Summary of Xai-based Feature Ensemble For Enhanced Anomaly Detection in Autonomous Driving Systems, by Sazid Nazat and Mustafa Abdallah
XAI-based Feature Ensemble for Enhanced Anomaly Detection in Autonomous Driving Systems
by Sazid Nazat, Mustafa Abdallah
First submitted to arxiv on: 20 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 framework for enhancing both anomaly detection and interpretability in autonomous vehicles (AVs). Traditional AI models are often opaque, making it difficult to understand and trust their decision-making processes. The proposed feature ensemble framework integrates multiple Explainable AI (XAI) methods, including SHAP, LIME, and DALEX, with various AI models such as Decision Trees, Random Forests, Deep Neural Networks, K Nearest Neighbors, Support Vector Machines, and AdaBoost. This fusion of top features across six diverse AI models creates a robust and comprehensive set of features critical for detecting anomalies. The framework is evaluated using independent classifiers on two popular autonomous driving datasets, VeReMi and Sensor, demonstrating improved accuracy, robustness, and transparency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make self-driving cars safer by making the computers that control them more understandable. Right now, these computers are often too good at predicting what will happen next, but not good enough at explaining why they made a certain decision. The authors of this paper have developed a new way to combine different AI methods and models to detect unusual events, like a pedestrian stepping into the road. By using many different approaches, the new system is more reliable and easier to understand than existing systems. |
Keywords
» Artificial intelligence » Anomaly detection
