MIT Researchers Develop Smart Gloves That Identify Objects by Touch

MIT (Massachusetts Institute of Technology) researchers have compiled a massive dataset that enables an AI system to recognize objects through touch alone. The information gathering glove could then provide a foundation for aiding robots or be used to map out information of certain objects within the Virtual worlds.

The low-cost knitted glove, called “scalable tactile glove”, is equipped with 550 tiny sensors across the surface of each hand. These sensors acts as neural pathways for collecting data when humans interact with objects in various ways. As every object has its unique properties, the sensors can pick up pressure signals to “learn” and recognise patterns related to specific objects. The threads connect from the glove to an external circuit that translates the pressure data into “tactile maps,” which are brief videos of dots displaying various sizes depending on the intensity of the touch across a graphic of a hand. The bigger the dot the bigger the application of pressure is being applied on the surface of the glove.

Utilizing and perfecting the tactile sensing system can transform how we will soon interact in the virtual world. Having an advanced haptic feedback glove can add another layer of realism when interacting with different objects picking up its weight and unique properties that we experience in the real world.

Prosthetics manufacturers are also recognising the significance of the information gathering technology when it comes to choosing the optimal spots for placing pressure sensors and help customize prosthetics to the tasks and objects people regularly interact with.