An educational landing game in Flutter and Flame, with 14 stages, Gemini guidance and a Q-learning demo. Third place in the SpaceAware Application Challenge.
01 · Control
Thrust. Rotate. Adapt.
The lander mechanics include thrust, rotation, fuel, wind and hazards. Choices change the descent.
02 · Feedback
A little guidance. A clearer next step.
Gemini guidance is built into the learning experience.
03 · Learn
Different tools. Different roles.
The main game’s AI controller uses PD control. A separate interactive demonstration explains tabular Q-learning.
04 · Project scope
14 stages. One learning journey.
Built with Hoor Salman for the SpaceAware Application Challenge.
Two-person team · Third place, SpaceAware Application Challenge · October–November 2025
AURORA Mission X
Learning about landing through play and feedback.
FlutterDartFlameGeminiQ-learning
At a glance
Role
Led development of the Flutter and Flame simulator
Team
Two people, with Hoor Salman
Event
SpaceAware Application Challenge
Built with
Flutter, Dart, Flame, Gemini, plus a JavaScript Q-learning demo
Result
Third place, November 2025
01 / Purpose
What we set out to do.
Create an educational space-landing experience for the SpaceAware Application Challenge.
02 / Approach
How it came together.
We built the game in Flutter and Flame, with 14 stages and Gemini guidance. A separate interactive demo implements tabular Q-learning in JavaScript.
03 / Contribution
What I built.
Built with Hoor Salman. I led the development of the Flutter and Flame simulator, including the lander physics, the 14 stages, the Gemini guidance and the Q-learning demo.
04 / Demonstration
See it working.
The lander supports thrust, rotation, fuel, wind and hazards. The main game’s AI pilot uses proportional-derivative control, and a separate interactive demo teaches tabular Q-learning.
AURORA Mission X. A cinematic introduction with footage from the interactive learning demo.Built by Husain Altelly and Hoor Salman. The Blender lander is a conceptual illustration. Game audio and sound effects omitted. Music: Who Likes to Party by Kevin MacLeod (incompetech.com), CC BY 4.0. Excerpted, level-adjusted and faded.Watch the film in a new tab
View image AURORA’s interactive Q-learning demonstration, captured during a local demo run.AURORA Mission X team: Husain Altelly and Hoor Salman.
05 / Results
What we achieved.
We shipped a 14-stage simulator with Gemini guidance and an interactive Q-learning demo, and placed third in the SpaceAware Application Challenge in November 2025.
06 / Limitations
Limits and next steps.
AR was an experiment, and it’s switched off in the current version. The Q-learning demo is a teaching tool that runs separately from the main game’s PD controller, and we haven’t measured its success rate.
07 / Lessons learned
What I’m taking forward.
An educational interface needs to distinguish a demonstration, a working feature, and an experiment clearly. That distinction is especially useful when explaining what an AI component actually does.
The Blender scenes and animations are illustrations made for this portfolio, not recorded results. The YouTube videos show the real robots and lab demos, and the AURORA film includes footage from the interactive learning demo.
R. R. Ma, L. U. Odhner, A. M. Dollar, “A Modular, Open-Source 3D Printed Underactuated Hand,” ICRA 2013.
The Yale OpenHand Project is an initiative to advance the design and use of robotic hands designed and built through rapid-prototyping techniques in order to encourage more variation and innovation in mechanical hardware. Please visit the Yale OpenHand site for more details.
