Challenge
The products that we use in day-to-day lives serve singular purpose especially the ones who do not have the capability to learn from us and evolve. The brief revolved around building a small intelligent product and to rethink from scratch what are the interactions and roles of devices that are ‘trained’ and not only ‘used’.

Outcome
A humble switch which explores voice interaction model in the future intelligent home. Using supervised learning, one can train the switch and could be used for any appliance. Being decentralised, it cannot pass any data which usually a cause of concern with any AI driven technology.

Tags
#machinelearning
#tangibleuserinterface
#supervisedlearning
#voiceinteraction
#homedevice
#switch

Plug+

Plug+

The Context

The Context

While products have been designed and manufactured to serve a predefined use, logic, and behaviour, with advances in emerging technologies such as machine learning, increasingly objects are acquiring the capability of learning, context-awareness, and evolving affordances. This paradigm shift brings new models of interactions between people and objects. New complexities inside objects also bring challenges for designers to translate and bridge the gap in understanding these interactions.

While products have been designed and manufactured to serve a predefined use, logic, and behaviour, with advances in emerging technologies such as machine learning, increasingly objects are acquiring the capability of learning, context-awareness, and evolving affordances. This paradigm shift brings new models of interactions between people and objects. New complexities inside objects also bring challenges for designers to translate and bridge the gap in understanding these interactions.

How can we create new metaphors of interaction with intelligent objects?
What language should we use to communicate objects’ learning process?
What new values can the kind of trainable intelligence bring to us?

How can we create new metaphors of interaction with intelligent objects?
––
What language should we use to communicate objects’ learning process?
––
What new values can the kind of trainable intelligence bring to us?

8.1
6.1
7.1

The Process

Using supervised learning, one can train the switch which has a microphone, relay, maker 1000. This switch can be trained for any appliance at home which runs at 220V. The prototype consists of two-part, a switch box that allows you to connect any of your appliances, and a detachable training module that you can place anywhere in your home and train it with your unique voice command.

IxD-02

We designed a simple training interface, using led and the change of light, different modes such as training and using modes, can be indicated, and more importantly, it provides direct and understandable feedback to demonstrate the training progress.

feel know do

Team: Reuben D'Silva and Yuxi Liu
Instructors: Massimo Banzi and Simone Rebaudengo
Duration: 2 weeks

More Projects

SimpleHealthcare

NidraTangible Interactions

Video FacilitatorWeb conference tool

ZonderHealthcare

Y'eauCommunity Water Purification

RedeemerEmergency Services

PlanniWeather App

LokalTreatsImmigration Crisis

XR BowlingMixed Reality

AiroRadio