Projects
These are typical projects (individual or contribution > 50%)
MPL lab Paper >
A Multi-sensor data set with five types of sensors and three scenarios (on tripod 3Dof motion, on helmet 6Dof motion, and hand-held 6Dof motion).
1. 0.3Mp Stereo Event camera - Prophesee G3
2. 1Mp Stereo RGB camera - Pointgary GS3
3. 0.25Mp depth camera - Kinect Azure
4. 9 Axis IMU with AHRS - XSense MTi300
5. 128-line Lidar - Ouster-os0
MPL lab
A tight event-inertial fusion front-end with warping and feature extraction is designed. Implement the odometer with IMU pre-integration residual term and pose & linear velocity constraints. Establish the back-end pose graph optimization (based on time window) with Ceres nonlinear optimization library.
UM-SJTU JI
Built a hydraulic excavator testing model and controlled it by fixed-point path planning. Drew the concept diagram and built the testing model with thrust bearing and carbon fiber arm
Deployed ROS-based RS232 Modbus API to control the hydraulic system and applied closed-loop PID control. Develop shape detection system based on Binocular camera & OpenCV enabling excavator work anonymously.
Northwestern MSR
An open-source toolbox for users to have easy access to Hardware Synchronization on multi-sensors.
The toolbox has a GUI based on QT (rqt). Users can record a ROS bag or have a new topic reflector (reconstructed timestamp) as they want.
Furthermore, the hardware-level IMU data process is also embedded in Microcontroller.
Northwestern MSR
The goal of this project is to quickly build an accurate (calibration-free) localization system in indoor medium & large-scale scenarios.
In the project, we use the method of common view to construct a series of April tag pose associations and use them for localization. Uncertainty in the resulting position is about several centimeters.
