Karim Bouyarmane, Ph.D.
カリム・ブヤルマン

(PhD) Docteur en Systèmes Automatiques de l'Université Montpellier 2
(MSc) Ingénieur de l'Ecole Polytechnique (X 2004)
(MSc) Ingénieur des Mines de Paris

[Update] I am on leave from my academic positions and I joined Amazon as an AI and ML scientist in Seattle, Washington
[Update] I have left Inria and Université de Lorraine in September 2018 for a full-time position as Associate Professor of Artificial Intelligence at Ecole Polytechnique, with research affiliation at LIX

Ecole Polytechnique, Department of Computer Science
Route de Saclay, 91128 Palaiseau Cedex, France

karim.bouyarmane [at] loria.fr / univ-lorraine.fr / polytechnique.edu
bouykari [at] amazon.com

Research

Keywords: Artificial Intelligence; Robotics; Reinforcement Learning; Intelligent Systems; Autonomous Robots; Automatic Control; Computer Graphics; Optimization; Machine Learning; Computational Neuroscience.

Selected lectures

• Deep Reinforcement Learning [Lecture 1 on Markov Decision Processes, Bellman Equation, Exact Methods with Dynamic Programming, Value Iteration, Policy Iteration, Q-Learning, Deep Q-Network] [Lecture 2 on Policy Gradient, Actor-Critic, Deep Policy and Value Network, Evolution Strategies, CMA-ES].
• Theoretical Foundations of Multi-Task QP control [Lecture on Vector Optimization, Multi-Objective Optimization, Hartley Theorem, Matrix Differentiation].
• Path Planning and Motion Planning [Lecture on Exact Methods, Cell Decomposition, Triangulation, Extended Voronoi Diagrams, C-spaces, Sampling-Based Methods, PRM, RRT, Best-First Search].
• Humanoid Robot Artificial Intelligence (in French, extended version of previous lecture) [Lecture].
• Multi-Agent Multi-Contact Planning [Lecture, includes Optimization on Deformable Models, Finite-Element Method].

Featured Videos

• DARPA Robotics Challenge [mp4].
• Multi-Contact Planner [mp4].
• QP Controller [mp4].
• Multi-Robot QP Controller [Physical Robots mp4] [Virtual Characters mp4].
• Motion Retargeting, Immersive Teleoperation [mp4].

Publications

Book Chapter

• K. Bouyarmane*, S. Caron, A. Escande, and A. Kheddar, "Multi-Contact Planning and Control", in Humanoid Robotics: a Reference, Springer, 2019. [SpringerLink] [pdf].

(*: Corresponding Author)

International Journals

• K. Bouyarmane*, K. Chappellet, J. Vaillant, and A. Kheddar, "Multi-Robot and Task-Space Force Control with Quadratic Programming," in IEEE Transactions on Robotics, vol. 35, no. 1, pp. 64-77, February 2019. [IEEE Xplore] [pdf] [mp4].
• K. Bouyarmane* and A. Kheddar, "Non-Decoupled Locomotion and Manipulation Planning for Low-Dimensional Systems," in the Journal of Intelligent & Robotic Systems, Springer, vol. 91, no. 3, pp. 377-401, September 2018. [SpringerLink] [pdf] [Springer Nature SharedIt (Springer Nature SharedIt Online Access)].
• K. Bouyarmane* and A. Kheddar, "On Weight-Pritoritized Multi-Task Control of Humanoid Robots," in IEEE Transactions on Automatic Control, vol. 63, no. 6, pp. 1632-1647, June 2018. [IEEE Xplore] [pdf].
• J. Vaillant, K. Bouyarmane* (corresponding author), and A. Kheddar, "Multi-Character Physical and Behavioral Interactions Controller," in IEEE Transactions on Visualization and Computer Graphics, vol. 23, no. 6, pp. 1650-1662, June 2017. [IEEE Xplore (Open Access)] [pdf] [mp4].
• J. Vaillant, A. Kheddar*, H. Audren, F. Keith, S. Brossette, A. Escande, K. Bouyarmane, K. Kaneko, M. Morisawa, P. Gergondet, E. Yoshida, S. Kajita, and F. Kanehiro, "Multi-Contact Vertical Ladder Climbing with a HRP-2 Humanoid," in Autonomous Robots, Springer, vol. 40, no. 3, pp. 561-580, March 2016. [SpringerLink] [pdf] [mp4(1)] [mp4(2)] [mp4(3)] [mp4(4)].
• K. Bouyarmane*, J. Vaillant, N. Sugimoto, F. Keith, J. Furukawa, and J. Morimoto, "Brain-Machine Interfacing Control of Whole-Body Humanoid Motion," in Frontiers in Systems Neuroscience, Special Issue on the Augmentation of Brain Function, vol. 8, no. 138, pp. 1-10, August 2014. [Frontiers (Open Access)] [pdf] [wmv].
• K. Bouyarmane* and A. Kheddar, "Humanoid Robot Locomotion and Manipulation Step Planning," in Advanced Robotics (the International Journal of the Robotics Society of Japan), Special Issue on the Cutting Edge of Robotics in Japan 2012 (2), vol. 26, no. 10, pp. 1099-1126, July 2012 (Recommended as Best Presentation from the RSJ 2010 conference). [Taylor and Francis Online] [pdf] [avi] [mpg].

