SPECTRUM

The Challenge

Name: 
Stereo event-camera on miniature drone

Domain: 
Sensor integration, computer vision, design and development of miniaturized drones, advanced camera systems

Challenge proposer:

Objectives:
The primary objectives of this project are:

  • To design and develop a mini drone with a < 6-inch frame size that incorporates a stereo event camera;
  • To ensure that the mini drone is capable of agile flight and real-time data processing of the onboard sensors;
  • To integrate the stereo event camera with the drone’s control and navigation systems, enhancing the drone’s ability to perceive its environment and effectively avoid obstacles.

The Solution

Name: 
SPECTRUM – Stereo-perception enabled compact robot for unmanned monitoring

Description:
SPECTRUM introduces a compact aerial platform designed to autonomously navigate and inspect complex, low-visibility industrial environments, such as ship ballast tanks, using cutting-edge stereo event-based vision. At the core of the system is a stereo pair of Prophesee GenX320 event cameras and an NVIDIA Jetson Orin Nano onboard processor for low latency depth-processing. The mini drone features a lightweight but robust frame, high-RPM brushless motors for enhanced agility and manoeuvrability and open-source autopilot software for stability and reactivity. The system will run a custom vision stack, including spatiotemporal event filtering and noise suppression, stereo event correlation for disparity estimation, 3D edge-based depth reconstruction and SLAM.

This high-fidelity 3D pipeline offers excellent performance in visually degraded conditions, through the inherent resistance of event cameras to motion blur and variable lighting, maintaining perception in dust, glare or even total darkness. This leads to unprecedented agility and awareness during navigation in confined spaces and real-time obstacle recognition and avoidance. Onboard autonomy is provided by ROS2 handling sensor fusion, path planning and triggering failsafe behaviours, to enable safe and independent automated inspections.

The Solution Provider

CogniSensus builds technologies that allow better sensing, data modelling, visualisation and/or actuation, supporting the operation, decision- making or training in complex environments.

Open Call For Tech Solutions

AUTOASSESS invites Startups and SMEs to present their innovative technology solutions addressing specific use-case challenges identified by the AUTOASSESS technical team and end-users.

The Open Call for Tech Solutions is an initiative that supports the integration of external providers into our project, enhancing use cases through innovative approaches.

OVERVIEW

AUTOASSESS main goal is to innovate by creating a fully autonomous inspection of ballast tanks and cargo holds of vessels. By embracing an open approach of innovation model, AUTOASSESS aspires to use the entire value chain of the consortium as well as external stakeholders. The objective? To assess the best ideas, regardless of the origins!

Key features of AUTOASSESS Open Calls:

  • Financial Support to Third Parties (FSTP) mechanism: Promoting third-party involvement, ensuring that innovative solutions are market-ready before project completion.
  • Collaborative Co-Creation: Supporting external technology providers and invite them to develop and enhance existing use cases.
  • Targeted Problem-Solving: Implementing two open calls: Open Call for Tech Solutions and Open Call for Tech Innovations (planned for 2025).

Key Team Members:

Georgios Tsimiklis

Georgios Tsimiklis

Project Overview
Vasileios Balntas​

Vasileios Balntas​

Project Lead

Fotios Konstantinidis

Smart Manufacturing Leader
Valantis Tsiakos

Valantis Tsiakos

Drone development and installation of the camera
Mary Papaefthymiou

Mary Papaefthymiou

Administrative and Quality

Sign up for the AUTOASSESS newsletter and be
the first to know once our open calls are launched