Home
Welcome to the mobile_robotics_final wiki!
Our project is Object Pose Estimation via Curvature-based ICP for Goal-Oriented Robot Manipulation.
Perception is critical for a robot to accomplish localization and manipulation tasks successfully in household environment. Object localization becomes very challenging in such complicated environment. We proposed a curvature-based Iterative Closest Point algorithm, to help the robot localize a target object in the scene. The point cloud data was collected from the Laboratory for Progress's Fetch Robot, and our result shows that we can correctly localize object from a cluttered scene.
This video shows how the data is collected by the Fetch Robot.
In model-to-model experiment setting, our goal is to map the source point cloud of an object to the target point cloud of the same object. The following video visualizes the process.
In model-to scene experiment, we still want to find the transform matrix to map the object to the target point cloud. But the target point cloud is now a complicated scene. The following video shows how our algorithm works under model-to-scene experiment setting. Our algorithm is capable of mapping the source point cloud (red) to the target point cloud (black).
Please refer to the following pages for detailed information.
- Justin Diep
- Kevin French
- Tianyang Pan
- Yue Tang
- Zheming Zhou