English

The Adaptive Stress Testing Formulation

Robotics 2020-04-10 v1 Machine Learning Systems and Control Systems and Control Machine Learning

Abstract

Validation is a key challenge in the search for safe autonomy. Simulations are often either too simple to provide robust validation, or too complex to tractably compute. Therefore, approximate validation methods are needed to tractably find failures without unsafe simplifications. This paper presents the theory behind one such black-box approach: adaptive stress testing (AST). We also provide three examples of validation problems formulated to work with AST.

Keywords

Cite

@article{arxiv.2004.04293,
  title  = {The Adaptive Stress Testing Formulation},
  author = {Mark Koren and Anthony Corso and Mykel J. Kochenderfer},
  journal= {arXiv preprint arXiv:2004.04293},
  year   = {2020}
}

Comments

Presented at the Workshop on Robust Autonomy at RSS 2019