I am a second-year graduate student majoring in computing science in Simon Fraser University. And I am a research assistant in Autonomy Lab of SFU. My research focus is Human Robot Interaction and I implement robot behaviors to enable them interact with human naturally. I am also trying to build modularized legged robots, and use deep learning method to help them walk and recognize objects (especially for human face identity). Besides, I have been painting for more than 10 years (my Pixiv page), and I also play acoustic guitar, electric guitar and drum sets. My Curriculum Vitae is here.
- 09/2014-08/2016(Expected) Master of Science, School of Computing Science, Simon Fraser University
- 09/2015-08/2016(Expected) Graduate Certificate in Science and Technology Commercialization, Beedie School of Business, Simon Fraser University
Study frameworks, perspective and techniques for research scientists and engineers to contribute to new product development and commercialization in industry.
SFU Science & Technology Scholarship
- 09/2010-06/2014 Bachelor of Engineering, School of Electronic and Informaition Engineering, Beijing Jiaotong University
Cumulative GPA: 87/100, Major GPA: 90/100, Ranking: 21/220
2011-2013 Dean’s List (15%)
Scholarship for Scientific Innovation Excellence 2013 (1%), Scholarship for Community Work Excellence 2012 (3%)
- 09/2010-06/2012 Elite English Program, School of Language and Communication Studies, Beijing Jiaotong University
Coursework: Speaking and Debating, Interpreting, Advanced Oral English and etcetera
Top 25 students across the whole campus are enrolled in this program every year.
- 07/2013-08/2013 Artificial General Intelligence Summer School 2013, Peking University
Coursework: state-of-the-art AGI projects including NARS, AERA and OpenCog (more about this,my notes)
Peking University is among top 2 in China. 50 students over the world are enrolled in the summer school every year.
InspiRED is a LEGO-like 3D-printable 70-cm humanoid robot platform featured with highly-customized components. Its controller is a low-cost but powerful single-board Linux computer Odroid-U3 and we use ROS and Open-CV with it. A large number of commonly used electronic equipments including RC servos, camera, HDMI-display, IR sensor, IMU, speaker, microphone, LED, PS2 controller and etc. are supported. We participated in the robotics startup competition, “Ogopogo’s Lair” and won funding support from NCFRN.
Initial is a 40-cm humanoid robot. It’s used for testing of running ROS on single board computer, Odriod U3, which talks to a low level controller board for controlling servo motors via serial port. It is also equipped with an HD camera, and the video stream can be transported to the laptop via wifi.
It was for an Undergraduates Curricular-extra Academic Science and Technology Competition. I was the project leader and covered most of the programming and algorithms designing work. We designed and made the Intelligent Navigation And Tracking Robot in one year. And we ended up with winning the first prize in Beijing and was the only team in my university that gaining the qualification for national final 2013, where we won the second prize.
I developed a quadcopter based on STM32 since 2013.11. A WLAN Model is attached to its CPU so that it can be controlled by a mobile phone via WLAN. And it is equipped with a video camera to recognize and track certain patterns.
I developed a rover based on ARM7 in 2013.02. It is controlled by LPC2148, and its position can be detected by using Zigbee equipments which is connected to a laptop which can display it.
I studied the basic algorithms and take the programming races on Codeforces and other online platforms. I officially became a member of BJTU ACM/ICPC team in 2012. And I, together with my two teamates, took the Asian zone qualified of 37th ACM/ICPC in 2012, winning a bronze medal finally. (Solved problems collection are in the Algorithm category of this blog.)
TECO Green Tech International Contest
TECO Green Technology International Contest is a contest on environmentally-friendly technology organized by TECO Technology Foundation in Taiwan in 2013. Our team’s project, Indoor Localization and Navigation based on Zibee was enrolled in the Internation Final, together with Tsinghua University, Tokio University, Singapore Nayang University, Moscow State University and etcetra. (more about this)
Mathematical Modeling Contest of Beijing Jiaotong University
The problem was to predict the traffic load of Beijing in several years after the given years. And the data of the startup years was given. I, together with my two friends, used Neural Network Tool Box in Matlab to solve this problem and we got the second prize in this contest.
