Citation
Dorsa Sadigh, Katherine Driggs Campbell, Alberto Puggelli, Wenchao Li, Victor Shia, Ruzena Bajcsy, Alberto L. Sangiovanni-Vincentelli, Shankar Sastry, Sanjit Seshia. "Data-Driven Probabilistic Modeling and Verification of Human Driver Behavior". AAAI Spring Symposium on Formal Verification and Modeling in Human-Machine Systems, 2014.

Abstract
We address the problem of formally verifying quantitative properties of driver models.We first propose a novel stochastic model of the driver behavior based on Convex Markov Chains, i.e., Markov chains in which the transition probabilities are only known to lie in convex uncertainty sets. This formalism captures the intrinsic uncertainty in estimating transition probabilities starting from experimentally-collected data. We then formally verify properties of the model expressed in probabilistic computation tree logic (PCTL). Results show that our approach can correctly predict quantitative information about driver behavior depending on her state, e.g., whether he or she is attentive or distracted.

Electronic downloads

• EECS-2013-197.pdf · application/pdf · 470 kbytes

• HTML

  Dorsa Sadigh, Katherine Driggs Campbell, Alberto Puggelli,
  Wenchao Li, Victor Shia, Ruzena Bajcsy, Alberto L.
  Sangiovanni-Vincentelli, Shankar Sastry, Sanjit Seshia.
  <a
  href="http://robotics.eecs.berkeley.edu/pubs/6.html"
  >Data-Driven Probabilistic Modeling and Verification of
  Human Driver Behavior</a>, AAAI Spring Symposium on
  Formal Verification and Modeling in Human-Machine Systems,
  2014.

• Plain text

  Dorsa Sadigh, Katherine Driggs Campbell, Alberto Puggelli,
  Wenchao Li, Victor Shia, Ruzena Bajcsy, Alberto L.
  Sangiovanni-Vincentelli, Shankar Sastry, Sanjit Seshia.
  "Data-Driven Probabilistic Modeling and Verification of
  Human Driver Behavior". AAAI Spring Symposium on Formal
  Verification and Modeling in Human-Machine Systems, 2014.

• BibTeX

  @inproceedings{SadighDriggsCampbellPuggelliLiShiaBajcsySangiovanniVincentelli14_DataDrivenProbabilisticModelingVerificationOfHumanDriver,
      author = {Dorsa Sadigh and Katherine Driggs Campbell and
                Alberto Puggelli and Wenchao Li and Victor Shia
                and Ruzena Bajcsy and Alberto L.
                Sangiovanni-Vincentelli and Shankar Sastry and
                Sanjit Seshia},
      title = {Data-Driven Probabilistic Modeling and
                Verification of Human Driver Behavior},
      booktitle = {AAAI Spring Symposium on Formal Verification and
                Modeling in Human-Machine Systems},
      year = {2014},
      abstract = {We address the problem of formally verifying
                quantitative properties of driver models.We first
                propose a novel stochastic model of the driver
                behavior based on Convex Markov Chains, i.e.,
                Markov chains in which the transition
                probabilities are only known to lie in convex
                uncertainty sets. This formalism captures the
                intrinsic uncertainty in estimating transition
                probabilities starting from
                experimentally-collected data. We then formally
                verify properties of the model expressed in
                probabilistic computation tree logic (PCTL).
                Results show that our approach can correctly
                predict quantitative information about driver
                behavior depending on her state, e.g., whether he
                or she is attentive or distracted.},
      URL = {http://robotics.eecs.berkeley.edu/pubs/6.html}
  }
  

Posted by Ehsan Elhamifar on 16 May 2014.
Groups: ehumans
For additional information, see the Publications FAQ or contact webmaster at robotics eecs berkeley edu.