CraneDataset
- Citation Author(s):
-
Weili DingYinrui Shang
- Submitted by:
- yinrui shang
- Last updated:
- DOI:
- 10.21227/jcg0-jg48
12 views
- Categories:
- Keywords:
Abstract
The visual sensor captures images of the crane loading operation scene, while simultaneously collecting the motion control commands from the crane's operational control end. A neural network model is trained to predict the crane's motion control commands in an end-to-end manner.
Instructions:
The CraneDataset includes two datasets: simcrane and realcrane, which correspond to the crane simulation data and the crane real-world data, respectively. Both datasets contain images and motion control instructions from the crane operation side. The images and motion control instructions are time-aligned. The neural network is trained to learn the correspondence between the image sequences and the motion control instructions. The trained network then predicts the crane's motion control instructions in an end-to-end manner based on the input images.
