Model based AI achieves precise control for planetary landings
DreamLander: A 6-DOF World Model based Reinforcement Learning Planetary Lander
Robotics
Summary
Landing spacecraft safely on other planets is very hard because they have very little fuel to correct their course. The authors created DreamLander, an AI system that learns to control the landing using a model of the spacecraft’s environment and movement. DreamLander can guide the spacecraft to land within 2 meters of the target and slow it down effectively just using sensor data. This approach makes landing more efficient and could be adapted to different kinds of landings.
What this means in practice
- •For space mission engineers: Use DreamLander to generate fuel-efficient guidance and control for spacecraft descent and landing phases.
- •For autonomous vehicle developers: Adapt model based reinforcement learning approaches like DreamLander to improve precise control in complex, multi-degree-of-freedom navigation tasks.
Authors
George Nehma, Patrick Quinn, Madhur Tiwari, Camilo Riano-Rios
Abstract
Soft powered descent landings are becoming evermore important in the field of space exploration and scientific advancement, because of their ability to deliver mission critical payloads, both highly accurately and safely. The high efficiency restriction on planetary landings due to the severely limited fuel supply results in the need for optimal guidance trajectories and control. Model based reinforcement learning is proving to be an important tool in simplifying the highly complex process of generating optimal guidance trajectories and control. In this work, we present DreamLander, a state of the art model based reinforcement learning algorithm based on DreamerV3, to generate optimal guidance and control for a realistic 6 degree of freedom entry descent landing problem. The model based approach creates a sample efficient and highly generalizable model that can be applied to a variety of scenarios whilst maintaining a high degree of accuracy, landing within 2 meters of the designated landing zone, and with velocity norm less than 0.3 meters per second. DreamLander makes use of state sensor observations, making progress toward End-to-End solutions of the Entry Descent Landing problem.