Summary of Improving Explainable Object-induced Model Through Uncertainty For Automated Vehicles, by Shihong Ling et al.
Improving Explainable Object-induced Model through Uncertainty for Automated Vehicles
by Shihong Ling, Yue Wan, Xiaowei Jia, Na Du
First submitted to arxiv on: 23 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computer Vision and Pattern Recognition (cs.CV); 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 The proposed “object-induced” model approach in this study addresses challenges in explainable automated vehicle (AV) architectures by prioritizing the role of objects in scenes for decision-making. The integrated uncertainty assessment using an evidential deep learning paradigm with a Beta prior enables AVs to provide more transparent and reliable explanations for actions. Advanced training strategies, including uncertainty-guided data reweighting and augmentation, are explored to improve model performance. Experimental results on the BDD-OIA dataset demonstrate that the enhanced model outperforms existing baselines across various scenarios. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary AVs are becoming a reality, promising safer and more efficient travel options. But they need to be able to explain their decisions in complex situations. The problem is that current models don’t fully account for uncertainties. This study creates a new approach that focuses on objects in the scene and incorporates uncertainty into decision-making. It also develops new training methods that use uncertainty to improve performance. By testing this model on real-world data, researchers found that it can explain its decisions better than existing models and make more accurate predictions. |
Keywords
» Artificial intelligence » Deep learning
