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.
One of my favorite comics is the PhD comics (“Piled Higher and Deeper”), which relates to many problems and funny moments of a PhD-student’s and a post-doc’s life.
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 selfimprovement 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.
Biography
Petar Kormushev is a Team Leader (equivalent to U.S. 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” award, 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 iCub robot is a humanoid robot developed within the project RobotCub. The iCub was designed and built mainly by the Italian Institute of Technology in Genova.
Reinforcement Learning is a type of Machine Learning approach in which the learning algorithm discovers by itself how to reach a given goal by a trial-and-error process.
Reinforcement Learning is different than supervised learning and unsupervised learning. It can be considered as “semi-supervised” learning, because of the information given by the reward function.
The reward function is the way in which the goal is specified… to be continued.
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).
I maintain a list of active Bulgarian researchers in robotics and machine learning:
Petar Kormushev is a Team Leader (equivalent to U.S. Assistant Professor) at Italian Institute of Technology, working on robot learning by imitation and reinforcement learning.
Dragomir N. Nenchev is a professor at Tokyo City University, working on motion/force control, space robots, humanoid robots, and service robots.
Lubomir Lilov is a professor at Sofia University, heading the master’s program on Mechatronics and Robotics at the Faculty of Mathematics and Informatics.
Rosen Diankov is the author of OpenRAVE robotics platform for manipulation planning, etc.
Alexander Stoytchev is a professor at Iowa State University. He constructed a dual-arm Barrett WAM robot and is researching in developmental robotics.
Jivko Sinapov is a PhD student of prof. Alexander Stoytchev.
Vladimir Zamanov is teaching robotics at Technical University of Sofia.
Ivan Dryanovski is a PhD student at CCNY (City College of New York), doing research on 3D SLAM and Micro Air Vehicle Navigation.
Dragomir Anguelov was a PhD student at Stanford University, collaborating with prof. Sebastian Thrun on computer vision for robots. Now he is working at Google in Mountain View.
Dimitar Ivanov Chakarov is an associate professor at the Mechatronic Systems dept. of BAS in Bulgaria.
Evtim Venets Zahariev is an associate professor and head of the department of Dynamics and optimization of controlled mechanical systems at BAS in Bulgaria.
Andrey Popov is at Hamburg University of Technology, doing research on UAV robots (esp. quadrocopters and H-infinity controllers).
Marin Kobilarov is a post-doc in control and dynamical systems at Caltech, doing research on motion planning and control.
Bojan Jakimovski is the CEO of Bionics4Robotics, which is a robotics- and AI- related company in Munich, Germany.
Ilian Bonev is a professor working on precision robotics and parallel manipulators at ETS, Canada.
Roko Tschakarow works at SCHUNK as a Business Unit Manager System Solutions Mechatronics. His work is on building lightweight and modular robots.
Alexander Gegov is a Reader at University of Portsmouth, UK. His main research interests are in computational intelligence.
If you are an active Bulgarian researcher in robotics I will be happy if you contact me, so that I can add you to this list.
List of other Bulgarian robotics enthusiasts and hobbyists:
Orlin Dimitrov (Орлин Димитров) is a student who did restoration of the Bulgarian robot ROBKO 01 and created various controllers for it. He has a website about ROBKO 01.
PRACTRO - Robotics Conference with International Participation. Dimitar Cenev and Veselin Pavlov are constructing a website in Bulgarian called Robotic Design.
RSS feed
