Adaptive and flexible robotic pick-and-place
FMCG industry is trending towards e-commerce adoption. However, there are challenges in the existing packaging lines. One of the main challenges is to pack products in accordance to mass customized orders. In this project, we aim to develop an automated solution for this challenge in bin picking sce...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/77710 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | FMCG industry is trending towards e-commerce adoption. However, there are challenges in the existing packaging lines. One of the main challenges is to pack products in accordance to mass customized orders. In this project, we aim to develop an automated solution for this challenge in bin picking scenario, which is picking up object from a clustered bin. The robot system setup consists of a robotic arm equipped with gripper, a 2D/3D camera. The robot system is able to detect FMCG products (object detection) and to calculate the pose of the product (pose estimation). This paper aims to show several aspects of developing the solution: ROS architecture development, perception, and motion planning. There are two perception methods proposed in this paper: feature matching (SIFT) and deep learning (Mask R-CNN). Each method will be described in detail. |
|---|