“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. “
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.
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
[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.
This is a summary of the workshops which were organized by the IEEE TC on Robot Learning:
Good papers are like good wine: they need time to mature.
Of course, there are a few jerks out there, as Marc Raibert puts it, who can write perfect manuscripts on the first try, but if you’re reading this, I assume you are not one of these disgusting individuals.
So, for the rest of us mortals, I have tried to collect advice from various sources about how to write good scientific papers. Also, I contribute some of my own humble personal experience.
One of my most favourite papers on this topic is, without doubt, Marc Raibert’s paper about “Spilling the beans”. If you haven’t read it yet, please do so!
I totally agree with Raibert, and always try to “spill the beans” in my own papers as much and as early as possible.
The “Cargo Cult Science”, as named by Richard Feynman, is a must-see for all researchers, in my opinion. If you don’t know what I’m talking about, I recommend watching Feynman’s commencement address at Caltech at my Inspiration page.
Endowing robots with human-like abilities to perform motor skills in a smooth and natural way will greatly promote the use of robots in everyday life. However, acquiring new motor skills is not simple and involves various forms of learning. The efficiency of the process lies in the interconnections between imitation and self-improvement strategies.
Similarly to humans, a robot should ideally be able to learn new skills by employing such mechanisms. Some tasks can be successfully transferred to the robot using only imitation strategies. Other tasks can be learned very efficiently by the robot alone using reinforcement learning.
The recent development of compliant robots progressively moves their operational domain from industrial applications to home and office uses, where the role and tasks can not be determined in advance. While some tasks allow the user to interact with the robot to teach it new skills, it is generally preferable to provide a mechanism that permits the robot to learn to improve and extend its skills to new
contexts under its own guidance.
I will present my efforts in developing machine learning algorithms which allow robots to learn faster and more successfully real-world skills.
Petar Kormushev is a Team Leader (equivalent to Assistant Professor) at the Advanced Robotics department of the Italian Institute of Technology (IIT). His research interests include robotics and machine learning,
especially reinforcement learning for intelligent robot behavior. In 2009 he obtained a PhD degree in Computational Intelligence from Tokyo Institute of Technology. He also holds a MSc degree in
Artificial Intelligence, a MSc degree in Bio- and Medical Informatics, and a BSc degree in Computer Science. He has participated in the INFRAWEBS project for designing the future Semantic Web, as well as the Japanese NEDO project for developing next-generation robots. He received the first “John Atanasoff” scholarship by the Eureka foundation, and a 4-year Japanese research fellowship.
I am trying to create a contemporary English-Bulgarian scientific dictionary which contains modern and state-of-the-art scientific terms and their corresponding translations from English to Bulgarian and vice-versa. Most of the included words are too new and do not yet have a well-established translation in Bulgarian, which is one of the main reasons for trying to build such a dictionary in the first place, by trying to propose appropriate Bulgarian terms for the novel English terms.
The current version contains mostly terms from robotics and machine learning, because these are my main areas of research interest.
The COMAN robot is a compliant humanoid robot which is currently under development by the Advanced Robotics dept. of the Italian Institute of Technology in Genoa, Italy.
COMAN stands for “COmpliant huMANoid”, because this robot is designed with passive compliance (via springs) in his joints. This allows it to be more robust to environment perturbations (e.g. walking on uneven ground), to be safer for human-robot interaction (soft to touch), to be more energy-efficient, and to perform more dynamic motions (e.g. jumping, running).
COMAN can also be interpreted as Co-Man, meaning a co-worker, a robot which is a partner to humans, designed for safe physical human-robot interaction. The robot’s design is derived from the compliant joint design of the cCub bipedal robot.
This is a close-up of the passively-compliant legs of the robot:
Below is a video of the COMAN walking experiment I did together with Barkan Ugurlu and Nikos Tsagarakis. The goal was to learn to minimize the energy consumption used for walking by COMAN. This video accompanies my IROS 2011 paper presented in San Francisco, in September 2011.
We present a learning-based approach for minimizing the electric energy consumption during walking of a passively-compliant bipedal robot. The energy consumption is reduced by learning a varying-height center-of-mass trajectory which uses efficiently the robot’s passive compliance. To do this, we propose a reinforcement learning method which evolves the policy parameterization dynamically during the learning process and thus manages to find better policies faster than by using fixed parameterization. The method is first tested on a function approximation task, and then applied to the humanoid robot COMAN where it achieves significant energy reduction.
In recent years, there have been some amazing demonstrations of successful learning robots, which master some difficult motor skills.
Here I have collected some of the most impressive ones, which I consider being major milestones at the time they were done:
This is work done by my former colleague Stephen Hart: Dexter robot learning to reach
Work by James Kuffner in CMU:
This is work done by my friend and colleague Sylvain Calinon:
One of my main research topics is robot learning. Normally, in machine learning, the algorithms are classified in three classes: supervised (aka. imitation learning in robotics), unsupervised (aka. exploration in robotics), and semi-supervised (aka. reinforcement learning in robotics).