Active Object Recognition via Monte Carlo Tree Search
Mikko Lauri, Nikolay A. Atanasov, George Pappas, Risto Ritala

Citation
Mikko Lauri, Nikolay A. Atanasov, George Pappas, Risto Ritala. "Active Object Recognition via Monte Carlo Tree Search". Workshop on Beyond Geometric Constraints at the International Conference on Robotics and Automation (ICRA), 2015.

Abstract
This paper considers object recognition with a camera, whose viewpoint can be controlled in order to improve the recognition results. The goal is to choose a multi-view camera trajectory in order to minimize the probability of having misclassified objects and incorrect orientation estimates. Instead of using offline dynamic programming, the resulting stochastic optimal control problem is addressed via an online Monte Carlo tree search algorithm, which can handle various constraints and provides exceptional performance in large state spaces. A key insight is to use an active hypothesis testing policy to select camera viewpoints during the rollout stage of the tree search.

Electronic downloads

Internal. This publication has been marked by the author for TerraSwarm-only distribution, so electronic downloads are not available without logging in.

Citation formats

• HTML

  Mikko Lauri, Nikolay A. Atanasov, George Pappas, Risto
  Ritala. <a
  href="http://www.terraswarm.org/pubs/549.html"
  >Active Object Recognition via Monte Carlo Tree
  Search</a>, Workshop on Beyond Geometric Constraints
  at the International Conference on Robotics and Automation
  (ICRA), 2015.

• Plain text

  Mikko Lauri, Nikolay A. Atanasov, George Pappas, Risto
  Ritala. "Active Object Recognition via Monte Carlo Tree
  Search". Workshop on Beyond Geometric Constraints at
  the International Conference on Robotics and Automation
  (ICRA), 2015.

• BibTeX

  @inproceedings{LauriAtanasovPappasRitala15_ActiveObjectRecognitionViaMonteCarloTreeSearch,
      author = {Mikko Lauri and Nikolay A. Atanasov and George
                Pappas and Risto Ritala},
      title = {Active Object Recognition via Monte Carlo Tree
                Search},
      booktitle = {Workshop on Beyond Geometric Constraints at the
                International Conference on Robotics and
                Automation (ICRA)},
      year = {2015},
      abstract = {This paper considers object recognition with a
                camera, whose viewpoint can be controlled in order
                to improve the recognition results. The goal is to
                choose a multi-view camera trajectory in order to
                minimize the probability of having misclassified
                objects and incorrect orientation estimates.
                Instead of using offline dynamic programming, the
                resulting stochastic optimal control problem is
                addressed via an online Monte Carlo tree search
                algorithm, which can handle various constraints
                and provides exceptional performance in large
                state spaces. A key insight is to use an active
                hypothesis testing policy to select camera
                viewpoints during the rollout stage of the tree
                search.},
      URL = {http://terraswarm.org/pubs/549.html}
  }
  

Posted by Nikolay A. Atanasov on 30 Apr 2015.
Groups: services