I am building a robotic arm for pick and place application. The robot is going to recognize several objects using the RGB feed from Kinect (will use a model such as YOLOv2 for object detection, running at maybe 2-3 FPS) and find the corresponding depth map (from Kinect again) to be used with the kinematic models for the arm. The YOLOv2 network input size is 416x416 px.

I will be working on Ubuntu 16.04 with ROS Kinetic. I also plan to work on indoor mapping and autonomous navigation in the future.

Is the Kinect 360 sufficient to achieve this? Is it worth buying the newer Kinect for XBOX One and will the 1080p feed make a huge difference?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.