Homepage
Research
Videos
Publications
Data Sets
Courses
C.V.
Travel
Personal
Other Links

Current

Simultaneous Localization, Mapping and Moving Object Tracking

Localization, mapping and moving object tracking serve as the basis for scene understanding, which is a key prerequisite for making a robot truly autonomous. Simultaneous localization, mapping and moving object tracking (SLAMMOT) involves not only simultaneous localization and mapping (SLAM) in dynamic environments but also detecting and tracking these dynamic objects. It is believed by many that a solution to the SLAM problem would open up a vast range of potential applications for autonomous robots. Accordingly, a solution to the SLAMMOT problem would expand robotic applications in proximity to human beings where robots work not only for people but also with people. [More information]

4D Spatio-Temporal Mapping of Urban Environments

Many applications in robotics, civil engineering, architecture, landscape architecture, city planning, computer graphics and computer vision require accurate three-dimensional (3D) models of real-world objects. SLAMMOT not only build models of stationary objects but also dynamic activities. In this project, we develop systems and algorithms for building four-dimensional (4D) spatio-temporal maps of both urban and indoor environments. [More information]

Robotics for Safe Driving

The focus of this project is on short-range sensing, to look all around the vehicle for improving driving safety and preventing traffic injuries caused by human factors such as speeding, or distraction. We believe that being able to detect and track every stationary object and every moving object, to reason about the dynamic traffic scene, to detect and predict every critical situation, and to warn and assist drivers in advance, is essential to prevent these kinds of accidents. [More information]

Past

Internships

I spent the 2002 Summer at RIACS, NASA Ames Research Center, working with Peter Cheeseman and Doron Tal, on three-dimensional extended Kalman filter based simultaneous localization and mapping.   I spent the 2001 Summer at Z+F USA, Inc. in Pittsburgh, working on 3D range image processing and Spin-Images Implementation.

Paint Stripping Robot

From 1999 to 2000, I developed the landmark-based localization and coverage planning algorithms for the M2000 paint stripping robot at the National Robotics Engineering Consortium (NREC).

Design, Modelling and Control of Marine Robots

AUV ROV ASV Modelling and control of marine vehicles have been a great challenge due to the nonlinear nature of both the vehicles themselves and the environments in which they operate. From 1993 to 1996 and 1998 to 1999,  I worked with Jenhwa Guo and Chiu-Forng Chen at National Taiwan University on design, modelling and control of marine vehicles, such as autonomous underwater vehicles (AUV), remotely operated vehicles (ROV) and autonomous surface vessels (ASV). I developed a numerical motion simulation system for modelling marine vehicles in which the effects of trimming weight subsystem, deballast subsystem, control surfaces and main propulsion subsystem are taken into account. I developed an adaptive controller for marine vehicles using neural network. The experimental results show that the neural network adapts to time-varying plant dynamics as well as disturbance upsets when the learning process is kept active through the control operation. [More information]