DIRECT

Distributed Intelligence for REsilient Collaborative roboTics
in Extreme Environments

Horizon Europe €1.69 million Sept 2026 – Aug 2030

News & Events

Latest from the project.

Nov 2026

DIRECT Seminar

We are delighted to host the first DIRECT Seminar at the University of Warwick. The event will feature five keynote speakers from UK Atomic Energy Authority, Kent Fire & Rescue Service, Extend Robotics, IEEE RAS UK & Ireland, and Ross Robotics. PwC UK will also join an interview about their vision in drone/robotics market. The seminar will explore how robotics is transforming nuclear decommissioning, emergency response, and operations in challenging industrial environments.

DIRECT project kick-off meeting held online DIRECT project kick-off meeting held online
Sept 2026

DIRECT Kickoff Meeting

The DIRECT kick-off meeting was successfully held online, marking the official start of the project. The EU Project Officer also provided an introduction to the project and its implementation.

DIRECT project kick-off meeting held online

About

Toward a smart robotic team in most challenging environments.

Robots hold great potential to support humans in extreme environments—such as post-disaster zones—where conditions are hazardous, unpredictable, and often lack reliable connectivity. Their capacity to operate in dangerous or inaccessible areas makes them crucial for search and rescue, damage assessment, and emergency response. Yet, conventional robotic systems often struggle in such contexts due to limited adaptability, fragile autonomy, and insufficient coordination. Challenges like degraded sensor inputs, dynamic unstructured terrains, GPS-denied environments, and constrained communications further hinder their effectiveness. While embodied AI has significantly enhanced the perception and action capabilities of individual robots, its focus has largely remained on single-agent systems. Achieving efficient multi-robot collaboration under uncertain, real-time, and bandwidth-limited conditions remains a major research frontier. The DIRECT project tackles these challenges by developing an innovative distributed machine learning framework that enables a fleet of robots to collaboratively perceive, reason, plan, and act in extreme environments.

€1.69M
EU funding
19
Project partners
8
Work packages
5
Research objectives

Objectives

O1

Distributed perception, reasoning, planning and action pipeline

Develop a four-stage pipeline (perception, reasoning, planning and action) that enables distributed task execution across a robot swarm in disaster zones.

O2

Resilient federated learning

Design a resilient federated learning model optimized for limited connectivity and hardware constraints.

O3

6G-powered sensing–computing–communication infrastructure

Develop a 6G-powered integrated sensing–computing–communication infrastructure that supports collaborative perception, reasoning and co-planning.

O4

Human-in-the-loop collaborative decision-making

Implement human-in-the-loop collaborative decision-making for remote support of multi-robotic systems.

O5

Validation through simulation and benchmarking

Validate the DIRECT framework through simulation, benchmark model and dataset development.

Work Packages

WP1 Project Management and Coordination
WP2 Mission Requirements and System Architecture
WP3 Distributed AI Framework for Multi-robots Collaboration
WP4 6G-Enabled Sensing–Computing–Communication Infrastructure for Distributed AI
WP5 Collaborative Human-Robot Interaction Framework
WP6 Framework Integration, Evaluation and Pilot Study
WP7 Communications, Dissemination, Standardization and Exploitation
WP8 Ethics Requirement

Documents

Project outputs, in one place.

Deliverables, publications, datasets and software produced by the DIRECT consortium will be made available here (also in Zenodo) as the project progresses.

Deliverables

Formal project deliverables submitted to the European Commission throughout the project lifetime.

To be published.

Publications

Peer-reviewed papers, conference proceedings and preprints authored by the DIRECT consortium.

To be published.

Datasets

Benchmark datasets collected and released to support multi-robot perception and planning research.

To be published.

Software

Open-source code, simulation environments and toolkits developed as part of the DIRECT framework.

To be published.

Consortium

Coordinated by the University of Warwick. Delivered by a global consortium.

DIRECT brings together 19 partners across universities, research institutes and industry, with complementary expertise in robotics, distributed AI and extreme-environment operations.

University of Warwick

Coordinator

Connected and Collaborative Robotics Lab (CCR Lab) — integrating AI with advanced communication and networking for seamless robot-to-robot and human-to-robot collaboration.

Contact

Get in touch.

Project Coordinator

Dr. Zhenhui Yuan
Associate Professor
Connected and Collaborative Robotics Lab (CCR Lab)
University of Warwick, United Kingdom
zhenhui.yuan@warwick.ac.uk

CCR Lab website

Events & Engagement Manager

Miss.Wanlu Sun
PhD Researcher
Connected and Collaborative Robotics Lab (CCR Lab)
University of Warwick, United Kingdom

Wanlu.Sun.2@warwick.ac.uk

Social Media & Communications Manager

Mr.Zexin Deng
PhD Researcher
Connected and Collaborative Robotics Lab (CCR Lab)
University of Warwick, United Kingdom

Zexin.Deng@warwick.ac.uk

Funded by the European Union under the Horizon Europe programme.
Grant Agreement No. 101299316, 2026–2030.
Topic(s): HORIZON-MSCA-2025-SE-01-01.