IBM Open Sources DIY Cardboard Robot: TJ Bot

IBM has open-sourced a DIY cardboard robot: TJ Bot, inviting bot enthusiasts around the world to create their own personalized bots.

Project address: https://github.com/ibmtjbot/tjbot

TJ Bot continues the spirit of the maker community; it is a DIY toolkit that allows you to build a programmable cardboard robot powered by Watson. The robot consists of a cut piece of cardboard (which can be 3D printed or laser cut), a Raspberry Pi, and various plugins (including an RGB LED light, a microphone, a servo motor, and a camera). At the same time, TJ Bot is an open-source project, and we can find relevant guides on Instructables.com and GitHub. IBM’s team has provided three starter guides for TJ Bot, but they hope everyone can contribute their own DIY robot assembly guides.

Here are the existing processes for making TJ Bot:

• Make TJ Bot respond to emotions. The RGB LED light on TJ Bot’s head changes color based on the public sentiment of a given topic on Twitter. It connects to the Twitter API (https://dev.twitter.com/overview/api), can automatically fetch tweets, and can identify overall sentiment by running the Watson Tone Analyzer (http://www.ibm.com/watson/developercloud/tone-analyzer.html). For example, you can program TJ Bot to track public sentiment about the Emmy Awards in real-time. Tutorial address: http://www.instructables.com/id/Make-Your-Robot-Respond-to-Emotions-Using-Watson/

• Control TJ Bot with your voice. You can give basic commands to TJ Bot using your voice. For example, you can ask TJ Bot to “change the light to yellow,” and it will adjust its lighting accordingly. TJ Bot uses the Watson Speech To Text API to transcribe, analyze, and understand what you say.

  Tutorial address: http://www.instructables.com/id/Use-Your-Voice-to-Control-a-Light-With-Watson/

• Chat with TJ Bot. Create a “chat” bot using three Watson APIs in just three steps. The Watson Speech To Text API (http://www.ibm.com/watson/developercloud/speech-to-text.html) converts your voice into text, then Watson Conversation (https://www.ibm.com/watson/developercloud/conversation.html) processes the text and calculates a response, after which Watson Text To Speech converts the text back into audio, allowing TJ Bot to respond. You can chat with TJ Bot about anything from the weather to your favorite TV shows, depending on how you program your Raspberry Pi. Tutorial address: http://www.instructables.com/id/Build-a-Talking-Robot-With-Watson-and-Raspberry-Pi/

TJ Bot is an example of embodied cognition, which involves embedding artificial intelligence into tangible objects in your daily life. In this case, we place Watson technology into a cut piece of cardboard, imagining that your home’s walls, your furniture, or various objects in your home could possess these capabilities.

One key to creating cognitive embodiment is understanding how humans interact with objects. Interacting with these objects, such as with TJ Bot, is much more natural than interacting with existing computing devices: you don’t need to type on a keyboard; you can simply command it with your voice.

Whether you want to write code with a “big idea” or complete an academic project, you can participate in the TJ Bot open-source project.

© This article is a translation by Machine Heart, please contact this public account for authorization.

✄————————————————

Join Machine Heart (Full-time reporter/intern): hr@almosthuman.cn

Submissions or reporting inquiries: editor@almosthuman.cn

Advertising & business cooperation: bd@almosthuman.cn