Physics Experiments Competition of Beijing Jiaotong University
It was in 2011 and every team was asked to build up an application with LED lights. It was the first time for me to take part in a scientific competition. And my team made a Canteen Order Device. We won the 1st prize in this competition. (more about this)
Optimal Gaze-Based Robot Selection in Multi-Human Multi-Robot Interaction
This project presents a computer vision based system for interaction between multiple humans and multiple robots. Each human can “select” (obtain the undivided attention of) a robot by simply looking directly at it. This extends previous work whereby a single human can select one or more robots from a population. Each robot optimally assigns human identities to tracked faces in its camera view using a local Hungarian algorithm. Then the system finds the global optimal allocation of robot-to-human selections using a second, centralized, Hungarian algorithm. This is the first demonstration of optimal many-to-many robot-selection HRI.
Cooperative Behaviour for Model Training with Autonomous Mobile Robots
In order to gain the benefits of supervised learning techniques without requiring a human to construct a labeled dataset, we have developed a behavior for a pair of mobile robots to train a visual classifier on their own. This autonomous approach takes advantage of the rote nature of dataset creation to allow machines to replace humans with little appreciable loss of performance. A specific implementation of this behavior was written for Chatterbox robots, whose automatically-built dataset was compared to human-constructed ones.
Orbiting a Moving Target with Multi-Robot Collaborative Visual SLAM
Towards autonomous 3D modelling of moving targets, we present a system where multiple ground-based robots cooperate to localize, follow and scan from all sides a movingtarget. Each robot has a single camera as its only sensor, and they perform collaborative visual SLAM (CoSLAM). We present a simple robot controller that maintains the visual constraints of CoSLAM while orbiting a moving target so as to observe it from all sides. Real-world experiments demonstrate that multiple ground robots can successfully track and scan a moving target. (video)
3D Mesh Segmentation Based on cascaded algorithm for super-patch agglomeration
I interned for the Special Interests Group on Visual Computing (SIGVC) at Chinese Academy of Science. I worked with Dr. Huaiyu Wu, doing research on 3D mesh segmentation, applying cascaded algorithm for super-patch agglomeration. (Note: the thumbnail image is from here)
the Visualization of the Deep Learning Process
I joined the deep learning research in the National University Science Park of BUPT as a research assistant for Dr. Da Xiao from 2013.07 to 2013.10, using the Theano and Pylearn2. With MNIST and Cifar-10 Image Dataset, I visualized the mapping from the features of input data to the units in hidden layers. I learned GPU programming, which could accelerate the calculation speed to 100 times what CPU is capable of, through applying Theano and Pylearn2 in this project .
Improving Collaborative Filtering Algorithm for VOD System
I worked with Pro. Guo in Communication Network Lab of my school from 2013.02 to 2013.07. The goal was to improve the performance of traditional Collaborative Filtering Algorithm for the video recommender system. I, together with my partner, promoted the QoS, which was based on the video watching time, as a factor during the machine learning process and got a better recommendation result, evaluated by NDCG and MSE, than the one without QoS factor.
Video Recommender System Algorithm Research Based On ABS
My job was to build up the simulation platform for Agent Based Simulation on Netlogo. I learned Netlogo programming and finished this platfrom myself. The selection tactics of the audience can be controlled and feedback can be collected to enhance the performance of the recommender system.(more about this)
The Bubble Image Processing Based On DPIV Algorithm
The goal was to track the path of the bubbles in water using DPIV algorithm on Matlab. The team contains two members. And my job was to program the core part of DPIV Algorithm in Matlab. The bubbles were labelled with different number and their velocity and size could be visualized.
