Home » Teams » MLIA » Nicolas Perrin-Gilbert

  • Nicolas Perrin-Gilbert

  • Chargé de recherche CNRS
  • Équipe: MLIA
  • Bureau: 301
  • Email: nicolas.perrin@sorbonne-universite.fr
  • Addresse: ISIR, Campus Pierre et Marie Curie, 4 place Jussieu, BC173, 75005 Paris
  • Site web: https://perrin-isir.github.io/
  • Bio: Je suis roboticien et chercheur en apprentissage automatique. Je travaille comme chargé de recherche CNRS à l'ISIR depuis 2013.

    Liens: Github / DBLP / Google Scholar / Vidéos

Publications

  • Nicolas Perrin-Gilbert. Ingredients for Motion Planning-powered Reinforcement Learning. Computer Science [cs]. Sorbonne université, 2024. ⟨tel-04927374⟩
    [ HTTP | PDF ]
  • Nicolas Perrin-Gilbert. AFU: Actor-Free critic Updates in off-policy RL for continuous control. 2024. ⟨hal-04822857⟩
    [ HTTP ]
  • Alexandre Chenu, Olivier Serris, Olivier Sigaud, Nicolas Perrin-Gilbert. Single-Reset Divide & Conquer Imitation Learning. 2024. ⟨hal-04822877⟩
    [ HTTP ]
  • Emily Clement, Nicolas Perrin-Gilbert, Philipp Schlehuber-Caissier. Layered Controller Synthesis for Dynamic Multi-agent Systems. International Conference on Formal Modeling and Analysis of Timed Systems (FORMATS 2023), Sep 2023, Antwerp, Belgium. pp.50-68, ⟨10.1007/978-3-031-42626-1_4⟩. ⟨hal-04237998⟩
    [ HTTP ]
  • Valentin Macé, Raphaël Boige, Felix Chalumeau, Thomas Pierrot, Guillaume Richard, et al.. The Quality-Diversity Transformer: Generating Behavior-Conditioned Trajectories with Decision Transformers. GECCO '23: Genetic and Evolutionary Computation Conference, Jul 2023, Lisbon Portugal, France. pp.1221-1229, ⟨10.1145/3583131.3590433⟩. ⟨hal-04237993⟩
    [ HTTP ]
  • Olivier Sigaud, Gianluca Baldassarre, Cédric Colas, Stephane Doncieux, Richard Duro, et al.. A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents. 2024. ⟨hal-04810195⟩
    [ HTTP | PDF ]
  • Alexandre Chenu, Nicolas Perrin-Gilbert, Olivier Sigaud. Divide & Conquer Imitation Learning. 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), Oct 2022, Kyoto, Japan. pp.8630-8637, ⟨10.1109/IROS47612.2022.9982020⟩. ⟨hal-03753530⟩
    [ HTTP | PDF ]
  • Alexandre Chenu, Olivier Serris, Olivier Sigaud, Nicolas Perrin-Gilbert. Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration. 2022. ⟨hal-04823341⟩
    [ HTTP ]
  • Lin Dong, Nicolas Perrin, Florian Richer, Agnes Roby-Brami, Guillaume Morel. The stability investigation of variable viscosity control in the human‐robot interaction. The International Journal of Medical Robotics and Computer Assisted Surgery, 2022, 18 (5), ⟨10.1002/rcs.2416⟩. ⟨hal-03869394⟩
    [ HTTP ]
  • Felix Chalumeau, Thomas Pierrot, Valentin Macé, Arthur Flajolet, Karim Beguir, et al.. Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems. GECCO 2022 Workshop on Quality Diversity Algorithm Benchmarks, Jul 2022, Boston (MA), United States. ⟨hal-04237990⟩
    [ HTTP ]
  • Thomas Pierrot, Valentin Macé, Felix Chalumeau, Arthur Flajolet, Geoffrey Cideron, et al.. Diversity policy gradient for sample efficient quality-diversity optimization. GECCO '22: Genetic and Evolutionary Computation Conference, Jul 2022, Boston, United States. pp.1075-1083, ⟨10.1145/3512290.3528845⟩. ⟨hal-03864262⟩
    [ HTTP ]
  • Astrid Merckling, Nicolas Perrin-Gilbert, Alex Coninx, Stéphane Doncieux. Exploratory State Representation Learning. Frontiers in Robotics and AI, 2022, 9, pp.762051. ⟨10.3389/frobt.2022.762051⟩. ⟨hal-03864236⟩
    [ HTTP | PDF ]
