In the previous chapter, we looked at actuators and how to interface the robot's sensors using the Tiva-C LaunchPad board. In this chapter, we will mainly look at vision sensors and the interface that they use with our robot.
The robot we are designing will have a 3D vision sensor, and we will be able to interface it with vision libraries such as Open Source Computer Vision (OpenCV), Open Natural Interaction (OpenNI), and Point Cloud Library (PCL). The main application of the 3D vision sensor in our robot is autonomous navigation.
We will also look at how to interface the vision sensors with ROS and process the images that it senses using vision libraries such as OpenCV. In the last section of this chapter, we will look at the mapping and localization algorithm that we will use in our robot, called SLAM (simultaneous localization and mapping), and its implementation using a 3D vision sensor, ROS, and image-processing libraries.
In this chapter, we will cover the following topics:
- List of robotic vision sensors and image libraries
- Introduction to OpenCV, OpenNI, and PCL
- The ROS-OpenCV interface
- Point cloud processing using the PCL-ROS interface
- Conversion of point cloud data to laser scan data
- Introduction to SLAM