International Conferences

• K. Otani*, K. Bouyarmane, and S. Ivaldi, "Generating Assistive Humanoid Motions for Co-Manipulation Tasks with a Multi-Robot Quadratic Program Controller", in Proceedings of the 2018 IEEE International Conference on Robotics and Automation, pp. 3107-3113, Brisbane, Australia, May 2018. [IEEE Xplore] [pdf] [mp4].
• V. Samy*, K. Bouyarmane, and A. Kheddar,"Analysis of a simple model for post-impact dynamics active compliance in humanoids falls with nonlinear optimization", in Proceedings of the 2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots, pp. 62-67, Brisbane, Australia, May 2018. [IEEE Xplore] [pdf] [mp4].
• J. Spitz*, K. Bouyarmane, S. Ivaldi, and J.-B. Mouret, "Trial-and-Error Learning of Repulsors for Humanoid QP-based Whole-Body Control," in Proceedings of the 2017 IEEE-RAS International Conference on Humanoid Robots, pp. 468-475, Birmingham, UK, November 2017. [IEEE Xplore] [pdf] [mp4].
• V. Samy*, S. Caron, K. Bouyarmane, and A. Kheddar, "Post-Impact Adaptive Compliance for Humanoid Falls using Predictive Control of a Reduced Model," in Proceedings of the 2017 IEEE-RAS International Conference on Humanoid Robots, pp. 655-660, Birmingham, UK, November 2017. [IEEE Xplore] [pdf] [mp4].
• K. Otani* and K. Bouyarmane, "Adaptive Whole-Body Manipulation in Human-to-Humanoid Multi-Contact Motion Retargeting," in Proceedings of the 2017 IEEE-RAS International Conference on Humanoid Robots, pp. 446-453, Birmingham, UK, November 2017. [IEEE Xplore] [pdf] [mp4].
• V. Samy*, K. Bouyarmane, and A. Kheddar, "QP-based Adaptive-Gains Compliance Control in Humanoid Falls," in Proceedings of the 2017 IEEE International Conference on Robotics and Automation, pp. 4762-4767, Singapore, 2017. [IEEE Xplore] [pdf] [mp4].
• A. Di Fava, K. Bouyarmane*, K. Chappellet, E. Ruffaldi, and A. Kheddar, "Multi-Contact Motion Retargeting from Human to Humanoid Robot," in Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, pp. 1081-1086, Cancun, Mexico, November 2016. [IEEE Xplore] [pdf] [mp4].
• K. Bouyarmane*, J. Vaillant, N. Sugimoto, F. Keith, J. Furukawa, and J. Morimoto, "BCI Control of Whole-Body Humanoid by Combining Motor Imagery Detection and Autonomous Motion Planning," in Springer Lecture Notes on Computer Science LNCS 8226, Minho Lee, Akira Hirose, Zeng-Guang Hou, Rhee Man Kil Editors, (Proceedings of the 2013 International Conference on Neural Information Processing), pp. 310-318, Daegu, Republic of Korea, November 2013. [SpringerLink] [pdf] [wmv].
• K. Bouyarmane*, J. Vaillant, and J. Morimoto, "Low-Dimensional User Control of Autonomously Planned Whole-Body Humanoid Locomotion Motion Towards Brain-Computer Interface Applications," in Nature-Inspired Mobile Robotics, Waldron, Tokhi, Virk Editors, (Proceedings of the 2013 IFToMM International Conference on Climbing and Walking Robots), pp. 740-748, Sydney, Australia, July 2013. [World Scientific] [pdf] [mp4] [wmv].
• K. Bouyarmane* and A. Kheddar, "On the Dynamics Modeling of Free-Floating-Base Articulated Mechanisms and Applications to Humanoid Whole-Body Dynamics and Control," in Proceedings of the 2012 IEEE-RAS International Conference on Humanoid Robots, pp. 36-42, Osaka, Japan, December 2012. [IEEE Xplore] [pdf] [mp4].
• K. Bouyarmane*, J. Vaillant, F. Keith, and A. Kheddar, "Exploring Humanoid Robot Locomotion Capabilities in Virtual Disaster Response Scenarios," in Proceedings of the 2012 IEEE-RAS International Conference on Humanoid Robots, pp. 337-342, Osaka, Japan, December 2012. [IEEE Xplore] [pdf] [mpg].
• K. Bouyarmane* and A. Kheddar, "FEM-based Static Posture Planning for a Humanoid Robot on Deformable Contact Support," in Proceedings of the 2011 IEEE-RAS International Conference on Humanoid Robots, pp. 487-492, Bled, Slovenia, October 2011. [IEEE Xplore] [pdf] [avi].
• K. Bouyarmane* and A. Kheddar, "Using a Multi-Objective Controller to Synthesize Simulated Humanoid Robot Motion with Changing Contact Configurations," in Proceedings of the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4414-4419, San Fransisco, CA, USA, September 2011. [IEEE Xplore] [pdf] [mp4] [wmv].
• K. Bouyarmane* and A. Kheddar, "Multi-Contact Stances Planning for Multiple Agents," in Proceedings of the 2011 IEEE International Conference on Robotics and Automation, pp. 5546-5353, Shanghai, China, May 2011. [IEEE Xplore] [pdf] [avi] [mpg].
• K. Bouyarmane* and A. Kheddar, "Static Multi-Contact Inverse Problem for Multiple Humanoid Robots and Manipulated Objects," in Proceedings of the 2010 IEEE-RAS International Conference on Humanoid Robots, pp. 8-13, Nashville, TN, USA, December 2010 (Best Paper Finalist Award). [IEEE Xplore] [pdf] [mp4].
• K. Bouyarmane*, A. Escande, F. Lamiraux, and A. Kheddar, "Potential Field Guide for Humanoid Multicontacts Acyclic Motion Planning," in Proceedings of the 2009 IEEE International Conference on Robotics and Automation, pp. 1165-1170, Kobe, Japan, May 2009. [IEEE Xplore] [pdf].