  • Thomas Pierrot, Valentin Macé, Felix Chalumeau, Arthur Flajolet, Geoffrey Cideron, et al.. DIVERSITY POLICY GRADIENT FOR SAMPLE EFFI-CIENT QUALITY-DIVERSITY OPTIMIZATION. Workshop on Agent Learning in Open-Endedness (ALOE) at ICLR 2022, 2022, virtual, Vatican City. ⟨hal-03753541⟩
    [ HTTP | PDF ]
  • Alexandre Chenu, Nicolas Perrin-Gilbert, Stéphane Doncieux, Olivier Sigaud. Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms. 30th International Conference on Artificial Neural Networks - ICANN 2021, Sep 2021, Bratislava, Slovakia. pp.568-579, ⟨10.1007/978-3-030-86380-7_46⟩. ⟨hal-03404366⟩
    [ HTTP ]
  • Thomas Pierrot, Nicolas Perrin-Gilbert, Olivier Sigaud. First-Order and Second-Order Variants of the Gradient Descent in a Unified Framework. 30th International Conference on Artificial Neural Networks - ICANN 2021, Sep 2021, Bratislava, Slovakia. pp.197-208, ⟨10.1007/978-3-030-86340-1_16⟩. ⟨hal-03404369⟩
    [ HTTP ]
  • Alexandre Chenu, Nicolas Perrin-Gilbert, Stephane Doncieux, Olivier Sigaud. Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms. 2021. ⟨hal-03196479⟩
    [ HTTP | PDF ]
  • Thomas Pierrot, Nicolas Perrin, Feryal Behbahani, Alexandre Laterre, Olivier Sigaud, et al.. Learning Compositional Neural Programs for Continuous Control. 2020. ⟨hal-03083161⟩
    [ HTTP ]
  • Geoffrey Cideron, Thomas Pierrot, Nicolas Perrin, Karim Beguir, Olivier Sigaud. QD-RL: Efficient Mixing of Quality and Diversity in Reinforcement Learning. 2020. ⟨hal-03083159⟩
    [ HTTP ]
  • Astrid Merckling, Alexandre Coninx, Loic Cressot, Stephane Doncieux, Nicolas Perrin. State Representation Learning from Demonstration. 6th International Conference on Machine Learning, Optimization, and Data Science, LOD 2020, Jul 2020, Siena, Italy. ⟨hal-03083156⟩
    [ HTTP ]
  • Guillaume Matheron, Nicolas Perrin, Olivier Sigaud. Understanding Failures of Deterministic Actor-Critic with Continuous Action Spaces and Sparse Rewards. Artificial Neural Networks and Machine Learning – ICANN 2020, Sep 2020, Bratislava, Slovakia. pp.308-320, ⟨10.1007/978-3-030-61616-8_25⟩. ⟨hal-03080925⟩
    [ HTTP | PDF ]
  • Guillaume Matheron, Nicolas Perrin, Olivier Sigaud. PBCS: Efficient Exploration and Exploitation Using a Synergy Between Reinforcement Learning and Motion Planning. Artificial Neural Networks and Machine Learning – ICANN 2020, Sep 2020, Bratislava, Slovakia. pp.295-307, ⟨10.1007/978-3-030-61616-8_24⟩. ⟨hal-03080918⟩
    [ HTTP | PDF ]
  • Thomas Pierrot, Guillaume Ligner, Scott Reed, Olivier Sigaud, Nicolas Perrin, et al.. Learning Compositional Neural Programs with Recursive Tree Search and Planning. Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Dec 2019, Vancouver, Canada. ⟨hal-03080949⟩
    [ HTTP ]
  • Aloïs Pourchot, Nicolas Perrin, Olivier Sigaud. Importance mixing: Improving sample reuse in evolutionary policy search methods. 2019. ⟨hal-02397754⟩
    [ HTTP ]
  • Thomas Pierrot, Nicolas Perrin, Olivier Sigaud. First-order and second-order variants of the gradient descent in a unified framework. 2019. ⟨hal-02397757⟩
    [ HTTP ]
  • Zexiang Liu, Necmiye Ozay, Nicolas Perrin. Warm-Starting Fixed-Point Based Control Synthesis. [Research Report] University of Michigan-Ann Arbor; Cnrs; Sorbonne Université. 2018. ⟨hal-02397867⟩
    [ HTTP | PDF ]
  • Stéphane Doncieux, David Filliat, Natalia Díaz-Rodríguez, Timothy Hospedales, Richard Duro, et al.. Open-Ended Learning: A Conceptual Framework Based on Representational Redescription. Frontiers in Neurorobotics, 2018, 12, pp.59. ⟨10.3389/fnbot.2018.00059⟩. ⟨hal-01889947⟩
