Roi Yehoshua

PhD Candidate
Computer Science Department


E-mail: roiyeho@gmail.com
Office: Building 202, New Physics Building, 2nd Floor, Room 205, MAVERICK Lab
Tel: +972-3-531-7606
Address: Bar Ilan University, Ramat Gan 52900, Israel

I am currently a PhD candidate in the computer science department under the supervision of Prof. Gal Kaminka and Dr. Noa Agmon.
My research topic is in the field of adversarial coverage, working to solve the robotics coverage problem in environments where threats exist that might harm the robot or hinder its task.

Courses

Publications

  1. Roi Yehoshua and Noa Agmon. Multi-Robot Adversarial Coverage. In Proceedings of the 22nd European Conference on Artificial Intelligence (ECAI-16), 2016. (27% acceptance rate) [pdf]
  2. Roi Yehoshua and Noa Agmon. Robotic Adversarial Coverage: From Theory to Practice. In IJCAI Workshop on Autonomous Mobile Service Robots, 2016. [pdf]
  3. Roi Yehoshua, Noa Agmon, and Gal A. Kaminka. Robotic Adversarial Coverage of Known Environments. International Journal of Robotics Research, 2016. In press.
  4. Roi Yehoshua and Noa Agmon. Online Adversarial Coverage: Proofs. Technical Report SMART 2015/02, Bar Ilan University, Computer Science Department, SMART group, 2015. [pdf]
  5. Roi Yehoshua and Noa Agmon. Online Robotic Adversarial Coverage. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-15), 2015. [pdf]
  6. Roi Yehoshua, Noa Agmon, and Gal A. Kaminka. Frontier-Based RTDP: A New Approach to Solving the Robotic Adversarial Coverage Problem. In Proceedings of the 14th International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-15), 2015. (25% acceptance rate) [pdf]
  7. Roi Yehoshua and Noa Agmon. Adversarial Modeling in the Robotic Coverage Problem: Proofs and Algorithm Details. Technical Report SMART 2015/01, Bar Ilan University, Computer Science Department, SMART group, 2015. [pdf]
  8. Roi Yehoshua and Noa Agmon. Adversarial Modeling in the Robotic Coverage Problem. In Proceedings of the 14th International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-15), 2015. (25% acceptance rate) [pdf]
  9. Roi Yehoshua, Noa Agmon, and Gal A. Kaminka. Safest Path Adversarial Coverage: Proofs and Algorithm Details. Technical Report SMART 2014/01, Bar Ilan University, Computer Science Department, SMART group, 2014. [pdf]
  10. Roi Yehoshua, Noa Agmon, and Gal A. Kaminka. Safest Path Adversarial Coverage. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-14), 2014. [pdf]
  11. Roi Yehoshua, Noa Agmon, and Gal A. Kaminka. Towards Safest Path Adversarial Coverage (Extended Abstract). In Proceedings of the 13th International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-14), 2014. [pdf]
  12. Roi Yehoshua, Noa Agmon, and Gal A. Kaminka. Towards Efficient Robot Adversarial Coverage. In AAAI Workshop on Intelligent Robotic Systems, 2013. This is a slightly revised version of the IROS-2013 paper. [pdf]
  13. Roi Yehoshua, Noa Agmon, and Gal A. Kaminka. Robotic Adversarial Coverage: Introduction and Preliminary Results. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-13), 2013. [pdf]
  14. Roi Yehoshua, Mireille Avigal, and Ron Unger. Analysis of the effects of lifetime learning on population fitness using vose model. In Proceedings of the 12th annual conference on Genetic and evolutionary computation (GECCO-10), 2010. [pdf]

Research Goals

My primary research interest is in the application of machine learning models and techniques to robotics. This includes, in particular, the study of the theoretical aspects of machine learning, integrating learning capabilities into a robot control system, automated planning, modeling uncertain dynamic environments, modeling environments with adversarial presence, and coordination and learning in multi-robot systems.