Summary of System Safety Monitoring Of Learned Components Using Temporal Metric Forecasting, by Sepehr Sharifi et al.
System Safety Monitoring of Learned Components Using Temporal Metric Forecasting
by Sepehr Sharifi, Andrea Stocco, Lionel C. Briand
First submitted to arxiv on: 21 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Robotics (cs.RO); Software Engineering (cs.SE)
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 paper proposes a novel approach to developing a safety monitor for learning-enabled autonomous systems, which is crucial for ensuring system safety. The proposed method uses probabilistic time series forecasting based on Deep Learning (DL) models to predict the satisfaction or violation of safety requirements given learned component outputs and operational contexts. The authors empirically evaluate four state-of-the-art DL-based models, including Temporal Fusion Transformer (TFT), using autonomous aviation and driving case studies. The results show that probabilistic forecasting is effective for safety monitoring, with TFT being the most accurate model for predicting imminent safety violations in both case studies. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps make self-driving cars and airplanes safer by creating a system to monitor their actions and prevent accidents. The idea is to use special computer models that can predict what will happen if the car or plane makes a certain move, based on its past actions and the current situation. The researchers tested several different types of these predictive models and found that one called Temporal Fusion Transformer worked best at predicting when an accident might happen. This could help make self-driving vehicles more reliable and trustworthy. |
Keywords
» Artificial intelligence » Deep learning » Time series » Transformer
