Projects

Here is a collection of project I have done in the past on various topics of interest.

lidar_robot_mapping (ROS, Autoware, Gazebo, C++)

Hands-on Experience with RS–LiDAR-16, OS2–64, and OS2–128 to build an occupancy grid of controlled environment. Fusion of slam toolbox with Autoware package based NDT Mapping to get odom to baselink transformation and, accurate 2D SLAM.

Using a Intel Realsense T265 to build an occupancy grid and autonomously navigate around using move_base.
[code]

Workplace Service Robot (ROS, Gazebo, C++, Python)

Autonomous Mobile Robot (AMR), a holonomic drive with 4 mecanum-wheels. It autonomously maps an environment, localizes itself, and navigate to pick-up and drop-off objects in a simulated environment.
[code]

Sensor fusion-based Tracking (C++)

Utilize sensor data from both LIDAR and RADAR measurements for object (e.g. pedestrian, vehicles, or other moving objects) tracking with the Kamlan Filter, Extended Kamlan Filter, and Unscented Kamlan Filter.

Vehicle Localization (C++)

The Vehicle has been “kidnapped” and transported to a new location! Luckily it has a map of this location and a (noisy) GPS estimate of its initial location. Then the vehicle starts to move, in the meanwhile, it records the noisy sensor and control data. A real-time particle filter is implemented to localize the vehicle with the sensor data. In this project, particle filter will be given a map and some initial localization information (analogous to what a GPS would provide). At each time step my filter will also get observation and control data.
[code]

Path Planning (C++)

Implemented a simple real-time path planner in C++ to navigate a car around a simulated highway scenario, including other traffic, given waypoint, and sensor fusion data.
[code]

Model Predictive Control (C++)

Implemented a Model Predictive Control (MPC) to drive a car in a game simulator. The server provides reference waypoints via websocket, and we use MPC to optimize the actuators (steering and throttle), simulate the vehicle trajactory, and minimize the cost like cross-track error.
[code]