Stanford Robotics

Artificial Intelligence Laboratory - Stanford University

Mohammad Khansari



Mohammad Khansari

Contact

Mohammad Khansari
Artificial Intelligence Laboratory
Stanford University
Stanford, CA 94305-9010
USA

Gates Building, Room 122
Phone: +1 650 725-8810
Fax: +1 650 725-1449
E-mail: This e-mail address is being protected from spambots. You need JavaScript enabled to view it

  Personal Homepage


Research Interests

  • Robot Learning
  • Dynamical Systems
  • Optimal, Adaptive, and Impedance Controls
  • Modeling and Simulation
  • Motion Primitives¬†
Seyed Mohammad Khansari-Zadeh is a post-doctoral researcher at LASA laboratory at EPFL. He received his PhD (2012) in Robotics from EPFL, and his MSc (2008) in Dynamics and Control from Sharif University of Technology. His research interests include imitation learning for
robot control, dynamical systems, nonlinear control, and humanoids.

Projects

Workshops, Tutorials, and Organized Sessions

Theses

  • S.M. Khansari-Zadeh.
    A Dynamical System-based Approach to Modeling Stable Robot Control Policies via Imitation Learning.
    PhD thesis, École Polytechnique Fédérale de Lausanne, November 2012. BibTeX

    @phdthesis{KhansariThesis,
    	author = {S.M.~Khansari-Zadeh},
    	title = {{A} {D}ynamical {S}ystem-based {A}pproach to {M}odeling {S}table {R}obot {C}ontrol {P}olicies via {I}mitation {L}earning},
    	school = {École Polytechnique Fédérale de Lausanne},
    	year = {2012},
    	type = {PhD thesis},
    	month = {November},
    	doi = {10.5075/epfl-thesis-5552},
    	owner = {mohammad},
    	timestamp = {2013.01.08}
    }
    			

Journal Publications

  • S.M. Khansari-Zadeh and A. Billard.
    Learning Control Lyapunov Function to Ensure Stability of Dynamical System-based Robot Reaching Motions.
    Robotics and Autonomous Systems. Vol. 62, No. 6, pp. 752-765, 2014. BibTeX

    @article{Khansari_Billard_RAS2014,
    	author = {S.M.~Khansari-Zadeh and A.~Billard},
    	title = {Learning Control Lyapunov Function to Ensure Stability of Dynamical System-based Robot Reaching Motions},
    	journal = {Robotics and Autonomous Systems},
    	year = {2014},
    	volume = {62},
    	pages = {752--765},
    	number = {6},
    }
    			
  • S.M. Khansari-Zadeh and A. Billard.
    A dynamical system approach to realtime obstacle avoidance.
    Autonomous Robots. Vol. 32, pp. 433-454, 2012. BibTeX

    @article{Khansari_Billard_AR_12,
    	author = {S.M.~Khansari-Zadeh and A.~Billard},
    	title = {{A} dynamical system approach to realtime obstacle avoidance},
    	journal = {{A}utonomous {R}obots},
    	year = {2012},
    	volume = {32},
    	pages = {433--454},
    	file = {:C\:\\Mohammad\\PhD\\My Papers\\Journal_AR\\Khansari_Billard_AR.pdf:PDF},
    	issn = {0929-5593},
    	issue = {4},
    	owner = {Mohammad},
    	publisher = {Springer Netherlands},
    }
    			
  • S.M. Khansari-Zadeh, K. Kronander, and A. Billard.
    Learning to play minigolf: A dynamical system-based approach.
    Advanced Robotics. Vol. 26, No. 17, pp. 1967-1993, 2012. BibTeX

    @article{Khansari_Minigolf_AR2012,
    	author = {S.M.~Khansari-Zadeh and K.~Kronander and A.~Billard},
    	title = {{L}earning to play minigolf: {A} dynamical system-based approach},
    	journal = {{A}dvanced {R}obotics},
    	year = {2012},
    	volume = {26},
    	pages = {1967--1993},
    	number = {17},
    	doi = {10.1080/01691864.2012.728692},
    	owner = {Mohammad},
    }
    			
