Results

1st RAMI Cascade Campaign

for Marine Robots

The First RAMI Cascade Evaluation Campaign for marine robots has ended, it challenged the navigation and perception capabilities of participant teams by presenting them training datasets collected on scenarios similar those of physical campaigns.

Based on these data, teams were required to develop their software and tune their algorithms, which were then evaluated on a test dataset composed as follows:

- 3 Images showing Black numbers on yellow pipes 

- 3 Images showing Black numbers over a red background

- 6 Images showing only tubes and water with no OPIs

- 5 Images showing colored buoys (2 Red, 2 White, 1 Yellow)

- 3 Images showing a Red marker over a yellow pipe

Every team submitted a Docker Image as a Docker Hub repository, which was evaluated following the rules described here

 

Ranking

Below are the TOTAL final ranking for each Team:

Rank Team Points
1 Ensta Team Robex 113/125
2 TEAMERGO 107/125
3 OUBOT 45/125

Detailed scoring per function:

Classification

Rank Team Points
1 Ensta Team Robex 47/48
2 TEAMERGO 47/48
3 OUBOT 20/48

Identification

Rank Team Points
1 Ensta Team Robex 30/35
2 TEAMERGO 18/35
3 OUBOT 3/35

Centroid computation

Ranking Team Points
1 TEAMERGO 42/42
2 Ensta Team Robex 36/42
3 OUBOT 22/42

We thank all participating team for taking part in the competition and looking forward to seeing you at our next events!

Organising committee

Chair

Dr Gabriele Ferri (CMRE, Italy)

Co-chairs

Alessandro Faggiani (CMRE, Italy)

Dr Tommaso Fabbri (CMRE, Italy)