Biography
Ioannis is an Associate Professor in Engineering Science at the Oxford Robotics Institute. His research combines dynamic whole-body motion planning and control with machine learning, focusing on robots with arms and legs.
He received his PhD (2011) and MSc with distinction (2007) from the University of Edinburgh, where he worked on machine learning for motion planning and control of articulated robots.
After his studies, he joined the Dynamic Legged Systems Lab at the Advanced Robotics Department of the Italian Institute of Technology, where he worked on a hydraulically-actuated, fully torque-controlled quadruped robot. There he led the Locomotion Group within the HyQ team, while his work focused on dynamic motion planning and control for legged locomotion.
He was a postdoctoral researcher at the Robot Learning & Interaction Group of the Indiap Research Institute, where he worked on learning complex skills from demonstration. His work there mainly focused on skill representation, online Bayesian nonparametric learning, Riemannian manifold methods and optimal control for motion generation.
Ioannis’ list of publications can be found here.
Most Recent Publications
Motion planning in dynamic environments using context-aware human trajectory prediction
Motion planning in dynamic environments using context-aware human trajectory prediction
BiConMP: a nonlinear model predictive control framework for whole body motion planning
BiConMP: a nonlinear model predictive control framework for whole body motion planning
You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example
You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example
Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent Space
Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent Space
Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion
Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion
Publications
2020
Motion Planning for Quadrupedal Locomotion: Coupled Planning, Terrain Mapping and Whole-Body Control, Carlos Mastalli, Ioannis Havoutis, Michele Focchi, D.G. Caldwell and C. Semini, IEEE Transactions on Robotics (T-RO), 2020. [video][pdf]
Guided Constrained Policy Optimization for Dynamic Quadrupedal Robot Locomotion, Siddhant Gangapurwala, Alexander Mitchell and Ioannis Havoutis, IEEE Robotics and Automation Letters (RA-L), 2020. [video][pdf]
GaitMesh: controller-aware navigation meshes for long-range legged locomotion planning in multi-layered environments, Martim Brandao, Omer Burak Aladag and Ioannis Havoutis, IEEE Robotics and Automation Letters (RA-L), 2020. [video][pdf]
Reliable Trajectories for Dynamic Quadrupeds using Analytical Costs and Learned Initializations, O. Melon, M. Geisert, D. Surovik, I. Havoutis and M. Fallon, IEEE International Conference on Robotics and Automation (ICRA), 2020. [video][pdf]
Learning sequences of approximations for hierarchical motion planning, Martim Brandao and Ioannis Havoutis, International Conference on Automated Planning and Scheduling (ICAPS), 2020. [pdf]
2019
Multi-controller multi-objective locomotion planning for legged robots, Martim Brandao, Maurice Fallon and Ioannis Havoutis, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019. [pdf]
Contact Planning for the ANYmal Quadruped Robot using an Acyclic Reachability-Based Planner, M. Geisert, T. Yates, A. Orgen, P. Fernbach and I. Havoutis, Towards Autonomous Robotic Systems Conference (TAROS), 2019. [pdf][ Frontiers in Robotics & AI Best Paper Award ]
2018
Learning from demonstration for semi-autonomous teleoperation, I. Havoutis and S. Calinon, Autonomous Robots, 2018. [pdf]
Programming by Demonstration for Shared Control with an Application in Teleoperation, M.J.A. Zeestraten, I. Havoutis and S. Calinon, IEEE Robotics and Automation Letters (RA-L), 2018. [pdf]
2017
Learning Task-Space Synergies using Riemannian Geometry, M.J.A. Zeestraten, I. Havoutis, S. Calinon and D.G. Caldwell, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017. [pdf]
Supervisory teleoperation with online learning and optimal control, I. Havoutis and S. Calinon, IEEE International Conference on Robotics and Automation (ICRA), 2017. [pdf]
An Approach for Imitation Learning on Riemannian Manifolds, M.J.A. Zeestraten, I. Havoutis, J. Silverio, S. Calinon and D.G. Caldwell, IEEE Robotics and Automation Letters (RA-L), 2017. [pdf]
Whole-body Trajectory Optimization for Non-periodic Dynamic Motions on Quadrupedal Systems, A. Radulescu, I. Havoutis, D.G. Caldwell and C. Semini, IEEE International Conference on Robotics and Automation (ICRA), 2017. [pdf]