  • S.M. Khansari-Zadeh and A. Billard.
    Learning stable nonlinear dynamical systems with Gaussian mixture models.
    IEEE Trans. on Robotics. Vol. 27, No. 5, pp. 943-957, 2011. BibTeX

    @article{Khansari_Billard_TRO11,
    	author = {S.M.~Khansari-Zadeh and A.~Billard},
    	title = {{L}earning stable nonlinear dynamical systems with {G}aussian mixture models},
    	journal = {{IEEE} {T}rans. on {R}obotics},
    	year = {2011},
    	volume = {27},
    	pages = {943--957},
    	number = {5},
    	doi = {10.1109/TRO.2011.2159412},
    	issn = {1552-3098},
    	keywords = {Dynamical systems, Stability analysis, Imitation learning, Point-to-point motions, Gaussian Mixture Model},
    	owner = {Mohammad},
    }
    			
  • S.M. Khansari-Zadeh and F. Saghafi.
    Vision-Based Navigation in Autonomous Close Proximity Operations using Neural Networks.
    Aerospace and Electronic Systems, IEEE Transactions on. Vol. 47, No. 2, pp. 864-883, April 2011. BibTeX

    @article{Khansari_TAE11,
    	author = {S.M.~Khansari-Zadeh and F.~Saghafi},
    	title = {Vision-Based Navigation in Autonomous Close Proximity Operations using Neural Networks},
    	journal = {Aerospace and Electronic Systems, IEEE Transactions on},
    	year = {2011},
    	volume = {47},
    	pages = {864--883},
    	number = {2},
    	month = {april},
    	doi = {10.1109/TAES.2011.5751231},
    	issn = {0018-9251}
    }
    			
  • E. Gribovskaya, S.M. Khansari-Zadeh, and A. Billard.
    Learning Nonlinear Multivariate Dynamics of Motion in Robotic Manipulators.
    The International Journal of Robotics Research. Vol. 30, pp. 1-37, 2010. BibTeX

    @article{Gribovskaya_Khansari,
    	author = {E.~Gribovskaya and S.M.~Khansari-Zadeh and A.~Billard},
    	title = {{L}earning {N}onlinear {M}ultivariate {D}ynamics of {M}otion in {R}obotic {M}anipulators},
    	journal = {{T}he {I}nternational {J}ournal of {R}obotics {R}esearch},
    	year = {2010},
    	volume = {30},
    	pages = {1--37},
    	file = {:C\:\\Personal Files\\Mohammad\\PhD\\Literature Review\\Gribovskaya-Khansari_IJRR10.pdf:PDF},
    	owner = {Mohammad},
    }
    			
  • F. Saghafi, S.M. Khansari-Zadeh, and VEtiminanbakhsh.
    Aircraft Visual Identification by Neural Networks.
    International Journal of Aerospace Science and Technology (JAST). Vol. 5, No. 3, pp. 123-128, 2008. BibTeX

    @article{Khansari_JAST08,
    	author = {F.~Saghafi and S.M.~Khansari-Zadeh and V. Etiminanbakhsh},
    	title = {Aircraft Visual Identification by Neural Networks},
    	journal = {International Journal of Aerospace Science and Technology (JAST)},
    	year = {2008},
    	volume = {5},
    	pages = {123--128},
    	number = {3},
    	owner = {Mohammad},
    	timestamp = {2014.01.31}
    }
    			

Conference Publications

  • S.M. Khansari-Zadeh, K. Kronander, and A. Billard.
    Modeling robot discrete movements with state-varying stiffness and damping: A framework for integrated motion generation and impedance control.
    In Proc. of Robotics: Science and Systems X (RSS 2014), Berkeley, California, 2014. BibTeX

    @inproceedings{Khansari_RSS14,
    	author = {S.M.~Khansari-Zadeh and K.~Kronander and A.~Billard},
    	title = {Modeling robot discrete movements with state-varying stiffness and damping: A framework for integrated motion generation and impedance control},
    	booktitle = {{P}roc. of Robotics: Science and Systems X (RSS 2014)},
    	year = {2014},
    	address = {Berkeley, California},
    }
    			
