– – – – – – – – –


About me

Petar Kormushev

My name is Petar Kormushev. I am a Research Team Leader (equivalent to Assistant Professor) at the Advanced Robotics department of the Italian Institute of Technology (IIT), Genoa. I am also a Visiting Senior Research Fellow at King’s College London, UK.

I do research in robotics and machine learning. My research focus is on reinforcement learning algorithms and their application to autonomous robots. You can see details about my Research and Publications, as well as watch Videos from my research experiments with robots.

At IIT, I am a team leader at the Learning and Interaction group of the Advanced Robotics department. We develop machine learning algorithms and apply them to robots like the compliant humanoid robot COMAN, the iCub humanoid robot, the Barrett WAM arm manipulator robot, and the Fujitsu HOAP-2 small humanoid robot. This is my page at IIT.

In 2009 I obtained my PhD degree from Tokyo Institute of Technology, where I was doing research in computational intelligence under the supervision of Prof. Kaoru Hirota. My PhD thesis was dedicated to methods for speeding up the reinforcement learning process. I was also supervised by Visiting Prof. Kohei Nomoto from Mitsubishi Electric Corp. and Visiting Prof. Shigeaki Sakurai from Toshiba Corp.

I have had the chance to collaborate with many excellent researchers in robotics and machine learning, including Dr. Sylvain Calinon and Dr. Nikos Tsagarakis from IIT, Prof. Dragomir N. Nenchev from Tokyo City University, Assoc. Prof. Gennady Agre from Bulgarian Academy of Sciences, and Dr. Barkan Ugurlu from Toyota Technological Institute. I am deeply grateful to my university lecturer Assoc. Prof. Maria Nisheva, for inspiring me to pursue studies in artificial intelligence.

In addition to my scientific research, I have more than 7 years of working experience. In 2008, I worked at Google Japan for 3 months as a software engineer in the Search Quality team. I created a prototype of a new search query categorization system (which I called Google Genus) using machine learning algorithms.

In 2005, I received my MSc degree in Artificial Intelligence from Sofia University, at the Faculty of Mathematics and Informatics. In 2006, shortly before going to Japan, I successfully defended my second MSc degree in Bio- and Medical Informatics. My long-term goal is to combine knowledge from different scientific fields in order to achieve synergetic effect and be able to tackle very complex problems.

Thanks for visiting my website, I wish you pleasant surfing!

— Petar

Open positions in my team

PhD positions in Robotics and Machine Learning for 2015 (deadline passed)
PhD positions in Robotics and Machine Learning for 2014 (deadline passed)
Post-doc position in Machine Learning for Robotics, May 2013 (deadline passed)
Post-Doc positions in Robotics at IIT for 2012 (deadline passed)
PhD positions in Robotics at IIT for 2012 (deadline passed)

Visiting Researcher at KCL

Since August 2014 I am a Visiting Senior Research Fellow at KCL (King’s College London). I am working with the groups of Prof. Kaspar Althoefer and Prof. Maria Fox.
We are also collaborating on two EU FP7 projects (PANDORA and STIFF-FLOP) on the topics of persistent autonomy for underwater vehicles and learning for robot-assisted surgery.


Special Issue on Humanoid Robotics

I am co-editing a special Issue on Humanoid Robotics for the Advanced Robotics journal of RSJ. The submission deadline for papers is:   April 14, 2014

More information about this special issue

With the President of Bulgaria, Mr. Rosen Plevneliev

With the President of Bulgaria, Mr. Rosen Plevneliev

I received the 2013 John Atanasoff award by the President of Bulgaria!


“John Atanasoff” Award, 2013
Awarded by the President of Bulgaria for scientific excellence and contributions to the development of Information and Communications Technologies (ICT) in Bulgaria and abroad. The award bears the name of Prof. John Atanasoff (who is of Bulgarian descent) – the inventor of the first electronic digital computer.

More info here


In 2012, I was appointed as a co-chair of the prestigious IEEE RAS Technical Committee on Robot Learning!

“After three very successful years for the Technical Committee on Robot Learning, the founding chairs Jan Peters, Jun Morimoto, Russ Tedrake and Nicholas Roy are stepping down as chairs of the committee. They will be replaced by Petar Kormushev, Edwin Olson, Ashutosh Saxena, and Wataru Takano who have kindly agreed to take the reigns of the committee.”

