Rosen Diankov, Ph.D
出杏光魯仙
であんこうろせん

JSK Robotics Lab
University of Tokyo

My ultimate goal is to solve the robotics problem: combine vision, perception, planning, and control into one coherent framework to create intelligent and autonomous robots. Since I joined The Robotics Institute, I've been working on such an architecture titled OpenRAVE. My current research focuses on building automatic construction of autonomous manipulation programs without requiring programmers to tweak endless parameters or write scripts. Although I'm very interested in getting humanoid/mobile-manipulator robots in the kitchen to help out with chores, the ultimate applcation of this research is industrial robotics. I also work on robot vision and am looking for effective ways to plan around environments using cameras attached to the robot.

Robots

I was a JSPS research fellow during 2007 at the AIST Digital Human Research Center working on the humanoid robot HRP2. Under the supervision of Dr. Satoshi Kagami and Dr. Koichi Nishiwaki, I jointly developed a system to get humanoid robots to grasp objects in dynamic environments without specifying apriori how the objects should be grasped.

After that, I worked at Intel Research Pittsburgh on a robot to autonomously perform manipulation tasks in human-centric environments like the kitchen. The mobile manipulator's name is HERB and consists of a Barrett WAM, a Barrett Hand, and a Segway RMP.

For a short period of time, I had the honor of interning at Willow Garage, a new robotics startup. Since then, I adopted the ROS robotics architecture and was able to focus OpenRAVE only for motion planning research.

Currently I'm collaborating with the JSK Robotics Lab at the University of Tokyo on building intelligent humanoids.


You can find a complete list of past research here