Trajectory and Foothold Optimization using Low-Dimensional Models for Rough Terrain Locomotion, C. Mastalli, M. Focchi, I. Havoutis, A, Radulescu, S. Calinon, J. Buchli, D.G. Caldwell and C. Semini, IEEE International Conference on Robotics and Automation (ICRA), 2017. [pdf]
2016
Learning assistive teleoperation behaviors from demonstration, I. Havoutis and S. Calinon, IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR), 2016. [pdf]
Online Incremental Learning of Manipulation Tasks for Semi-Autonomous Teleoperation, I. Havoutis, A.K. Tanwani and S. Calinon, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Workshop on Closed-loop Grasping and Manipulation':' Challenges and Progress, 2016. [abstract][paper]
High-slope terrain locomotion for torque-controlled quadruped robots, M. Focchi, A. Del Prete, I. Havoutis, R. Featherstone, D.G. Caldwell and C. Semini, Autonomous Robots, 2016. [link][pdf]
Hierarchical Planning of Dynamic Movements without Scheduled Contact Sequences, C. Mastalli, I. Havoutis, M. Focchi, D.G. Caldwell and C. Semini, IEEE International Conference on Robotics and Automation (ICRA), 2016. [pdf]
Optimization for non-periodic dynamic motions of legged systems, A. Radulescu, I. Havoutis, D.G. Caldwell and C. Semini, International Workshop on Human-Friendly Robotics (HFR)., 2016. [pdf]
Preview Optimization for Learning Locomotion Policies on Rough Terrain, C. Mastalli, I. Havoutis, A. Radulescu, M. Focchi, D.G. Caldwell and C. Semini, Workshop on Dynamic Locomotion and Manipulation with Complex Robotic Systems in the Real World (DLMC), 2016. [pdf]
Dexterous Undersea Interventions with Far Distance Onshore Supervision: the DexROV Project, J. Gancet, P. Weiss, G. Antonelli, M.F. Pfingsthorn, S. Calinon, A. Turetta, C. Walen, D. Urbina, S. Govindaraj, P. Letier, X. Martinez, J. Salini, B. Chemisky, G. Indiveri, G. Casalino, P. Di Lillo, E. Simetti, D. De Palma, A. Birk, A. Tanwani, I. Havoutis, A. Caffaz and L. Guilpain, IFAC Conference on Control Applications in Marine Systems (CAMS), 2016. [pdf]
2015
Lidar-based navigation-level path planning for field-capable legged robots, I. Havoutis, D. Caldwell and C. Semini, International Conference on Climbing and Walking Robots (CLAWAR), 2015. [pdf]. [ CLAWAR 2015 Best Technical Paper Award ]
Planning and Execution of Dynamic Whole-Body Locomotion for a Hydraulic Quadruped on Challenging Terrain, A. W. Winkler, C. Mastalli, I. Havoutis, M. Focchi, D. Caldwell and C. Semini, IEEE International Conference on Robotics and Automation (ICRA), 2015. [pdf]
On-line and On-board Planning and Perception for Quadrupedal Locomotion, C. Mastalli, I. Havoutis, A. W. Winkler, D. G. Caldwell and C. Semini, IEEE International Conference on Technologies for Practical Robot Applications (TePRA 15), 2015. [pdf]
Pattern Generation and Compliant Feedback Control for Quadrupedal Dynamic Trot-Walking Locomotion: Experiments on RoboCat-1 and HyQ, B. Ugurlu, I. Havoutis, C. Semini, K. Kayamori, D. G. Caldwell, T. Narikiyo, Autonomous Robots, 2015. [link][pdf]
2014
Ground Reaction Forces Control for Torque-Controlled Quadruped Robots, M. Focchi, A. Del Prete, I. Havoutis, C. Semini, R. Featherstone and D. G. Caldwell, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), workshop on Whole-Body Control for Robots in the Real World, 2014. [pdf]
Optimization of dynamic motions for legged robots, I. Havoutis, J. Buchli, D. G. Caldwell and C. Semini, Dynamic Walking 2014, ETHz, Zurich, Switzerland, 2014. [poster][pdf]
Terrain mapping with a pan and tilt stereo camera for locomotion on a quadruped robot, S. Bazeille, M. Camurri, J. Ortiz, I. Havoutis, D. G. Caldwell and C. Semini, ICRA14 Workshop on Modeling, Estimation, Perception and Control of All Terrain Mobile Robots (WMEPC14), 2014. [pdf]
Path planning with force-based foothold adaptation and virtual model control for torque controlled quadruped robots, A. Winkler, I. Havoutis, S. Bazeille, J. Ortiz, M. Focchi, R. Dillmann, D. Caldwell and C. Semini, IEEE International Conference on Robotics and Automation (ICRA), 2014. [pdf]
Combining Active Compliance with Force-Feedback for on-the-fly Motion Replanning, A. W. Winkler, I. Havoutis and C. Semini, ICRA14 Workshop on Hydraulic Robots with Torque Control for Inverse Dynamics and Active Compliance, 2014. [pdf]
Quadruped robot trotting over irregular terrain assisted by stereo-vision, S. Bazeille, V. Barasuol, M. Focchi, I. Havoutis, M. Frigerio, J. Buchli, D. G. Caldwell and C. Semini, Journal of Intelligent Service Robotics, doi:10.1007/s11370-014-0147-9, Springer Berlin Heidelberg, 2014. [pdf][link]
2013
Motion Planning and Reactive Control on Learnt Skill Manifolds, I. Havoutis and S. Ramamoorthy, International Journal of Robotics Research (IJRR), 2013. [pdf, link]
