A work on the Image-based Deep Reinforcement Meta-Learning for Autonomous Lunar Landing Published on the Journal of Spacecraft and Rockets
May 10, 2021
Image
Image-based Deep Reinforcement Meta-Learning for Autonomous Lunar Landing
We are glad to share that the last paper on the Journal of Spacecraft and Rockets is finally out!
In this paper, we apply image-based reinforcement meta-learning to solve the lunar pinpoint powered descent and landing task with uncertain dynamical parameters and actuator failure. The agent, a deep neural network, takes real-time images and ranging observations acquired during the descent and maps them directly to thrust command (i.e. sensor-to-action policy).
A special thank goes to our SSEL's members, Andrea Scorsoglio, Andrea D'Ambrosio, Luca Ghilardi, Brian Gaudet, Fabio Curti and Roberto Furfaro.
You can read it on Researchgate: