Email:
ondruska_at_robots.ox.ac.uk

Peter joined the group in 2012 as a DPhil student and is a member of St. Hilda’s College.

Peter has a strong background in algorithm design and his primary focus is on applications of Artificial Intelligence in robotics. His further research interests span areas as diverse as deep machine learning, inverse reinforcement learning, computer vision, planning and natural language processing.

Peter  has done internships in Facebook, Google, Microsoft Research and MetaMind. In his free time he does competitive ballroom dancing and enjoys participation in algorithmic programming competitions like TopCoder and Codeforces where he enjoys notable success.

Curriculum Vitae available here.




2017

  • [PDF] [DOI] M. Wulfmeier, D. Rao, D. Z. Wang, P. Ondruska, and I. Posner, “Large-scale cost function learning for path planning using deep inverse reinforcement learning.” in The International Journal of Robotics Research 2017, p. 278364917722396, DOI: 10.1177/0278364917722396 (link).
    [Bibtex]
    @Article{WulfmeierIJRR2017,
    author = {Markus Wulfmeier and Dushyant Rao and Dominic Zeng Wang and Peter Ondruska and Ingmar Posner},
    title = {Large-scale cost function learning for path planning using deep inverse reinforcement learning},
    journal = {The International Journal of Robotics Research},
    year = {2017},
    pages = {0278364917722396},
    doi = {10.1177/0278364917722396},
    pdf = {http://dx.doi.org/10.1177/0278364917722396},
    url = {http://dx.doi.org/10.1177/0278364917722396},
    }

2016

  • [PDF] J. Dequaire, D. Rao, P. Ondruska, D. Zeng Wang, and I. Posner, “Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks.” in ArXiv e-prints 2016, archive prefix: arXiv, ePrint: 1609.09365, cs.CV, keywords: “Computer Science – Computer Vision and Pattern Recognition, Computer Science – Artificial Intelligence, Computer Science – Learning, Computer Science – Robotics”.
    [Bibtex]
    @Article{DequaireArXivSeptember2016,
    author = {Dequaire, J. and Rao, D. and Ondruska, P. and Zeng Wang, D. and Posner, I.},
    title = {{Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks}},
    journal = {ArXiv e-prints},
    year = {2016},
    month = sep,
    archiveprefix = {arXiv},
    eprint = {1609.09365},
    pdf = {https://arxiv.org/abs/1609.09365},
    keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Learning, Computer Science - Robotics},
    primaryclass = {cs.CV},
    }
  • [PDF] P. Ondruska, J. Dequaire, D. Zeng Wang, and I. Posner, “End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks,” in Robotics: Science and Systems, Workshop on Limits and Potentials of Deep Learning in Robotics, 2016. Awarded “Best Workshop Paper”; see http://juxi.net/workshop/deep-learning-rss-2016/#papers
    [Bibtex]
    @InProceedings{OndruskaRSS2016,
    author = {Ondruska, Peter and Dequaire, Julie and Zeng Wang, Dominic and Posner, Ingmar},
    title = {{End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks}},
    booktitle = {Robotics: Science and Systems, Workshop on Limits and Potentials of Deep Learning in Robotics},
    year = {2016},
    month = June,
    award = {Best Workshop Paper},
    awardlink = {http://juxi.net/workshop/deep-learning-rss-2016/#papers},
    pdf = {http://www.robots.ox.ac.uk/~mobile/Papers/2016RSS_ondruska.pdf},
    }
  • [PDF] P. Ondruska, J. Dequaire, Zeng Wang Dominic, and I. Posner, “End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks.” in ArXiv e-prints 2016, archive prefix: arXiv, ePrint: 1604.05091, cs.LG, keywords: “Computer Science – Learning – Artificial Intelligence – Computer Vision and Pattern Recognition – Neural and Evolutionary Computing – Robotics”.
    [Bibtex]
    @Article{OndruskaArXivApril2016,
    author = {Ondruska, Peter and Dequaire, Julie and Zeng Wang, Dominic, and Posner, Ingmar},
    title = {{End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks}},
    journal = {ArXiv e-prints},
    year = {2016},
    month = apr,
    adsnote = {Provided by the SAO/NASA Astrophysics Data System},
    adsurl = {http://adsabs.harvard.edu/abs/2016arXiv160405091O},
    archiveprefix = {arXiv},
    eprint = {1604.05091},
    pdf = {http://arxiv.org/abs/1604.05091},
    keywords = {Computer Science - Learning - Artificial Intelligence - Computer Vision and Pattern Recognition - Neural and Evolutionary Computing - Robotics},
    primaryclass = {cs.LG},
    }
  • [PDF] P. Ondruska, “Neural Robotics – A New Perspective,” , Phoenix, Arizona USA, 2016, AAAI 2016 Robotics Fellowship.
    [Bibtex]
    @TechReport{OndruskaAAAI_RF_2016,
    author = {Peter Ondruska},
    title = {Neural Robotics - A New Perspective},
    institution = {AAAI 2016 Robotics Fellowship},
    year = {2016},
    address = {Phoenix, Arizona USA},
    month = {February},
    pdf = {http://www.robots.ox.ac.uk/~mobile/Papers/2016AAAI_RF_ondruska.pdf},
    }
  • [PDF] P. Ondruska and I. Posner, “Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks,” in The Thirtieth AAAI Conference on Artificial Intelligence (AAAI), Phoenix, Arizona USA, 2016.
    [Bibtex]
    @InProceedings{OndruskaAAAI2016,
    author = {Peter Ondruska and Ingmar Posner},
    title = {Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks},
    booktitle = {The Thirtieth AAAI Conference on Artificial Intelligence (AAAI)},
    year = {2016},
    address = {Phoenix, Arizona USA},
    month = {February},
    pdf = {http://www.robots.ox.ac.uk/~mobile/Papers/2016AAAI_ondruska.pdf},
    github = {https://github.com/pondruska/DeepTracking},
    }

