SciTransfer
PILLAR-Robots · Project

Self-Learning Autonomous Robots for Dynamic Industrial, Agricultural and Educational Environments

digitalTestedTRL 5

Imagine a robot that doesn't need a manual for every new task but learns like a curious child. Instead of following a rigid script, it figures out its own goals based on what it experiences in the real world. It's like giving a machine a 'sense of purpose' so it can adapt to changes without a human programmer rewriting the code.

By the numbers
4,990,046
EU Contribution in EUR
34
Total deliverables
5
Target TRL
The business problem

What needed solving

Current robots are too rigid and require expensive manual programming for every new task. This makes them inefficient in unpredictable environments like farms or retail stores where conditions change constantly.

The solution

What was built

A Purposeful Intrinsically Motivated Cognitive Architecture. This includes multimodal perception modules, motivational mechanisms for goal detection, and learning algorithms integrated into ROS 2 Humble.

Audience

Who needs this

Agricultural robotics companiesWarehouse automation providersEducational robot manufacturersRetail automation SMEs
Business applications

Who can put this to work

Agri-food
any
Target: Smart farming equipment provider

If you are a smart farming equipment provider dealing with unpredictable outdoor environments — this project developed a purposeful cognitive architecture that allows robots to acquire relevant skills autonomously. This leads to higher productivity in crop management without constant manual reprogramming.

Retail & Logistics
SME
Target: Warehouse automation firm

If you are a warehouse automation firm dealing with unstructured industrial spaces — this project developed learning algorithms that align robot behavior with specific goals. This enables robots to handle changing layouts and new product types more flexibly.

Education
SME
Target: Edutainment technology developer

If you are an edutainment technology developer dealing with the need for interactive learning tools — this project developed multimodal perception modules and goal-detection systems. This allows robots to interact more naturally and adaptively with students.

Frequently asked

Quick answers

What is the cost or pricing for implementing this technology?

Based on available project data, specific pricing or licensing costs are not provided; the project is funded by an EU contribution of EUR 4,990,046 for research and development.

Can this be scaled to a full industrial level?

The project aims to reach TRL5, meaning it is validated in relevant environments. Based on available project data, the goal is to prepare the ground for further large-scale demonstrations through industry and SME engagement.

How is the IP and licensing handled?

Based on available project data, specific IP or licensing terms are not mentioned, though the consortium includes 3 SMEs and 3 industry partners to facilitate market transition.

How does this integrate with existing robot software?

The system is implemented in ROS 2 Humble and uses flexible software interfaces to ensure modularity, making it compatible with standard robotic operating systems.

What is the timeline for commercial availability?

The project period runs from 2022-10-01 to 2026-10-31, suggesting that full validation and TRL5 results will be finalized by late 2026.

Consortium

Who built it

The consortium is well-balanced for technology transfer, consisting of 8 partners across 4 countries. With an industry ratio of 38% (including 3 SMEs and 3 industry players), there is a strong commercial pull to complement the academic research from 2 universities and 3 research centers.

How to reach the team

Contact UNIVERSIDADE DA CORUNA in Spain

Next steps

Talk to the team behind this work.

Contact us to explore licensing opportunities for the Purposeful Cognitive Architecture.