  • K. Kronander, S.M. Khansari-Zadeh, and A. Billard.
    Learning to control planar hitting motions in a minigolf-like task.
    In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pp. 710-717, 2011. BibTeX

    @inproceedings{Kronander_IROS2011,
    	author = {K.~Kronander and S.M.~Khansari-Zadeh and A.~Billard},
    	title = {{L}earning to control planar hitting motions in a minigolf-like task},
    	booktitle = {{P}roc. of the {IEEE}/{RSJ} {I}nt. {C}onf. on {I}ntelligent {R}obots and {S}ystems ({IROS})},
    	year = {2011},
    	pages = {710--717},
    	owner = {Mohammad},
    }
    			
  • S.M. Khansari-Zadeh and A. Billard.
    Imitation learning of globally stable non-linear point-to-point robot motions using nonlinear programming.
    In Proc. of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pp. 2676-2683, 2010. BibTeX

    @inproceedings{Khansari_IROS10,
    	author = {S.M.~Khansari-Zadeh and A.~Billard},
    	title = {{I}mitation learning of globally stable non-linear point-to-point robot motions using nonlinear programming},
    	booktitle = {{P}roc. of the {IEEE}/{RSJ} {I}nt. {C}onf. on {I}ntelligent {R}obots and {S}ystems ({IROS})},
    	year = {2010},
    	pages = {2676--2683},
    	owner = {Mohammad},
    	timestamp = {2010.06.23}
    }
    			
  • S.M. Khansari-Zadeh and A. Billard.
    BM: An iterative algorithm to learn stable non-linear dynamical systems with Gaussian mixture models.
    In Proceeding of the International Conference on Robotics and Automation (ICRA), pp. 2381-2388, 2010. BibTeX

    @inproceedings{Khansari10,
    	author = {S.M.~Khansari-Zadeh and A.~Billard},
    	title = {{BM}: {A}n iterative algorithm to learn stable non-linear dynamical systems with {G}aussian mixture models},
    	booktitle = {{P}roceeding of the {I}nternational {C}onference on {R}obotics and {A}utomation ({ICRA})},
    	year = {2010},
    	pages = {2381--2388},
    	owner = {Mohammad},
    	timestamp = {2010.01.28}
    }
    			
  • F. Saghafi, SPouya, and S.M. Khansari-Zadeh.
    Intelligent Landing of Autonomous Aerial Vehicles Using Fuzzy Logic Control.
    In In Proceeding of IEEE Aerospace Conference, 2009. BibTeX

    @inproceedings{Pouya_IEEE09,
    	author = {F.~Saghafi and S. Pouya and S.M.~Khansari-Zadeh},
    	title = {Intelligent Landing of Autonomous Aerial Vehicles Using Fuzzy Logic Control},
    	booktitle = {In Proceeding of IEEE Aerospace Conference},
    	year = {2009},
    	owner = {Mohammad},
    	timestamp = {2014.01.31}
    }
    			
  • F. Saghafi and S.M. Khansari-Zadeh.
    Vision-Based Trajectory Tracking Controller for Autonomous Close Proximity Operations.
    In In Proceeding of IEEE Aerospace Conference, 2008. BibTeX

    @inproceedings{Khansari_IEEE08,
    	author = {F.~Saghafi and S.M.~Khansari-Zadeh},
    	title = {Vision-Based Trajectory Tracking Controller for Autonomous Close Proximity Operations},
    	booktitle = {In Proceeding of IEEE Aerospace Conference},
    	year = {2008},
    	owner = {Mohammad},
    	timestamp = {2014.01.31}
    }
    			

Conference Workshop Publications

  • K. Kronander, S.M. Khansari-Zadeh, and A. Billard.
    Incremental Motion Learning with Gaussian Process Modulated Dynamical Systems.
    Electronic proc. of the Workshop on Learning Plans with Context From Human Signals, RSS 2014, Berkley, 2014. BibTeX