2015

  • [PDF] M. Wulfmeier, P. Ondruska, and I. Posner, “Maximum Entropy Deep Inverse Reinforcement Learning,” in Neural Information Processing Systems Conference, Deep Reinforcement Learning Workshopin CoRR, Montreal, Canada, 2015, vol. abs/1507.04888.
    [Bibtex]
    @InProceedings{2015deepIRL,
    author = {Markus Wulfmeier and Peter Ondruska and Ingmar Posner},
    title = {Maximum Entropy Deep Inverse Reinforcement Learning},
    booktitle = {Neural Information Processing Systems Conference, Deep Reinforcement Learning Workshop},
    year = {2015},
    volume = {abs/1507.04888},
    address = {Montreal, Canada},
    bibsource = {dblp computer science bibliography, http://dblp.org},
    biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/WulfmeierOP15},
    pdf = {http://www.robots.ox.ac.uk/~mobile/Papers/DeepIRL_2015.pdf},
    journal = {CoRR},
    timestamp = {Sun, 02 Aug 2015 18:42:02 +0200},
    }
  • [PDF] P. Ondruska, P. Kohli, and S. Izadi, “MobileFusion: Real-time Volumetric Surface Reconstruction and Dense Tracking On Mobile Phones,” in International Symposium on Mixed and Augmented Reality (ISMAR), Fukuoka, Japan, 2015.
    [Bibtex]
    @InProceedings{OndruskaISMAR2015,
    author = {Peter Ondruska and Pushmeet Kohli and Shahram Izadi},
    title = {MobileFusion: Real-time Volumetric Surface Reconstruction and Dense Tracking On Mobile Phones},
    booktitle = {International Symposium on Mixed and Augmented Reality (ISMAR)},
    year = {2015},
    address = {Fukuoka, Japan},
    month = {October},
    pdf = {http://www.robots.ox.ac.uk/~mobile/Papers/2015ISMAR_ondruska.pdf},
    }
  • [PDF] A. Kumar, O. Irsoy, J. Su, J. Bradbury, R. English, B. Pierce, P. Ondruska, I. Gulrajani, and R. Socher, “Ask Me Anything: Dynamic Memory Networks for Natural Language Processing.” in arXiv 2015.
    [Bibtex]
    @Article{KumarISBEPOGS15,
    author = {Ankit Kumar and Ozan Irsoy and Jonathan Su and James Bradbury and Robert English and Brian Pierce and Peter Ondruska and Ishaan Gulrajani and Richard Socher},
    title = {Ask Me Anything: Dynamic Memory Networks for Natural Language Processing},
    journal = {arXiv},
    year = {2015},
    month = {July},
    pdf = {http://arxiv.org/abs/1506.07285},
    }
  • [PDF] P. Ondruska, C. Gurau, L. Marchegiani, C. H. Tong, and I. Posner, “Scheduled Perception for Energy-Efficient Path Following,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Seattle, WA, USA, 2015.
    [Bibtex]
    @InProceedings{OndruskaICRA2015,
    author = {Peter Ondruska and Corina Gurau and Letizia Marchegiani and Chi Hay Tong and Ingmar Posner},
    title = {Scheduled Perception for Energy-Efficient Path Following},
    booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)},
    year = {2015},
    address = {Seattle, WA, USA},
    month = {May},
    pdf = {http://www.robots.ox.ac.uk/~mobile/Papers/2015ICRA_ondruska.pdf},
    }

2014

  • [PDF] P. Ondruska and I. Posner, “The Route Not Taken: Driver-Centric Estimation of Electric Vehicle Range,” in Proceedings of the 24th International Conference on Automated Planning and Scheduling (ICAPS), Portsmouth, NH, USA, 2014.
    [Bibtex]
    @InProceedings{OndruskaICAPS2014,
    author = {Peter Ondruska and Ingmar Posner},
    title = {The Route Not Taken: Driver-Centric Estimation of Electric Vehicle Range},
    booktitle = {Proceedings of the 24th International Conference on Automated Planning and Scheduling (ICAPS)},
    year = {2014},
    address = {Portsmouth, NH, USA},
    month = {June},
    pdf = {http://www.robots.ox.ac.uk/~mobile/Papers/2014ICAPS_ondruska.pdf},
    }
  • [PDF] P. Ondruska and I. Posner, “Probabilistic Attainability Maps: Efficiently Predicting Driver-Specific Electric Vehicle Range,” in IEEE Intelligent Vehicles Symposium (IV), Dearborn, MI, USA, 2014.
    [Bibtex]
    @InProceedings{OndruskaIVS2014,
    author = {Peter Ondruska and Ingmar Posner},
    title = {Probabilistic Attainability Maps: Efficiently Predicting Driver-Specific Electric Vehicle Range},
    booktitle = {IEEE Intelligent Vehicles Symposium (IV)},
    year = {2014},
    address = {Dearborn, MI, USA},
    month = {June},
    pdf = {http://www.robots.ox.ac.uk/~mobile/Papers/2014IVS_ondruska.pdf},
    }