{
  "id": "2302.04634",
  "version": "v1",
  "published": "2023-02-06T18:56:20.000Z",
  "updated": "2023-02-06T18:56:20.000Z",
  "title": "Closed-loop Analysis of Vision-based Autonomous Systems: A Case Study",
  "authors": [
    "Corina S. Pasareanu",
    "Ravi Mangal",
    "Divya Gopinath",
    "Sinem Getir Yaman",
    "Calum Imrie",
    "Radu Calinescu",
    "Huafeng Yu"
  ],
  "categories": [
    "cs.CV",
    "cs.AI",
    "cs.FL"
  ],
  "abstract": "Deep neural networks (DNNs) are increasingly used in safety-critical autonomous systems as perception components processing high-dimensional image data. Formal analysis of these systems is particularly challenging due to the complexity of the perception DNNs, the sensors (cameras), and the environment conditions. We present a case study applying formal probabilistic analysis techniques to an experimental autonomous system that guides airplanes on taxiways using a perception DNN. We address the above challenges by replacing the camera and the network with a compact probabilistic abstraction built from the confusion matrices computed for the DNN on a representative image data set. We also show how to leverage local, DNN-specific analyses as run-time guards to increase the safety of the overall system. Our findings are applicable to other autonomous systems that use complex DNNs for perception.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-02-06T18:56:20.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "case study",
      "vision-based autonomous systems",
      "formal probabilistic analysis techniques",
      "closed-loop analysis",
      "applying formal probabilistic analysis"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}