Connect with us

Artificial Intelligence

Muscle-Control System of Gestures for Navigation



MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) has introduced Muscle-Control system that lets pilots use gestures for accurate and specific navigation. They recently released a video of their ongoing work. In this video, they are using input from muscle signals to control devices. This latest video involves a full and excellent control of drones, using just a hand and arm gestures to navigate through a series of rings. This work is so impressive that not only they’re using biofeedback to control the devices, but there are also other kinds of gesture instead of optical signals. Moreover, these specific controls set up a wide range of potential applications for this kind of remote tech. This particular group of researchers is also looking at various applications for this control-system. They are including its use in collaborative robotics for potential industrial applications.

How this System Works

Electromyography electrodes and motion sensors of the system are worn on the biceps, triceps, and forearms. The algorithms process signals from the sensor to detect gestures. The muscle-control system doesn’t require offline calibration or training data for each new user. It identified 81.6% of gestures when it was tested. The system can be extended to other robot applications to make human-robot interaction easier.

Benefits of MIT Muscle-Control System

Drone piloting has significant benefits in terms of real-world use. They provide a view that can be seen via VR, especially when you imagine flocks taking flight with a pilot. That muscle-control could help in a significant way. For example, you can do a site survey for construction or a remote equipment inspection of offshore platforms and other infrastructure that’s hard for people to reach. Seamless, this robotic/human interaction is the ultimate goal of the team working on this tech. As we appreciate our movements and ability to manipulate our environment most effectively. So, the process of working and controlling with robots should be as smooth.

Thinking and doing mostly happen in parallel when we interact with our environment. Still, there’s often the requirement of lots of training when we act through the extension of machines or remote tools.

The industry that focuses on building robots can safely work alongside robots. Close collaboration with robots benefits significantly from advances that make the interaction between people and robotic equipment more natural, intuitive and, safe. MIT’s research could help in future industrial robotics products that require less training and programming to operate at scale.



Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *



Pin It on Pinterest

Share This