WAM_visuospatial_skill_learning_150px [Oct, 2013] “Visuospatial skill learning” – a novel approach for robot learning by demonstration (visual imitation learning).
[Aug, 2011] We presented our pizza-making robot at the Robotic Challenge event of AAAI’2011 in San Francisco!

See more info and photos here.

[Mar, 2011] New conference paper was accepted to IROS 2011!Kormushev, P., Ugurlu, B., Calinon, S., Tsagarakis, N., and Caldwell, D.G., “Bipedal Walking Energy Minimization by Reinforcement Learning”, IROS 2011.
Robot learns to clean a whiteboard [Aug, 2010] My new research experiment: Robot learns to clean a whiteboard! A free-standing Fujitsu HOAP-2 humanoid robot learns to clean a surface by upper-body kinesthetic teaching.
Publication: P. Kormushev, D. Nenchev, S. Calinon, D. Caldwell, Upper-body Kinesthetic Teaching of a Free-standing Humanoid Robot, IEEE Intl. Conf. on Robotics and Automation (ICRA 2011), 2011.
Haptic input used to demonstrate force profile of a task [Nov, 2010] New journal paper! Kormushev, P., Calinon, S., and Caldwell, D.G., “Imitation learning of positional and force skills demonstrated via kinesthetic teaching and haptic input”, Advanced Robotics, 2011.
Demonstrating the ironing task [Nov, 2010] New conference workshop paper!
Kormushev, P., Calinon, S., and Caldwell, D.G., “Approaches for Learning Human-like Motor Skills which Require Variable Stiffness During Execution”, Workshop on Humanoid Robots Learning from Human Interaction (Humanoids 2010), 2010.
Robot archer [May, 2010] My new research experiment: Robot archer! An iCub humanoid robot learns the skill of archery: it learns to aim and shoot arrows at the center of the target. Check it in the Videos section.

The paper publication: “Learning the skill of archery by a humanoid robot iCub”, IEEE Intl. Conf. on Humanoid Robots (Humanoids 2010), pp. 417-423, 2010.

Pancake flipping robot [Jan, 2010] My new research experiment: Pancake flipping robot! A Barrett WAM robot learns how to flip pancakes by itself, trying to imitate a demonstration done by a human teacher.

Watch it in the Videos section.




PhD positions in Robotics and Machine Learning for 2015

University of Genoa, jointly with the Italian Institute of Technology (IIT)
PhD Program in Bioengineering and Robotics
Call for PhD students for 2015

PhD positions with scholarships are available at the Italian Institute of Technology (IIT)
Location: Genoa, Italy
Starting date: November 2014
Application deadline: August 22, 2014 at 12:00 noon (Italian time/CET)

Please note that IIT is an English-language research institute, so it is not required to speak Italian.
Useful links:

I have two PhD positions open in my team, in Themes 21 and 22 respectively. Both are in the area of Robot Learning, as described below. For anyone interested, please contact me well before the application deadline!



THEME 21. Robot Learning of Motor Skills

Tutors: Dr. Petar Kormushev, Prof. Darwin G. Caldwell

pancake subclip - finally learned skill

Description: Despite the significant mechatronic advances in robot design, the motor skill repertoire of current robots is mediocre compared to their biological counterparts. Motor skills of humans and animals are still utterly astonishing when compared to robots. This PhD theme will focus on machine learning methods to advance the state-of-the-art in robot learning of motor skills. The type of motor skills that will be investigated include object manipulation, compliant interaction with objects, humans and the environment, force control and vision as part of the robot learning architecture.

The creation of novel, high-performance, passively-compliant humanoid robots (such as the robot COMAN developed at IIT) offers a significant potential for achieving such advances in motor skills. However, as the bottleneck is not the hardware anymore, the main efforts should be directed towards the software that controls the robot. It is no longer reasonable to use over-simplified models of robot dynamics, because the novel compliant robots possess much richer and more complex dynamics than the previous generation of stiff robots. Therefore, new solutions should be sought to address the challenge of compliant robot control.

Ideas from developmental robotics will be considered, in search for a qualitatively better approach for controlling robots, different than the currently predominant approach based on manually-engineered controllers.
The work within this PhD theme will include developing novel robot learning algorithms and methods that allow humanoid robots to easily learn new skills. At the same time, the methods should allow for natural and safe interaction with people. To this end, the research will include learning by imitation and reinforcement learning, as well as human-robot interaction.



