Summary
Dr Petar Kormushev is a Senior Lecturer (equiv. to Associate Professor) in Robotics at the Dyson School of Design Engineering. He is also the founder and director of the Robot Intelligence Lab at Imperial College London. He holds a PhD in Computational Intelligence from Tokyo Institute of Technology, an MSc in Artificial Intelligence, an MSc in Bio- and Medical Informatics, and a BSc in Computer Science. Dr Kormushev is also an Academic Fellow of the Data Science Institute.
Dr Kormushev's research interests include machine learning and robot learning algorithms, especially reinforcement learning for intelligent robot behavior. His long-term goal is to create autonomous robots that can learn by themselves and adapt to dynamic environments. You can find details about his Research and Publications, as well as watch Videos from his research experiments with robots.
PhD student openings are available on research topics related to robotics and machine learning. More information here:
Robot Intelligence Lab: http://www.imperial.ac.uk/robot-intelligence/
Personal website: http://kormushev.com
Photos
Videos
You can find all my research videos at:
http://www.youtube.com/user/PetarKormushev/videos
My participation in the DARPA Robotics Challenge finals in 2015 with the WALK-MAN robot
Online step replanning for a dynamically walking humanoid robot COMAN
Kinematic-free / Encoderless robot control of a Barrett WAM robot
Projects
Dr Kormushev has conducted research in robotics and machine learning within four FP7 European projects:
- WALK-MAN (Whole-body Adaptive Locomotion and Manipulation)
- PANDORA (Persistent Autonomy through learNing, aDaptation, Observation and Re-plAnning)
- STIFF-FLOP (STIFFness controllable Flexible and Learn-able Manipulator for surgical OPerations)
- AMARSI (Adaptive Modular Architectures for Rich Motor Skills)
During 2012-2015 he was a technical coordinator of two FP7 projects (PANDORA and STIFF-FLOP), and a co-chair of the IEEE RAS Technical Committee on Robot Learning. He has received a number of prestigious awards, including the 2013 John Atanasoff award from the President of Bulgaria. His PhD work was supported by a 4-year Japanese government research fellowship Monbukagakusho/MEXT.
Selected Publications
Journal Articles
Wang K, Fei H, Kormushev P, 2022, Fast online optimization for terrain-blind bipedal robot walking with a decoupled actuated SLIP model, Frontiers in Robotics and Ai, Vol:9, ISSN:2296-9144, Pages:1-11
AlAttar A, Chappell D, Kormushev P, 2022, Kinematic-model-free predictive control for robotic manipulator target reaching with obstacle avoidance, Frontiers in Robotics and Ai, Vol:9, ISSN:2296-9144, Pages:1-9
Cursi F, Bai W, Yeatman EM, et al. , 2022, GlobDesOpt: a global optimization framework for optimal robot manipulator design, Ieee Access, Vol:10, ISSN:2169-3536, Pages:5012-5023
Russell F, Takeda Y, Kormushev P, et al. , 2021, Stiffness modulation in a humanoid robotic leg and knee, Ieee Robotics and Automation Letters, Vol:6, ISSN:2377-3766, Pages:2563-2570
Cursi F, Modugno V, Lanari L, et al. , 2021, Bayesian neural network modeling and hierarchical MPC for a tendon-driven surgical robot with uncertainty minimization, Ieee Robotics and Automation Letters, Vol:6, ISSN:2377-3766, Pages:2642-2649
Saputra RP, Rakicevic N, Chappell D, et al. , 2021, Hierarchical decomposed-objective model predictive control for autonomous casualty extraction, Ieee Access, Vol:9, ISSN:2169-3536, Pages:39656-39679
Russell F, Kormushev P, Vaidyanathan R, et al. , 2020, The impact of ACL laxity on a bicondylar robotic knee and implications in human joint biomechanics, IEEE Transactions on Biomedical Engineering, Vol:67, ISSN:0018-9294, Pages:2817-2827
Kormushev P, Ugurlu B, Caldwell DG, et al. , 2019, Learning to exploit passive compliance for energy-efficient gait generation on a compliant humanoid, Autonomous Robots, Vol:43, ISSN:0929-5593, Pages:79-95
Conference
La Barbera V, Pardo F, Tassa Y, et al. , 2021, OstrichRL: a musculoskeletal ostrich simulation to study bio-mechanical locomotion, NeurIPS 2021
Tavakoli A, Fatemi M, Kormushev P, Learning to represent action values as a hypergraph on the action vertices, International Conference on Learning Representations, Vienna, Austria
Pardo F, Levdik V, Kormushev P, 2020, Scaling all-goals updates in reinforcement learning using convolutional neural networks, 34th AAAI Conference on Artificial Intelligence (AAAI 2020), Association for the Advancement of Artificial Intelligence, Pages:5355-5362, ISSN:2374-3468
Pardo F, Tavakoli A, Levdik V, et al. , 2018, Time limits in reinforcement learning, International Conference on Machine Learning, Pages:4042-4051
Kormushev P, Demiris Y, Caldwell DG, 2015, Kinematic-free Position Control of a 2-DOF Planar Robot Arm
Kryczka P, Kormushev P, Tsagarakis N, et al. , 2015, Online Regeneration of Bipedal Walking Gait Optimizing Footstep Placement and Timing
Kormushev P, Demiris Y, Caldwell DG, 2015, Encoderless Position Control of a Two-Link Robot Manipulator