Technology company Piccolo has launched its Vision Assistant product, which aims to support existing voice assistant technology with smart cameras that track the movements of people inside a home, enabling them to control smart devices with gestures.
The company’s founders, Marlon Misra and Neil Raina, have worked on machine learning and artificial intelligence at Udacity’s self-driving vehicle programme in 2016 and are looking to introduce those technologies into the home.
Cameras use a process known as skeletal tracking to monitor the movement of people within a room, and assess the positions of their bodies and arms, and movements of their arms and hands, to control smart devices around the home. A video on the company’s website demonstrates a figure holding an open hand towards a television to pause a video, and a snap of their fingers to play it.
The devices themselves will also have a degree of autonomy, using artificial intelligence to behave according to a set of preferences tailored to the inhabitants of the house, and act without requiring constant human input.
“Some devices, like lamps, will rarely be adjusted,” says the company on its website. “They will know to be on if you’re around, dim as it gets later, turn off if you take a nap on the sofa, and just slightly illuminate the room if you have to get something in the middle of the night.”
Piccolo is also aiming to work with, not against, existing smart technology companies. Its website makes reference to ‘voice-vision fusion’, and suggests that customers could point to an object and ask Alexa to ‘order five more of these’, rather than name it. Streaming service Netflix and espresso machines are also named as potential devices that could be controlled with gesture, rather than voice.
“Since no one company can make all the applications, and great ideas come from many places, there should be a platform that lets anyone make vision apps,” says the website. “But this is only possible if someone takes care of foundational computer vision technology, privacy controls, app deployment and other obstacles.
“Our ultimate goal is to become that platform that removes these obstacles and lets anyone create and deploy vision apps.”