{
  "id": "1903.03688",
  "version": "v1",
  "published": "2019-03-08T22:41:09.000Z",
  "updated": "2019-03-08T22:41:09.000Z",
  "title": "Training Classifiers For Feedback Control",
  "authors": [
    "Hasan A. Poonawala",
    "Niklas Lauffer",
    "Ufuk Topcu"
  ],
  "comment": "9 pages, conference",
  "categories": [
    "math.OC"
  ],
  "abstract": "One approach for feedback control using high dimensional and rich sensor measurements is to classify the measurement into one out of a finite set of situations, each situation corresponding to a (known) control action. This approach computes a control action without estimating the state. Such classifiers are typically learned from a finite amount of data using supervised machine learning algorithms. We model the closed-loop system resulting from control with feedback from classifier outputs as a piece-wise affine differential inclusion. We show how to train a linear classifier based on performance measures related to learning from data and the local stability properties of the resulting closed-loop system. The training method is based on the projected gradient descent algorithm. We demonstrate the advantage of training classifiers using control-theoretic properties on a case study involving navigation using range-based sensors.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-03-08T22:41:09.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "feedback control",
      "training classifiers",
      "control action",
      "closed-loop system",
      "projected gradient descent algorithm"
    ],
    "tags": [
      "conference paper"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 9,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}