    @misc{Kronander-RSS2014,
    	author = {K.~Kronander and S.M.~Khansari-Zadeh and A.~Billard},
    	title = {Incremental Motion Learning with Gaussian Process Modulated Dynamical Systems},
    	howpublished = {Electronic proc. of the Workshop on Learning Plans with Context From Human Signals, RSS 2014, Berkley},
    	year = {2014},
    	owner = {Mohammad},
    	timestamp = {2014.01.31}
    }
    			
  • S.M. Khansari-Zadeh and A. Billard.
    Realtime Avoidance of Fast Moving Objects: A Dynamical System-based Approach.
    Electronic proc. of the Workshop on Robot Motion Planning: Online, Reactive, and in Real-Time [IROS 2012], 2012. BibTeX

    @misc{Khansari2012_FastObsAvoidance,
    	author = {S.M.~Khansari-Zadeh and A.~Billard},
    	title = {Realtime Avoidance of Fast Moving Objects: A Dynamical System-based Approach},
    	howpublished = {Electronic proc. of the Workshop on Robot Motion Planning: Online, Reactive, and in Real-Time [IROS 2012]},
    	year = {2012},
    	abstract = {In this paper, we provide an extension to our previous approach (Khansari & Billard (2012), Autonomous Robots) to perform obstacle avoidance in the presence of multiple fast moving and rotating obstacles. Our approach leverage on the notion of DS to generate robot motions that are inherently robust to perturbations and can instantly adapt to changes in the target and obstacles' positions in a dynamically moving environments. We validate our method in the challenging experiment of dodging a fast moving and rotating box on the 7-degrees of freedom (DoF) KUKA DLR arm.},
    	owner = {Mohammad},
    	timestamp = {2014.01.31}
    }
    			
  • S.M. Khansari-Zadeh and A. Billard.
    Learning to Play Mini-Golf from Human Demonstration using Autonomous Dynamical Systems.
    Presented in International Conference on Machine Learning (ICML), 2011. BibTeX

    @misc{Khansari2011-ID837,
    	author = {S.M.~Khansari-Zadeh and A.~Billard},
    	title = {Learning to Play Mini-Golf from Human Demonstration using Autonomous Dynamical Systems},
    	howpublished = {Presented in International Conference on Machine Learning (ICML)},
    	year = {2011},
    	abstract = {We present a new formulation for autonomous (i.e. time-independent) Dynamical Systems (DS) to perform discrete robot motions with non-zero velocity at a given target. The proposed model ensures the convergence of all trajectories to the target, and is inherently robust to perturbations. We evaluated the performance of our proposed method to control right-handed swings in mini-golf.},
    	owner = {Mohammad},
    	timestamp = {2014.01.31}
    }
    			
  • S.M. Khansari-Zadeh and A. Billard.
    Learning and Control of UAV maneuvers Based on Demonstrations.
    Presented at Robotics Science and Systems (RSS), Seattle, 2009. BibTeX

    @misc{Khansari2009-ID792,
    	author = {S.M.~Khansari-Zadeh and A.~Billard},
    	title = {Learning and Control of UAV maneuvers Based on Demonstrations},
    	howpublished = {Presented at Robotics Science and Systems (RSS), Seattle},
    	year = {2009},
    	owner = {Mohammad},
    	timestamp = {2014.01.31}
    }
    			

Miscellaneous Publications

  • S.M. Khansari-Zadeh and A. Billard.
    The derivatives of the SEDS optimization cost function and constraints with respect to the learning parameters.
    Technical reportEcole Polytechnique Federale de Lausanne, 2010. BibTeX

    @techreport{SEDS_Derivative,
    	author = {S.M.~Khansari-Zadeh and A.~Billard},
    	title = {{T}he derivatives of the {SEDS} optimization cost function and constraints with respect to the learning parameters},
    	institution = {Ecole Polytechnique Federale de Lausanne},
    	year = {2010},
    	file = {:C\:\\Mohammad\\PhD\\My Papers\\Technical Reports\\SEDS_Derivatives\\SEDS_Derivatives.pdf:PDF},
    	owner = {Mohammad},
    	timestamp = {2011.04.11},
    	url = {http://lasa.epfl.ch/khansari}
    }