A Compliant Control Architecture for the Hydraulic Quadruped - HyQ, I. Havoutis, A. Winkler and C.Semini, Workshop on New Applications of Hydraulic Actuation for Fast, Powerful, Efficient, Compact, and Compliant Robots, IROS 2013, Tokyo, Japan, 2013. [abstract][poster]
Virtual model control for quadrupedal trunk stabilization, I. Havoutis, C. Semini and D.G. Caldwell, Dynamic Walking 2013, Pittsburgh, Pennsylvania, USA, 2013. [pdf]
Onboard Perception-Based Trotting and Crawling with the Hydraulic Quadruped Robot (HyQ), I. Havoutis, J. Ortiz, S. Bazeille, V. Barasuol, C. Semini and D. G. Caldwell, In Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2013. [pdf]
Dynamic Trot-Walking with the Hydraulic Quadruped Robot - HyQ: Analytical Trajectory Generation and Active Compliance Control, B. Ugurlu, I. Havoutis, C. Semini and D. G. Caldwell, In Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2013. [pdf]
Inverse Dynamics for a Quadruped Robot Locomoting Along Slippery Surfaces, S. Zapolsky, E. Drumwright, I. Havoutis, J. Buchli and C. Semini, International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines (CLAWAR), 2013. [pdf]
Local Reflex Generation for Obstacle Negotiation in Quadrupedal Locomotion, M. Focchi, V. Barasuol, I. Havoutis, J. Buchli, C. Semini and D. G. Caldwell, International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines (CLAWAR), 2013. [pdf]
A comparison of Search-based Planners for a Legged Robot, M. A. Arain, I. Havoutis, C. Semini, J. Buchli and D. G. Caldwell, IEEE International Workshop on Robot Motion and Control (RoMoCo), 2013. [pdf]
Vision Enhanced Reactive Locomotion Control for Trotting on Rough Terrain, S. Bazeille, V. Barasuol, M. Focchi, I. Havoutis, M. Frigerio, J. Buchli, C. Semini and D. G. Caldwell, IEEE International Conference on Technologies for Practical Robot Applications (TePRA 13), 2013. [pdf]
Quadrupedal trotting with active compliance, I. Havoutis, C. Semini, J. Buchli and D.G. Caldwell, IEEE International Conference on Mechatronics (ICM), 2013. [pdf]
2012
Motion Generation with Geodesic Paths on Learnt Skill Manifolds, I. Havoutis and S. Ramamoorthy, In K. Mombaur and K. Berns (Eds.): Modeling, Simulation and Optimization of Bipedal Walking, Springer, 2012. [pdf]
Progress in quadrupedal trotting with active compliance, I. Havoutis, C. Semini, J. Buchli and D.G. Caldwell, Dynamic Walking 2012, Pensacola, Florida, USA, 2012. [pdf]
2011
Motion planning and reactive control on learnt skill manifolds, I. Havoutis, Ph.D. Thesis, School of Informatics, University of Edinburgh, 2011. [link]
Learnt skill manifolds for robot control, I. Havoutis and S. Ramamoorthy, International Workshop on Human-Friendly Robotics (HFR), 2011. [pdf]
2010
Constrained geodesic trajectory generation on learnt skill manifolds, I. Havoutis and S. Ramamoorthy, In Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2010. [pdf].
[ Finalist for IROS 2010 Best RoboCup Paper Award ]
Geodesic trajectory generation on learnt skill manifolds, I. Havoutis and S. Ramamoorthy, In Proc. IEEE International Conference on Robotics and Automation, 2010. [pdf]
Motion synthesis through randomized exploration on submanifolds in configuration space, I. Havoutis and S. Ramamoorthy, RoboCup 2009, J. Baltes et al. (Eds.), Lecture Notes in Artificial Intelligence, Volume 5949, pp. 92--103. Springer, Heidelberg, 2010. [pdf]
2009
Geodesic trajectory generation on learnt skill manifolds, I. Havoutis and S. Ramamoorthy, Workshop on Modeling, Simulation and Optimization of Bipedal Walking. Humanoids 09', Paris, France, 2009. [abstract] [poster]
Motion Synthesis on Learned Skill Manifolds, I. Havoutis and S. Ramamoorthy, RLSS 09'. Lisbon, Portugal, 2009. [poster]
2008
Synthesising Novel Movements through Latent Space Modulation of Scalable Control Policies, S. Bitzer, I. Havoutis and S. Vijayakumar, From Animals to Animats 10, pages 199--209, Springer, 2008. [link][pdf]
2007
Scalable Movement Representation In Low Dimensional Latent Space, I. Havoutis, MSc Thesis, University of Edinburgh, 2007. [pdf]
Most Recent Publications
Motion planning in dynamic environments using context-aware human trajectory prediction
Motion planning in dynamic environments using context-aware human trajectory prediction
BiConMP: a nonlinear model predictive control framework for whole body motion planning
BiConMP: a nonlinear model predictive control framework for whole body motion planning
You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example
You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example
Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent Space
Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent Space
Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion
Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion