advertisement

DashR is an AI-powered virtual assistant that acts as a true assistant in both the physical and virtual sense. what does From making you a custom drink to helping you find the best travel deals, DashR can do it all. - DashARM Beverage Maker: DashARM is a module that can automatically prepare drinks using voice commands to control a robotic arm. Our use case shows how we can make a cup of coffee while we're on the way, so that a hot drink is ready when we arrive. All you have to do to place your order is tell Dasha what you want. Hi Dasha, can you make me a cup of mocha? This can be used to prepare other drinks and potentially foods as well. - DashaCAM The DashCAM module allows us to see who is at the door remotely, and also send them a message if requested. We use SMS to send an image of the person at the door, and this uses Avaya and Google Cloud Platform for the interaction. Not home to receive a package? Ask Dasha to give instructions to the delivery boy. Combining this with our IoT sensors, this subsystem can be used to make the registration process for access controlled buildings completely contactless and seamless. DashaFly This is a travel assistant that allows you to search for flights and get information about cheaper flights and also covid alerts and pandemic warnings; and also a list of interesting things to do in the destination. External functions are essentially containers we create for Google Places and Amadeus to achieve this. Watch the demo here DashaHVAC allows you to get information about temperature, humidity, noise levels, light levels, and other information collected by IoT sensors, as well as control these settings using the voice assistant. Human: It's too cold here. Dasha's assistant: I have increased the temperature from 24.1 to 26 How we build it hardware: - servomotors - potentiometers - cables - sensors -dht11 -BME280 - 18650 batteries - Arduino controller boards voice assistant: - dasha.ai (dsl) -dsl -nodejs - python - ngrok -mongodb - google cloud storage Challenges we encounter - form coherent sentences in such a short time - character limit on #sayText (in fact, we had to shorten DashaFly's custom itinerary list because of this) - Argument error when training intentions (thanks to the mentors for helping us solve this) **Intentions should not have spaces. Achievements we are proud of - multiple work subsystems - MVP in operation what we learned - dasha scripting language - Language models can be complex to train. What's next for DashR? - make DashR more robust by training it on a more complex model.

advertisement

advertisement