Japanese Domestic Conferences

• T. Moulard*, F. Lamiraux, K. Bouyarmane, and E. Yoshida, "Roboptim: an Optimization Framework for Robotics," in Proceedings of the 2013 JSME (Japan Society for Mechanical Engineers) Robotics and Mechatronics Conference, Tsukuba, Japan, May 2013. [pdf].
• K. Bouyarmane* and A. Kheddar, "Multi-Contacts Stances Planning for Humanoid Locomotion and Manipulation," in Proceedings of the 28th RSJ Annual Conference of the Robotics Society of Japan, Nagoya, Japan, September 2010 (Selected Among Best Presentations). [pdf].

International Competition

• DARPA Robotics Challenge (DRC) with the AIST-NEDO team, 2012-2015. [Comprehensive Wikipedia article on the DRC] [Finals, 5-6 June 2015, Fairplex, Pomona, CA] [Trials, 20-21 December 2013, Homestead-Miami Speedway, Miami, FL].
• AIST-NEDO team's HRP-2 KAI performance in day 2 of the finals [mp4].
• Final standings of the AIST-NEDO team in the finals: 10^th (out of 23 finalist teams).

PhD Thesis

• K. Bouyarmane, On Autonomous Humanoid Robots: Contact Planning for Locomotion and Manipulation (French title: De l'Autonomonie des Robots Humanoïdes : Planification de Contacts pour Mouvements de Locomotion et Tâches de Manipulation), University of Montpellier (ex Montpellier 2 University), Doctoral School I2S: Information, Structures, Systems, Speciality in Automatic and Microelectronic Systems, Montpellier, France, defended 22 November 2011. [pdf].
• Thesis Committee

Prof. B. Espiau	Inria (France)	Chair
Prof. J.-C. Latombe	Stanford University (USA)	Reviewer (Rapporteur)
Prof. J.-P. Laumond	CNRS (France)	Reviewer (Rapporteur)
Prof. A. Crosnier	Montpellier 2 Uni. (France)
Prof. H. Hirukawa	AIST (Japan)
Prof. A. Kheddar	CNRS/AIST (France/Japan)	Advisor

General Information

Bio

I graduated from Ecole Polytechnique (Palaiseau, France) in 2007 and from Ecole Nationale Supérieure des Mines de Paris in 2008 (double Ingénieur diploma in the French educational system). I obtained a University of Montpellier PhD in 2012, after spending my doctoral program for the full 4 years at AIST in Tsukuba, Japan, in the JRL lab. I subsequently held a 2-year JSPS postdoctoral fellowship position at ATR in Kyoto, Japan, and I worked during the following 2.5 years on the EU (European) FP7 project Koroibot and the the EU H2020 project COMANOID at the LIRMM lab in Montpellier, France, as a CNRS researcher. From 2016 to 2018, I held a full-time tenured Associate Professor at Université de Lorraine and Inria, with a part-time teaching position at Ecole Polytechnique. I joined Ecole Polytechnique full-time in the start of academic year 2018, before going on leave for an AI and ML scientist position at Amazon in Seattle, Washington, which is is my current position.

Curriculum Vitae