Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.13869 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913300636237824 |
|---|---|
| author | Bai, Ruoxuan Yang, Jingxuan Gong, Weiduo Zhang, Yi Lu, Qiujing Feng, Shuo |
| author_facet | Bai, Ruoxuan Yang, Jingxuan Gong, Weiduo Zhang, Yi Lu, Qiujing Feng, Shuo |
| contents | Intelligent systems are increasingly integral to our daily lives, yet rare safety-critical events present significant latent threats to their practical deployment. Addressing this challenge hinges on accurately predicting the probability of safety-critical events occurring within a given time step from the current state, a metric we define as 'criticality'. The complexity of predicting criticality arises from the extreme data imbalance caused by rare events in high dimensional variables associated with the rare events, a challenge we refer to as the curse of rarity. Existing methods tend to be either overly conservative or prone to overlooking safety-critical events, thus struggling to achieve both high precision and recall rates, which severely limits their applicability. This study endeavors to develop a criticality prediction model that excels in both precision and recall rates for evaluating the criticality of safety-critical autonomous systems. We propose a multi-stage learning framework designed to progressively densify the dataset, mitigating the curse of rarity across stages. To validate our approach, we evaluate it in two cases: lunar lander and bipedal walker scenarios. The results demonstrate that our method surpasses traditional approaches, providing a more accurate and dependable assessment of criticality in intelligent systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13869 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Accurately Predicting Probabilities of Safety-Critical Rare Events for Intelligent Systems Bai, Ruoxuan Yang, Jingxuan Gong, Weiduo Zhang, Yi Lu, Qiujing Feng, Shuo Machine Learning Artificial Intelligence Intelligent systems are increasingly integral to our daily lives, yet rare safety-critical events present significant latent threats to their practical deployment. Addressing this challenge hinges on accurately predicting the probability of safety-critical events occurring within a given time step from the current state, a metric we define as 'criticality'. The complexity of predicting criticality arises from the extreme data imbalance caused by rare events in high dimensional variables associated with the rare events, a challenge we refer to as the curse of rarity. Existing methods tend to be either overly conservative or prone to overlooking safety-critical events, thus struggling to achieve both high precision and recall rates, which severely limits their applicability. This study endeavors to develop a criticality prediction model that excels in both precision and recall rates for evaluating the criticality of safety-critical autonomous systems. We propose a multi-stage learning framework designed to progressively densify the dataset, mitigating the curse of rarity across stages. To validate our approach, we evaluate it in two cases: lunar lander and bipedal walker scenarios. The results demonstrate that our method surpasses traditional approaches, providing a more accurate and dependable assessment of criticality in intelligent systems. |
| title | Accurately Predicting Probabilities of Safety-Critical Rare Events for Intelligent Systems |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.13869 |