Write a comment
University students participated in a hands-on ESA Academy training course at ESA's ESTEC technical center in the Netherlands last week, where they worked with 3D-printed rovers to develop autonomous navigation skills. Six teams were tasked with programming their rovers to detect and move towards a blue ball in a simulated Mars environment.
The students were provided with ExoMy rovers, 3D- by Erica Marchand
Paris, France (SPX) Nov 07, 2024
University students participated in a hands-on ESA Academy training course at ESA's ESTEC technical center in the Netherlands last week, where they worked with 3D-printed rovers to develop autonomous navigation skills. Six teams were tasked with programming their rovers to detect and move towards a blue ball in a simulated Mars environment.
The students were provided with ExoMy rovers, 3D-printed machines modeled after ESA's Rosalind Franklin rover. These devices featured six wheels, a camera, and a Raspberry Pi computer, with all hardware and software components being open source and complemented by detailed assembly guides.
"This ESA Academy Robotics Workshop 2024 engaged 30 university students with backgrounds in engineering or robotics from 14 different ESA Member States and Canada," said ESA robotics engineer Marti Vilella Ramisa. "The goal was to introduce them to designing and operating a 3D-printed rover, inspired by the Rosalind Franklin ExoMars rover set for deployment later this decade."
The four-day workshop combined lectures and practical sessions. Students enhanced their knowledge by making improvements and debugging the rovers' ROS 2 Robot Operating System, primarily coded in Python. Initial activities included a robotics overview and an introduction to the ExoMy rover, followed by simulations and manual control tests on Mars-like terrain using a wireless gamepad.
Participants explored different rover locomotion modes and their algorithms, implementing two new modes on their ExoMy for better maneuvering. Utilizing the built-in camera, teams captured and tagged images of the target ball to train a neural network for automatic detection through Machine Learning.
"The culminating task was to integrate locomotion and image recognition to autonomously locate and approach the ball, despite its unknown position," Marti added. "This was complex but highly rewarding, as all teams met the challenge and exceeded expectations."
The students presented their final projects and received evaluations, along with course transcripts and certificates. These achievements can be converted into European Credit Transfer and Accumulation System (ECTS) credits at their home universities.
More training courses and information about ESA Academy programs can be found here.
Related Links
ESA Academy
All about the robots on Earth and beyond!