Enhancing Remote-Sensing Satellite Task Scheduling Using Reinforcement Learning and Multi-Objective Optimization

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Observational analysis improved failure rate and mission execution in remote-sensing satellites, suggesting AI may enhance task scheduling.

Using reinforcement learning, optimization of task scheduling for remote-sensing satellites improved system performance significantly.
The research identifies a clear tradeoff between solution diversity and operational realism, with practical applications emphasized.
Employing multi-objective optimization via the Pareto front, two key metrics—failure rate and timely execution—were simultaneously optimized.
Incorporating realistic constraints like memory and power management enhances the deployability of the solutions found.

Khatir et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

Observational analysis improved failure rate and mission execution in remote-sensing satellites, suggesting AI may enhance task scheduling.