Distributed Watchpoints: Debugging Large Multi-Robot Systems

@article{mderosa-ijrr-2008,
  author = {De~Rosa, Michael and Goldstein, Seth Copen and Lee, Peter
     and Campbell, Jason D. and Pillai, Padmanabhan},
  journal = {International Journal of Robotics Research},
  keywords = {Debugging, Distributed Systems},
  month = {March},
  url = {http://www.cs.cmu.edu/~claytronics/papers/mderosa-ijrr-2008.pdf},
  number = {3},
  title = {Distributed Watchpoints: Debugging Large Modular Robotic
     Systems},
  abstract = {Distributed systems frequently exhibit properties of
     interest which span multiple entities. These properties cannot
     easily be detected from any single entity, but can be readily be
     detected by combining the knowledge of multiple entities. Testing
     for distributed properties is especially important in debugging
     or verifying software for modular robots. We have developed a
     technique we call distributed watchpoint triggers which can
     efficiently recognize distributed conditions. Our watchpoint
     description language can handle a variety of temporal, spatial,
     and logical properties spanning multiple robots. This paper
     presents the specification language, describes the distributed
     online mechanism for detecting distributed conditions in a
     running system, and evaluates the performance of our
     implementation.},
  volume = {27},
  also = {Distributed Watchpoints: Debugging Large Multi-Robot
     Systems, (icra07)},
  year = {2008}
}

@inproceedings{derosa-icra07,
  abstract = {Tightly-coupled multi-agent systems such as modular
     robots frequently exhibit properties of interest that span
     multiple modules. These properties cannot easily be detected from
     any single module, though they might readily be detected by
     combining the knowledge of multiple modules. Testing for
     distributed conditions is especially important in debugging or
     verifying the correctness of software for modular robots. We have
     developed a technique we call distributed watchpoint triggers
     which can efficiently recognize such distributed conditions. Our
     watchpoint description language can handle a variety of temporal,
     spatial, and logical properties spanning multiple robots. This
     paper presents that language, describes our fully-distributed,
     online mechanism for detecting distributed conditions in a
     running system, and evaluates the performance of our
     implementation. We found that the performance of the system is
     highly dependent on the program being debugged, scales linearly
     with ensemble size, and is small enough to make the system
     practical in all but the worst case scenarios.},
  author = {De~Rosa, Michael and Goldstein, Seth Copen and Lee, Peter
     and Campbell, Jason D. and Pillai, Padmanabhan and Mowry, Todd
     C.},
  booktitle = {Proceedings of the IEEE International Conference on
     Robotics and Automation {ICRA '07}},
  title = {Distributed Watchpoints: Debugging Large Multi-Robot
     Systems},
  year = {2007},
  month = {April},
  keywords = {Debugging, Distributed Algorithms},
  url = {http://www.cs.cmu.edu/~claytronics/papers/derosa-icra07.pdf}
}

@inproceedings{derosa-rss06,
  author = {De~Rosa, Michael and Goldstein, Seth Copen and Lee, Peter
     and Campbell, Jason D. and Pillai, Padmanabhan},
  booktitle = {Robotics: Science and Systems Workshop on
     Self-Reconfigurable Modular Robots},
  title = {Distributed Watchpoints: Debugging Very Large Ensembles of
     Robots},
  month = {August},
  year = {2006},
  keywords = {Claytronics, Modular Robotics, Debugging, Distributed
     Systems},
  address = {Philadelphia, PA},
  url = {http://www.cs.cmu.edu/~seth/papers/derosa-rss06.pdf},
  abstract = {We describe a debugging tool for modular robotics that
     introduces the concept of distributed watchpoint triggers. This
     technique can initiate debugging actions (system halt, global
     snapshot, logging, etc.) in an ensemble of robots based on
     temporal, physical, and logical conditions distributed over
     multiple robots. Our technique is specifically designed to be
     effective in debugging modular robotic ensembles, where many
     important types of failure conditions can be detected within
     small, physically connected subsets of the total ensemble.}
}

@inproceedings{bacon-wpdd91,
  title = {Hardware-Assisted Replay of Multiprocessor Programs},
  url = {http://www.cs.cmu.edu/~seth/papers/bacon-wpdd91.pdf},
  booktitle = {Proceedings of the ACM/ONR Workshop on Parallel and
     Distributed Debugging},
  author = {Bacon, David F. and Goldstein, Seth Copen},
  year = {1991},
  address = {Santa Cruz, CA},
  month = {May},
  keywords = {Debugging,Parallel Computing}
}

@inproceedings{derosa-icra07,
  abstract = {Tightly-coupled multi-agent systems such as modular
     robots frequently exhibit properties of interest that span
     multiple modules. These properties cannot easily be detected from
     any single module, though they might readily be detected by
     combining the knowledge of multiple modules. Testing for
     distributed conditions is especially important in debugging or
     verifying the correctness of software for modular robots. We have
     developed a technique we call distributed watchpoint triggers
     which can efficiently recognize such distributed conditions. Our
     watchpoint description language can handle a variety of temporal,
     spatial, and logical properties spanning multiple robots. This
     paper presents that language, describes our fully-distributed,
     online mechanism for detecting distributed conditions in a
     running system, and evaluates the performance of our
     implementation. We found that the performance of the system is
     highly dependent on the program being debugged, scales linearly
     with ensemble size, and is small enough to make the system
     practical in all but the worst case scenarios.},
  author = {De~Rosa, Michael and Goldstein, Seth Copen and Lee, Peter
     and Campbell, Jason D. and Pillai, Padmanabhan and Mowry, Todd
     C.},
  booktitle = {Proceedings of the IEEE International Conference on
     Robotics and Automation {ICRA '07}},
  title = {Distributed Watchpoints: Debugging Large Multi-Robot
     Systems},
  year = {2007},
  month = {April},
  keywords = {Debugging, Distributed Algorithms},
  url = {http://www.cs.cmu.edu/~claytronics/papers/derosa-icra07.pdf}
}

@inproceedings{funiak-iros07,
  author = {Funiak, Stanislav and Pillai, Padmanabhan and Campbell,
     Jason D. and Goldstein, Seth Copen},
  title = {Internal Localization of Modular Robot Ensembles},
  booktitle = {Workshop on Self-Reconfiguring Modular Robotics at the
     IEEE International Conference on Intelligent Robots and Systems
     (IROS) '07},
  year = {2007},
  month = {October},
  abstract = {The determination of the relative position and pose of
     every robot in a modular robotic ensemble is a necessary
     preliminary step for most modular robotic tasks. Localization is
     particularly important when the modules make local noisy
     observations and are not significantly constrained by inter-robot
     latches. In this paper, we propose a robust hierarchical approach
     to the {\em internal localization} problem that uses normalized
     cut to identify subproblems with small localization error. A key
     component of our solution is a simple method to reduce the cost
     of normalized cut computations. The result is a robust algorithm
     that scales to large, non-homogeneous ensembles. We evaluate our
     algorithm in simulation on ensembles of up to 10,000 modules,
     demonstrating substantial improvements over prior work.},
  keywords = {Claytronics, Probabilistic Inference, Sensing,
     Localization, Distributed Algorithms},
  url = {http://www.cs.cmu.edu/~claytronics/papers/funiak-iros07.pdf}
}