    [ HTTP | PDF ]
  • Philipp Schlehuber-Caissier, Nicolas Perrin. Computing regions of stabilizability for nonlinear control systems with input constraints. American Control Conference (ACC'18), 2018, Milwaukee, United States. pp.2869-2876, ⟨10.23919/ACC.2018.8430798⟩. ⟨hal-03135362⟩
    [ HTTP | PDF ]
  • Patricia Bouyer, Nicolas Markey, Nicolas Perrin, Philipp Schlehuber-Caissier. Timed-automata abstraction of switched dynamical systems using control invariants. Real-Time Systems, 2017, pp.1-27. ⟨10.1007/s11241-016-9262-3⟩. ⟨hal-01436413⟩
    [ HTTP | PDF ]
  • Nicolas Perrin. Biped Footstep Planning. Ambarish Goswami; Prahlad Vadakkepat. Humanoid Robotics: A Reference, Springer Netherlands, pp.1-21, 2017, 978-9400760455. ⟨10.1007/978-94-007-7194-9_29-1⟩. ⟨hal-03089498⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Christian Ott, Johannes Englsberger, Olivier Stasse, Florent Lamiraux, et al.. Continuous Legged Locomotion Planning. IEEE Transactions on Robotics, 2016, 33 (1), pp. 234-239. ⟨10.1109/TRO.2016.2623329⟩. ⟨hal-01433866⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Philipp Schlehuber-Caissier. Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems. Systems and Control Letters, 2016, 96, pp.51 - 59. ⟨10.1016/j.sysconle.2016.06.018⟩. ⟨hal-01394886⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Darwin Lau, Vincent Padois. Effective Generation of Dynamically Balanced Locomotion with Multiple Non-coplanar Contacts. International Symposium on Robotics Research, Sep 2015, Sestri Levante, Italy. ⟨hal-01388632⟩
    [ HTTP | PDF ]
  • Enrico Mingo Hoffman, Nicolas Perrin, Nikos Tsagarakis, Darwin Caldwell. Upper limb compliant strategy exploiting external physical constraints for humanoid fall avoidance. 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2013), Oct 2013, Atlanta, United States. pp.397-402, ⟨10.1109/HUMANOIDS.2013.7030005⟩. ⟨hal-03089494⟩
    [ HTTP | PDF ]
  • Patricia Bouyer, Nicolas Markey, Nicolas Perrin, Philipp Schlehuber-Caissier. Timed-Automata Abstraction of Switched Dynamical Systems Using Control Funnels. Formal Modeling and Analysis of Timed Systems, 9268, Springer International Publishing, pp.60 - 75, 2015, Lecture Notes in Computer Science, 978-3-319-22974-4. ⟨10.1007/978-3-319-22975-1_5⟩. ⟨hal-01395104⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Nikolaos Tsagarakis, Darwin Caldwell. Compliant attitude control and stepping strategy for balance recovery with the humanoid COMAN. 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), Nov 2013, Tokyo, Japan. pp.4145-4151, ⟨10.1109/IROS.2013.6696950⟩. ⟨hal-03089490⟩
    [ HTTP | PDF ]
  • Emmanouil Spyrakos-Papastavridis, Nicolas Perrin, Nikos G Tsagarakis, Jian S. Dai, Darwin G. Caldwell. Lyapunov Stability Margins for humanoid robot balancing. 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sep 2014, Chicago, IL, United States. ⟨10.1109/IROS.2014.6942673⟩. ⟨hal-01394903⟩
    [ HTTP | PDF ]
  • Luca Colasanto, Nicolas Perrin, Nikos G Tsagarakis, Darwin G Caldwell. Dynamically transitioning between surfaces of varying inclinations to achieve uneven-terrain walking. 2014 IEEE International Conference on Robotics and Automation (ICRA), May 2014, Hong Kong, China. pp.210 - 215, ⟨10.1109/ICRA.2014.6906611⟩. ⟨hal-01394896⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Christian Ott, Johannes Englsberger, Olivier Stasse, Florent Lamiraux, et al.. A Continuous Approach to Legged Locomotion Planning. 2013. ⟨hal-00805981⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Olivier Stasse, Florent Lamiraux, Eiichi Yoshida. Humanoid motion generation and swept volumes: theoretical bounds for safe steps. Advanced Robotics, 2013, 27 (14), pp.1045 - 1058. ⟨10.1080/01691864.2013.805468⟩. ⟨hal-01113510⟩