Range Finder Based on 51-MCU
MC89S51 was used as CPU. It was an automatic speed control and alarm system based on the ultrasonic ranging. Since it could display the distance on the LCD screen. (more about this)
- Teaching Assistant for CMPT 127 – Computing Laboratory
I was the TA for CMPT 127 in Simon Fraser University in 2014 fall and 2015 fall. This class teaches the basics of programming in C and C++, with an emphasis on program design and testing. The standard UNIX command-line build and version control tools are used.
Publication and Presentations:
- Optimal Gaze-Based Robot Selection in Multi-Human Multi-Robot Interaction
L. Zhang, R. Vaughan
Human-Robot Interaction Pioneers Workshop at the 2016 ACM/IEEE International Conference on Human-Robot Interaction (HRI 2016), Christchurch, New Zealand, March 2016 (PDF).
- Orbiting a Moving Target with Multi-Robot Collaborative Visual SLAM
J. Perron*, R. Huang*, J. Thomas, L. Zhang, P. Tan, R. Vaughan
Workshop on Multi-View Geometry in Robotics (MVIGRO) at the 2015 Robotics: Science and System Conference (RSS’15 workshop), Rome, Italy, July 2015 (PDF)
- the Zigbee Based Intelligent Navigation and Tracking Technology
2013 TECO Green Tech International Contest World Final, Tipei, 08/2013 (video)
- the Navigation and Tracking Multi-functional Robot
Expo of the College Student Research and Career-creation Program of Beijing, Beijing, 05/2013
Students’ Community Work:
Students Volunteer for 2016 ACM/IEEE International Conference on Human Robot Interaction (HRI 2016)
Help with troubleshooting, setting up, monitoring, etc the telepresence systems.
Founder and the 1st President of Beijing Jiaotong University Scientific English Association:
In 2012, I instituted the Scientific English Association in our university, aiming at propagating knowledge and enhancing academic exchange and communication. We held public speaking contests as a premature form of TEDx and look forward to holding an official TEDx in the near future. We also held cocktail parties for the future engineers and scientists to exchange brilliant ideas. We invited a myriads of successful people to give lectures and share their experience.(more about this)
Vice Captain of the School Debate Team:
I, being the vice president of the school debating team, am deeply in favor of this activity as I find it means more than itself. On the one hand, it enhanced the skills of public speaking, facilitating expressing myself in various occasions. On the other hand, it forces me to think critically and logically, equipping an even more clear mind.
Director of the School Students’ Union Office:
The School Students’ Union Office is the core of a whole students’ union. Our work was to make plans for different departments of the students’ union so that they could coorperate with each other effectively. And we kept the documentation for all the members and event details of the students’ union.
‘You are what you read’. Literature, history, economy, politics, phsycology and computer science related books are all I loved. Sometimes, I wrote book notes after reading and some of them are on this website.(more about this)
I enjoy various kinds of music ranging from classic music to rock music. I am a guitar player and I also covered some famous songs by my self.(more about this)
I learnt and practiced sketching at a young age for one year. After that, I drew all kinds of things by myself. Since last year, I started to paint with electronic devices, such as smart phones and Ipad, using an app called SketchBook Mobile. (more about this)
About this blog:
This blog is an inherit of http://blog.csdn.net/lethic. I had a good time at CSDNs blog, but it would be better to find a place of my own. This new blog contains five main categories: Algorithm, Programming, Tech, Words & Music, Work & Life, which may be chaned by time.
- Algorithm is a collection of programming algorithm study experience and some interesting problems solving report.
- Programming contains some notes of learning programming.
- Tech is the page for Data mining, Machine Learning, Microcontroller, Embedded System, Linux, Internet and etc..
- Words and Music may be the most interesting part. I love reading literature and history related books. At the same time, Im a rock music fan. So some critics to books and music will be included.
- Work and Life is where I write about my sentiment about my work in some students community and some essay in the daily life.
Please click here