THEME 22. Robot Learning for Agile Locomotion

Tutors: Dr. Petar Kormushev, Dr. Nikos Tsagarakis


Description: The state-of-the-art high-performance, passively-compliant humanoid robots (such as the robot COMAN developed by IIT) offer a significant potential for achieving more agile robot locomotion. At this stage, the bottleneck is not the hardware anymore, but the software that controls the robot. It is no longer reasonable to use over-simplified models of robot dynamics, because the novel compliant robots possess much richer and more complex dynamics than the previous generation of stiff robots. Therefore, a new solution should be sought to address the challenge of compliant humanoid robot control.

In this PhD theme, the use of machine learning and robot learning methods will be explored, in order to achieve novel ways for whole-body compliant humanoid robot control. In particular, the focus will be on achieving agile locomotion, based on robot self-learned dynamics, rather than on pre-engineered dynamics model. The PhD candidates will be expected to develop new algorithms for robot learning and to advance the state-of-the-art in humanoid robot locomotion.

The expected outcome of these efforts includes the realization of highly dynamic bipedal locomotion such as omni-directional walking on uneven surfaces, coping with multiple contacts with the environments, jumping and running robustly on uneven terrain and in presence of high uncertainties, demonstrating robustness and tolerance to external disturbances, etc. The ultimate goal will be achieving locomotion skills comparable to a 1.5 – 2 year-old child.



Department: ADVR (Department of Advanced Robotics, Istituto Italiano di Tecnologia)

Reference: P. Kormushev, S. Calinon, D.G. Caldwell. Reinforcement Learning in Robotics: Applications and Real-World Challenges. MDPI Journal of Robotics (ISSN 2218-6581), Special Issue on Intelligent Robots, vol.2, pp.122-148, 2013.

Contact: petar.kormushev(a)iit.it



Sofia science festival 2014

OFFICIAL CLOSING – “Return to the future”
May 11th, 2014

Dr. Petar Kormushev shows the capabilities of the state-of-the-art robots at the Italian Institute of Technology.


The demonstrations include various methods for machine learning that allow the robots to learn useful new skills.

Dr. Kormushev was awarded with the John Atanasoff award in 2013 by the President of Bulgaria.


More information – Italian institute of technology:



Machine Learning Summer Course

Machine Learning PhD Summer Course in Genova, Italy 30 June – 4 July 2014


Topic: Regularization Methods for Machine Learning (RegML)

Instructors: Francesca Odone, Lorenzo Rosasco

A 20 hours advanced machine learning course including theory classes and practical laboratory session. The course covers foundations as well as recent advances in Machine Learning with emphasis on high dimensional data and a core set techniques, namely regularization methods. In many respect the course is compressed version of the 9.520 course at MIT.

The course started in 2008 has seen an increasing national and international attendance over the years with a peak of 85 participants in 2013.

Registration required: send an e-mail to the instructors by May 24th. The course will be activated if a minimum number of participants is reached.

The course will be held in Genova in the heart of the Italian Riviera.
For more information see URL http://lcsl.mit.edu/courses/regml/

Robots at IIT – iCub, COMAN, HyQ

This is a demonstration of three robots built at the Italian Institute of Technology (IIT), where I work:

  • iCub – humanoid robot
  • COMAN – compliant humanoid robot
  • HyQ – hydraulic quadruped robot

The video was shown on “The Gadget Show”, Series 19 Episode 1.

Contest for John Atanasoff award in 2014

Sorry, this entry is only available in Български.

Kangaroo robot by Festo

An amazing robotic Kangaroo made by Festo!



Photo slideshow

Reviewing Revolution

(excerpt from Ludmila Kuncheva’s page)

“Reviewing will become obsolete. It has been needed in the past because there has been no way to tap on a larger readers’ audience for an opinion poll. Peer reviewing has been the only credible way to maintain standards of publication. The growing diversity of topics makes this process impractical, biased or spurious. We have technology now! We can allow for peer reviewing on a massive scale. Imagine a large pool of papers, automatically clustered and positioned within a big mosaic. Where do you look for papers? I doubt very much that you browse the contents of all relevant journals. Thank God for Internet! Now suppose that you have access to all papers. The best ones will be spotted and cited over and over. The citations will replace the reviews.

