Kentaro Wada
5-14-24 Sendagi, Bunkyo-ku, Tokyo, 1130022, Japan
www.kentaro.wada@gmail.com
●
+81 (80) 6177-5221
●
wkentaro.com
Date of birth: 31 January 1994
●
Nationality: Japanese
EDUCATION
University of Tokyo
MS in Information Science and Technology
September 2016 – August 2018 (expected)
BE in Mechano-Informatics
April 2012 – March 2016
Supervisors: Prof. Masayuki Inaba, Prof. Kei Okada
PORTFOLIO
wkentaro.com
Extensive listing of cocurricular and research projects.
DISTINCTION
University of Tokyo, Toyota Dwango Advanced AI Fellowship
2017
Google Summer of Code Student
2016
Completed an open source project from the Open Source Robotics Foundation.
5th Place Winners (Pick Task) at the Amazon Picking Challenge
2016
An internationally recognised premier robotics competition.
PUBLICATIONS
Kentaro Wada, Shingo Kitagawa, Kei Okada, and Masayuki Inaba, “Instance Segmentation of Visible
and Occluded Regions for Finding and Picking Target from a Pile of Objects”, Under review at the IEEE
International Conference on Intelligent Robots and Systems (IROS), 2018. [Paper] [Movie]
Kentaro Wada, Kei Okada, and Masayuki Inaba, “Probabilistic 3D Multilabel Real-time Mapping
for Multi-object Manipulation”, IEEE/RSJ International Conference on Intelligent Robots and Systems
(IROS), 2017. [Paper] [Movie] .
Shun Hasegawa, Kentaro Wada, Yusuke Niitani, Kei Okada, and Masayuki Inaba, “A Three-Fingered
Hand with a Suction Gripping System for Picking Various Objects in Cluttered Narrow Space”,
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017. [Paper] [Movie]
Kentaro Wada, Makoto Sugiura, Iori Yanokura, Yuto Inagaki, Kei Okada, and Masayuki Inaba,
“Pick-and-Verify: Verification-based Highly Reliable Picking System for Various Target Objects in
Clutter”, Journal of Advanced Robotics, 2017. [Paper] [Movie]
Kentaro Wada, Masaki Murooka, Kei Okada, and Masayuki Inaba, “3D Object Segmentation for
Shelf Bin Picking by Humanoid with Deep Learning and Occupancy Voxel Grid Map”, IEEE-RAS
International Conference on Humanoid Robotics (Humanoids), 2016. [Paper] [Movie]
Yuki Furuta, Kentaro Wada, Masaki Murooka, Shunichi Nozawa, Yohei Kakichi, Kei Okada and
Masayuki Inaba, “Transformable Semantic Map Based Navigation Using Autonomous Deep Learning
Object Segmentation”, IEEE-RAS International Conference on Humanoid Robotics (Humanoids), 2016.
[Paper] [Movie]
Page 1 of 2
RESEARCH
EXPERIENCE
Leader of the UTokyo Team at the Amazon Robotics Challenge
2015 – 2017
JSK Robotics Laboratory at the University of Tokyo
Supervisor: Associate Prof. Kei Okada
Objectives: To develop a robust state-of-the-art robot picking system for warehouse automation. 2015
edition: Verification based robust picking system by in-hand recognition. 2016 edition: Deep learning
based 3D semantic segmentation. 2017 edition: Few-shot deep learning of novel object segmentation
using only instance images.
Research Assistant at the UTokyo JSK Robotics Lab
2015 – 2017
JSK Robotics Laboratory at University of Tokyo
Supervisor: Associate Prof. Kei Okada
Objectives: To develop a system of continuous integration of a robotic system as a whole: (1) Same
software as a robotic system on simulation and real world. (2) Enable motion testing by a simulator
with dynamics.
Research Assistant at the UTokyo Tanaka Kenji Lab
2014 – 2015
Tanaka Kenji Laboratory at the University of Tokyo
Supervisor: Associate Prof. Kenji Tanaka
Objectives: To analyse customer data of an e-commerce site and segment the users’ tastes by clustering
user data according to page access and shopping.
WORK
EXPERIENCE
Donuts Co. Ltd., Tokyo
2013 – 2014
Interned as a System Integrator
Honda Research Institute, Tokyo
2014
Summer intern, Road scene understanding with deep learning
KEY SKILLS
■
High-level programming skills, especially with Python and C++, trained in the research use and
contributions to open source projects at GitHub.
■
Experience and knowledge of constructing a large robot vision system integrating various kinds of
hardware and software with the Robot Operating System (ROS).
■
Knowledge of deep learning implementation with the frameworks including, Chainer, PyTorch and
Caffe, and GPU computing using CUDA.
INTERESTS
Deep learning, Scene understanding, 3D reconstruction, Real-time vision system.
REFERENCES
Prof. Masayuki Inaba
Professor of the Graduate School of Information Technology and Science
University of Tokyo
73A1, Engineering Building NO. 2, 7-3-1, Hongo, Bunkyo-ku, Tokyo, 1138656, Japan
inaba@jsk.imi.i.u-tokyo.ac.jp
●
+81 (3) 5841-7416
Prof. Kei Okada
Professor of the Graduate School of Information Technology and Science
University of Tokyo
73A2, Engineering Building NO. 2, 7-3-1, Hongo, Bunkyo-ku, Tokyo, 1138656, Japan
k-okada@jsk.imi.i.u-tokyo.ac.jp
●
+81 (3) 5841-7416
[
CV compiled on 2018-04-21]
Page 2 of 2