IBM is a community of makers, creators and thinkers. By nature we’re a curious group of people – always asking questions about what’s next, and within my team, what else is possible with artificial intelligence. We love teaming up with others who are passionate about the possibilities of technology, whether it be inspiring a new hit song, creating the scariest movie trailer, or helping businesses make better decisions.
The idea of joining forces with other makers, creators and thinkers to explore the potential of Watson, in a fun and easy way, was the catalyst behind a new project our team is launching: TJBot.
In the spirit of the maker community, TJBot is a DIY kit that allows you to build your own programmable cardboard robot powered by Watson. It consists of a cardboard cutout (which can be 3D printed or laser cut), Raspberry Pi and a variety of add-ons – including a RGB LED light, a microphone, a servo motor, and a camera. Most excitingly – TJBot is an open-source project with instructions available on Instructables.com and GitHub. While the team at IBM has provided three starter-sets of instructions (recipes) for bringing TJBot to life, we’re asking all of you to contribute your own instructions to inspire your fellow makers.
Today, we’ve created recipes to:
Make TJBot respond to emotions. The RGB LED on TJBot’s head will change color based on the public sentiment of a given topic on Twitter. It connects to the Twitter API to fetch the tweets and runs Watson Tone Analyzer to identify the overall sentiment. For example, you could program TJBot to track the real-time social sentiment of a major awards show, like the #Emmys.
Use your voice to control TJBot. Using your voice, you could give TJBot basic commands. For example, you could ask TJBot to “turn the light yellow”, and it will change the color of its light. TJBot uses the Watson Speech to Text API to transcribe, analyze and understand what you are saying.
Chat with TJBot. Using three Watson APIs, this recipe creates a “talking” bot. In a three step process, Watson Speech to Text API will convert your voice to text, Watson Conversation will process the text and calculate a response, and Watson Text to Speech will then revert the text to audio, allowing TJBot to respond. Based on how you program your Rasberry Pi, you can talk to TJBot about anything from the weather to your favorite TV show.
TJBot is an example of ‘embodied cognition’ – the idea of embedding artificial intelligence into objects in our everyday lives. While in this case we’re putting Watson technologies into a cardboard cutout, imagine these types of capabilities in your walls, in your furniture or in objects in your home.
One of the key facets of creating cognitive objects is understanding the way in which humans will, and want to, interact with them. Interactions with these objects – like TJBot – can be more natural than with existing computing devices; instead of typing on a keyboard, you use voice commands.
Whether you spend your days coding the next “big idea”, or simply playing with code for your school project, we invite you and the global community of makers to meet TJBot and join us in building the future of AI. We look forward to seeing the videos, blogs, recipes and photos published by the Maker community to see what, and how, you create your own cognitive objects.
Want to get your own TJBot? Visit our GitHub page for more information. Be sure to use #TJBot when sharing your creations on social media!
IBM Research has initiated focused efforts called Code Risk Analyzer to bring security and compliance analytics to DevSecOps. Code Risk Analyzer is a new feature of IBM Cloud Continuous Delivery, a cloud service that helps provision toolchains, automate builds and tests, and control quality with analytics.
In 2019, IBM and the Broad Institute of MIT and Harvard started a multi-year collaborative research program to develop powerful predictive models that can potentially enable clinicians to identify patients at serious risk for cardiovascular disease (1, 2). At the start of our collaboration, we proposed an approach to develop AI-based models that combine and […]
Fifty years ago this month, IBM researcher and computing pioneer Edgar Frank Codd published the seminal paper “A Relational Model of Data for Large Shared Data Banks,” which became the foundation of Structured Query Language (SQL), a language originally built to manage structured data with relational properties. Today SQL is one of the world’s most […]