There will be fewer journals such as Nature, Science and Lancet. Only the best papers will find their place in the journals. These papers will no longer be original research, they will be rather “the best of…”. Selected by citation from the pool, say for the past 1 year, these papers can undergo a round of peer review. This time, however, the reviewing rules will be different:

  • First, all reviews will be handsomely paid.
  • Second, reviewers will bid for a paper. The candidates should submit their records, and the Editor will have the task to select among them.

As an additional benefit, we will kill fewer trees. Plus, a lot of human resource will be freed for better use of their expertise and energy. “

IEEE Technical Committee on Robot Learning

The robot hardware is progressively becoming more complex, which leads to growing interest in applying machine learning and statistics approaches within the robotics community. At the same time, there has been a growth within the machine learning community in using robots as motivating applications for new algorithms and formalisms. Considerable evidence of this exists in the use of robot learning approaches in high-profile competitions such as RoboCup and the DARPA Challenges, and the growing number of research programs funded by governments around the world. Additionally, the volume of research is increasing, as shown by the number of robot learning papers accepted to IROS and ICRA, and the corresponding number of learning sessions.

iCub robot archer - additional photo - IMG 5144  Pancake flipping robot - IMG 4086
The primary goal of the Technical Committee on Robot Learning is to act as a focus point for wide distribution of technically rigorous results in the shared areas of interest around robot learning. Without being exclusive, such areas of research interest include:

  • learning models of robots, tasks or environments
  • learning deep hierarchies or levels of representations, from sensor and motor representations to task abstractions
  • learning of plans and control policies by imitation and reinforcement learning
  • integrating learning with control architectures
  • methods for probabilistic inference from multi-modal sensory information (e.g., proprioceptive, tactile, vison)
  • structured spatio-temporal representations designed for robot learning such as low-dimensional embedding of movements
  • developmental robotics and evolutionary-based learning approaches

COMAN robot learning to walk - MVI 4773COMAN robot learning to walk - IMG 4682  HOAP-2 holding eraserHOAP-2 kinesthetic teaching with force sensor 01


  • [May 21, 2013] New Job opening – Post-doc in Robot Learning on topic: “Machine Learning for Robotics”. Details here: http://kormushev.com/news/postdoc-opening-in-machine-learning-for-robotics-2013/
  • [August 10, 2012] New IROS 2012 Workshop: “Beyond Robot Grasping – Modern Approaches for Dynamic Manipulation”. The workshop will be held on October 12, 2012 in Algarve, Portugal. More information at the website of the workshop: http://www.ias.informatik.tu-darmstadt.de/Research/IROS2012
  • [March 28, 2012] New AIMSA 2012 Workshop organized by the TC on “Advances in Robot Learning and Human-Robot Interaction”. The workshop will be held on September 12, 2012 in Varna, Bulgaria. More information at the website of the workshop: http://kormushev.com/AIMSA-2012/
  • [March 13, 2012] New chairs of the TC. After three very successful years for this TC on Robot Learning, the founding chairs Jan Peters, Jun Morimoto, Russ Tedrake and Nicholas Roy are stepping down as chairs of the committee. They will be replaced by Petar Kormushev, Edwin Olson, Ashutosh Saxena, and Wataru Takano who have kindly agreed to take the reign of the committee. Please see the changes in the mailing list addresses here.

Recent Activities of the Technical Committee

The technical committee regularly organizes special sessions associated with the “Robot learning” RAS keyword. If you want your paper to be considered for such a session and have used the above keyword in your submission, please forward an email to the TC co-chairs (contact info at: http://www.ieee-ras.org/robot-learning/contact). The technical committee will not be involved in the reviewing process but will organize the session based on the list of accepted submissions with this keyword.

Ironing robot - IMG 4366WAM robot - ArmInFridge

TC-organized Workshops

This is a summary of the workshops which were organized by the IEEE TC on Robot Learning:


Technical Committee Website:



Chairs of the Technical Committee

ashutosh saxena
Ashutosh Saxena
Cornell University, USA

edwin olson
Edwin Olson
University of Michigan, USA

petar kormushev
Petar Kormushev
Italian Institute of Technology, Italy

wataru takano
Wataru Takano
University of Tokyo, Japan


Who is Peter Joseph?

A nice interview with Peter Joseph: