Abstract
Benchmark Proposal: Neural Network Control Systems (NNCS) play critical roles in autonomy. However, verifying their correctness is a substantial challenge. In this paper, we consider the neural network compression of ACAS Xu, a popular benchmark usually considered for open-loop neural network verification. ACAS Xu is an air-to-air collisionavoi dance system for unmanned aircraft issuing horizontal turn advisories to avoid collision with an intruder aircraft. We propose specific properties and different system assumptions to use this system as a closed-loop NNCS benchmark. We present experimental results for our properties based on randomly generated test cases and provide simulation code.
| Original language | English |
|---|---|
| Pages (from-to) | 1-8 |
| Number of pages | 8 |
| Journal | EPiC Series in Computing |
| Volume | 96 |
| DOIs | |
| State | Published - 2023 |
| Event | 10th International Workshop on Applied Verification of Continuous and Hybrid Systems, ARCH 2023 - San Antonio, United States Duration: May 9 2023 → May 9 2023 |
Keywords
- ACAS Xu
- autonomous systems
- dynamical systems
- nonlinear systems
- test case
- verification
Fingerprint
Dive into the research topics of 'Closed-Loop ACAS Xu Neural Network Verification'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver