in agile production. These two aspects are reflected in the specific project objectives, aimed at realizing the fundamental enabling technology that will make intralogistics in agile production flexible, robust and easily deployable. These are:

  • Efficiency in manipulation: DARKO aims to ease dynamic manipulation tasks by exploiting inherently elastic manipulators, inertial coupling effects, flexible end-effectors, endowing robots with the required high-speed perception. It further develops algorithms to increase efficiency and safety.
  • Efficiency in human-robot co-production: DARKO increases efficiency and safety in environments shared between robots and humans in particular by means of learning and exploiting activity patterns, prediction and mutual communication of intents, as well as a novel framework for risk-aware planning and coordination. This supports predictive planning of activities to ensure zero-risk of collision.
  • Efficient deployment: the objective of efficient deployment – low effort & high flexibility – is addressed from the point of view of failure-aware and failure-resilient mapping and localization, as well as “auto-completion” of robot maps and information transfer using map priors from heterogeneous sources.
  • Risk-aware operations for safety and efficiency: risk assessment is added as a driving principle for the decisions taken by one or more intelligent agents acting at shop floor level, achieving efficient and safe intralogistics robotics.


Apart from the intrinsic benefits coming from reaching the overarching goals of the DARKO projects, implementing a safe robotics into agile production brins more value to the equation:

  • Time optimization: with the ability of robotic arms to throw objects onto conveyor belts, they reach further than their kinematic range and do not need to be driven to a range of locations to operate. This is just one way in which processes are optimized in a time-efficient fashion.
  • Safety first, throughout and last: reliability and safety are primary concerns throughout the development and implementation of DARKO’s sophisticate Human-Machine interaction technologies.
  • No-stress solution: thanks to the focus on an easy deployment, DARKO is flexible and reliable. This way, each robotic and technological solution is tailored to the needs of the specific client, and transformation becomes stress-free.

Digital Twin e Object and Anomaly Detection


Avatar, un virtual assistant human-like


Tech Radar, il Web Crawler per il mondo IT

Augmented Intelligence, DEEP LEARNING