    [ HTTP | PDF ]
  • Nicolas Perrin. From Discrete to Continuous Motion Planning. Tenth Workshop on the Algorithmic Foundations of Robotics, Jun 2012, Cambridge, Massachusetts, United States. pp.89-104, ⟨10.1007/978-3-642-36279-8_6⟩. ⟨hal-03089485⟩
    [ HTTP | PDF ]
  • Andrei Herdt, Nicolas Perrin, Pierre-Brice Wieber. LMPC based online generation of more efficient walking motions. IEEE-RAS International Conference on Humanoid Robots (Humanoids), Nov 2012, Osaka, Japan. pp.390-395, ⟨10.1109/HUMANOIDS.2012.6651549⟩. ⟨hal-02487630⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Olivier Stasse, Florent Lamiraux, Youn J. Kim, Dinesh Manocha. Real-time footstep planning for humanoid robots among 3D obstacles using a hybrid bounding box. IEEE International Conference on Robotics and Automation, May 2012, Saint Paul, Minnesota, United States. pp.0-0. ⟨hal-00668794⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Olivier Stasse, Léo Baudouin, Florent Lamiraux, Eiichi Yoshida. Fast humanoid robot collision-free footstep planning using swept volume approximations. IEEE Transactions on Robotics, 2012, 28 (2), p.427-439. ⟨10.1109/TRO.2011.2172152⟩. ⟨hal-00662550⟩
    [ HTTP | PDF ]
  • Nicolas Perrin. Footstep planning for humanoid robots : discrete and continuous approaches. Other [cs.OH]. Institut National Polytechnique de Toulouse - INPT, 2011. English. ⟨NNT : 2011INPT0080⟩. ⟨tel-04241437v2⟩
    [ HTTP | PDF ]
  • Léo Baudouin, Nicolas Perrin, Thomas Moulard, Florent Lamiraux, Olivier Stasse, et al.. Real-time Replanning Using 3D Environment for Humanoid Robot. IEEE-RAS International Conference on Humanoid Robots (HUMANOIDS 2011), Oct 2011, Bled, Slovenia. p.584-589, ⟨10.1109/Humanoids.2011.6100844⟩. ⟨hal-00601300⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Olivier Stasse, Florent Lamiraux, Eiichi Yoshida. Weakly collision-free paths for continuous humanoid footstep planning. International Conference on Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ, Sep 2011, San Francisco, United States. pp.4408 -4413, ⟨10.1109/IROS.2011.6048120⟩. ⟨hal-00639026⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Olivier Stasse, Florent Lamiraux, Eiichi Yoshida. A Biped Walking Pattern Generator based on "Half-Steps" for Dimensionality Reduction. IEEE International Conference on Robotics and Automation (ICRA 2011), May 2011, Shanghai, China. ⟨10.1109/ICRA.2011.5979917⟩. ⟨hal-00593659⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Olivier Stasse, Florent Lamiraux, Eiichi Yoshida. Adaptive sampling-based approximation of the sign of multivariate real-valued functions. 2010. ⟨hal-00544891⟩
    [ HTTP | PDF ]
  • Nicolas Perrin, Olivier Stasse, Florent Lamiraux, Eiichi Yoshida. Approximation of Feasibility Tests for Reactive Walk on HRP-2. IEEE International Conference on Robotics and Automation, May 2010, Anchorage, United States. pp.1-6, ⟨10.1109/ROBOT.2010.5509395⟩. ⟨hal-00455454⟩
    [ HTTP | PDF ]
  • Andrei Herdt, Nicolas Perrin, Pierre-Brice Wieber. Walking without thinking about it. IROS 2010 - IEEE-RSJ International Conference on Intelligent Robots & Systems, Oct 2010, Taipei, Taiwan. pp.190-195, ⟨10.1109/IROS.2010.5654429⟩. ⟨inria-00567668⟩
    [ HTTP | PDF ]