Like in humans, robots need to see, hear, speak, and express themselves as naturally as a humans can. For that, the right hardware design, sensors and movement is critical. Furhat is a robot head and a torso, designed in human form-factor. With advanced sensors such as wide field-of-view cameras, microphone arrays, stereo speakers, and anatomically-correct neck, and much more, the robot is optimized to interact with humans.
Creating a human face in a robot is the holy-grail of robotics. One of Furhat’s very unique features is its simple and powerful face design. The projector inside the Furhat head projects an animation onto a mask to create a face that feels alive. This combination of hardware and software give the robot the flexibility of a digital animated face with the impact of having a physical presence. The result is an incrdibly expressive and customizable face that looks and moves like a Pixar character, but in a robot.
The combination of facial animation and replaceable masks make it very easy to create expressive characters with any design. Furhat today comes with a generic adult mask and 22 animated faces that can be customized into further characters. Child and "Anime" masks are available, and additional customized faces and masks can be created on-demand.
Furhat has built in automatic behaviours such as blinking, micro movements, and facial, eye and neck expressions. When anyone develops an application for robots, we want them to focus on training the robot on new knowledge, while our AI system takes care of everything else.
Furhat is integrated with most leading speech recognition systems. We currently support more than 40 languages, in most countries around the world. We have perfected the speed and fluency of the robot, creating a predictive response time that is as fast as a human conversation.
Furhat comes integrated with more than 700 voices with varying regional dialects, and is integrated with the leading commercial Text-to-Speech systems in the world. You can choose the voice that best suits your Furhat character, whether it’s young or old, male or female, or fictional.
We've also just announced our collaboration with ElevenLabs, allowing the user to create a copy of a real voice, in minutes, and make it available in their robots.
Furhat can interact with up to 10 people simultaneously and has the ability to remember them during the course of an interaction. We develop state-of-the-art computer vision systems to track users in real-time, perform facial expression analysis, estimate head pose and user distance, giving the robot deeper knowledge of its surroundings in real-time.
The robot comes with a microphone array with noise cancelation and direction of arrival. You can also plug in any microphone for optimizing the robot for a specific environment. Powerful and high-end stereo speakers also allow the robot to be heard in noisy environments.
