Summary of Contingency Planning Using Bi-level Markov Decision Processes For Space Missions, by Somrita Banerjee and Edward Balaban and Mark Shirley and Kevin Bradner and Marco Pavone
Contingency Planning Using Bi-level Markov Decision Processes for Space Missions
by Somrita Banerjee, Edward Balaban, Mark Shirley, Kevin Bradner, Marco Pavone
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Robotics (cs.RO)
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 Machine learning educators can expect this research paper to contribute to autonomous contingency planning for scientific missions by enabling rapid policy computation from any off-nominal point in the state space. The authors propose a bi-level Markov Decision Process (MDP) framework, which improves computational tractability while aligning with existing mission planning practices and enhancing explainability and trustworthiness of AI-driven solutions. By converting a mission planning MDP into a bi-level MDP and testing it on RoverGridWorld, the authors demonstrate the computational tractability and near-optimal policies achievable with this approach, highlighting trade-offs between compute time and policy optimality as the problem’s complexity grows. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Autonomous contingency planning for scientific missions is important because it helps manage risks and rewards in uncertain situations. The research uses a special kind of math called Markov Decision Processes (MDPs) to help make decisions. But, when there are many possible actions to take, like with a planetary rover, the math can get very complicated. To solve this problem, the researchers came up with a new way to use MDPs that makes it faster and more reliable. They tested their idea on a special kind of computer simulation called RoverGridWorld and showed that it works well. This means that scientists can make better plans for their missions and feel more confident in the decisions they make. |
Keywords
» Artificial intelligence » Machine learning
