In the future, security robots will be able to open doors all by themselves to keep an eye on all kinds of threats. The Reebotic AI Robot is capable of doing that by using a deep learning based object detection algorithm. As the developers explain:

To accomplish tasks such as door opening, Reebotic’s engineers first collect thousands of photos and mark out the door knobs. Then, these photos are loaded into a Nvidia GPU server to train the deep learning model. After the training, when fed with a new image, the model is able to detect the door knob and mark out its pixel location in the image. Finally, this deep learning model is downloaded into Reebotic’s AI robot for the door opening task.

A camera is mounted to the robot’s arm gripper and the video is fed to the deep learning framework. The robot will be able to detect the door knob and uses the information collected to guide the arm to target it.

[HT]