Summary of Precision Mars Entry Navigation with Atmospheric Density Adaptation Via Neural Networks, by Felipe Giraldo-grueso et al.
Precision Mars Entry Navigation with Atmospheric Density Adaptation via Neural Networks
by Felipe Giraldo-Grueso, Andrey A. Popov, Renato Zanetti
First submitted to arxiv on: 17 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Systems and Control (eess.SY); Applications (stat.AP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper introduces a new approach to online filtering for Martian spacecraft entry navigation using neural networks. The proposed method estimates atmospheric density and accounts for uncertainty in real-time, leveraging measurement innovations to adapt network parameters. This is achieved by formulating the adaptation process as a maximum likelihood problem, enabling the use of efficient stochastic optimizers from machine learning. The paper compares performance with two other online adaptive approaches in various realistic Martian entry navigation scenarios, demonstrating superior estimation accuracy and precise alignment with sampled atmospheres. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Spacecraft entering Mars need special navigation to stay on track. Right now, there’s a big problem: the air density around Mars is hard to predict, which makes it tricky for spacecraft to navigate accurately. This new research solves this problem by using a special kind of computer program called a neural network to estimate the air density in real-time. The neural network learns from its mistakes and adapts to the uncertainty in the air density, making it better at predicting the right path for the spacecraft. |
Keywords
* Artificial intelligence * Alignment * Likelihood * Machine learning * Neural network
