Copyright 2019 Reflux Design
About Me
I'm now a PhD student in the field of Robotics in Department of Electrical, Computer, System Engineering, Rensselaer Polytechnic Institute, advised by Dr. John Wen.
Robotics Scientist
Hi, I'm Chen-Lung Eric Lu and I'm a Roboticist. Robots fascinated me with how similar it is with humans. My research interests encompass motion optimization and kinematic calibration for robot arms within manufacturing contexts. My research incorporates concepts from robotics, optimization, and control. Additionally, I have experience in semi-autonomous vehicles for search and exploration, utilizing SLAM, deep learning, and reinforcement learning methodologies.
Research Projects
I have been working on robotics since the forth year of my bachelor. I started my journey with Duckietown. From there I then became a visiting student in ETHZ, Switzerland, and worked in Institute of Dynamic System and Control (IDSC), Autolab under the supervision of Dr. Jacopo Tani and Dr. Andrea Censi. After coming back to Taiwan, I first kept working on Duckietown in Taiwan branch. From 2019 January, I start working as the Team Lead of NCTU in DARPA Subterranean Challenge.
DARPA Subterranean Challenge
I am the Team Lead of Team NCTU from January, 2019. Team NCTU have been competing in SubT Challenge in Tunnel Circuit and Urban Circuit, where we got #7 and #8 among all team and #2 among all self-funded team.
Shortbaseline (SBL) Ultra-wide bandwidth (UWB) based Localization
In subterranean environments, robots often face degrading sensing Challenge where SLAM often fail. To enable localizability estimation and thus avoid SLAM failure, we need to be able to localize our robot in such environments. Therefore, we develop a shortbaseline ultra-wide bandwidth based localization method or SBL-UWB localization with heterogeneous robot team.
Sound-UWB Anchor
We develop a sound-uwb anchor to assist SLAM in austere environments. The anchor not only serve as an artificial landmark but also a communication node which enable mesh communication of XBee and WiFi.
Toward Open Platform of Blind Navigation via Interactions with Autonomous Robots
Recent advance of technologies of autonomous robots shows their impact in blind navigation. Our lab have long been developing assistive technologies from wearable devices to robotics guide dogs. In this position paper, we aim to share some of our experience in blind navigation technologies with autonomous robots. The position paper is accepted to Hacking Blind Navigation Workshop in CHI 2019.
Watchtowers - Enable Localization of Duckiebot in Duckietown.
Duckietown has been a great platform to learn and conducting reseach in robotics and autonomous driving car. To keep advancing the platform, the ability of localizing those Duckiebot is crucial. Here, we present the watchtower solution. We chose watchtower is a tower-like infrastructure inside Duckietown. They survellent over the whole city and try to localize Duckiebots using the Apriltag on top. Every watchtower is equiped with a RPI 3B+. They detect Apriltag and send the localization results back to the server computer where optimization is performed. The reason we chose watchtower over over-head cameras is that we would like these little guy to be a part of the town.
Professional Skills
I work with ROS, Python in Daily bases. I know C++ as well.Deep Learning and Reinforcement Learning
I have studied and also some side project with DL and DRL
SLAM
Some of my works are realted to SLAM. I also use libraried like iSAM, GTSAM.
Robotics Operating System ROS
I work with ROS in daily basis
Python, C++
Mostly I code in Python. I also have plenty experience with C++.