A team from the Advanced Intelligent Robot Laboratory at the National Taiwan University of Science and Technology used CUDA, GeForce and Kinect Fusion to train a multi-axis robot to autonomously spray paint bicycle frames. Nowadays, autonomous spraying painting is an important process in industries for several reasons. However, programming an industrial robot by the ordinary teaching method through the use of the robot teach pendant is a tedious and time consuming task that requires skilled expertise.
The proposed method demonstrates efficient spraying performance in terms of coating quality as well as saving painting material. Experimental results have shown that the system could perform a full coverage on the target workpieces of various types in very short preparation time with minimum paint loss and without the expertise of the traditional robot teaching method.
Read the research paper >>
Trained Robot Autonomously Spray Paints Bicycle Frames
Sep 17, 2015
Discuss (0)
Related resources
- DLI course: Deep Learning for Industrial Inspection
- GTC session: Reward Fine-Tuning for Faster and More Accurate Unsupervised Object Discovery
- GTC session: Training Robot Behavior at Scale in the AWS Cloud With the NVIDIA Isaac Robotics Platform
- GTC session: Jetson Community Projects Showcase
- NGC Containers: MATLAB
- Webinar: Use Your Own CUDA ROS Node with NITROS on NVIDIA Jetson
About the Authors
