If you follow this site you know that I LOVE to combine my passion for hobbies with my passion for technologies. While I am watching my favorite sporting events with my boys, it isn’t uncommon for me to browse the internet for ideas for new fun things to do.
The family got a 3d printer for Christmas, so over the holidays I spent some time learning how to use the tool. While researching fun things to make, I came across this project. This project is for a T800 Terminator robot that has head movement and face tracking. While that may sound cool, my mind was already racing with how I could make this my own.
Here are some of the things that I already have working or are on the path to have working.
- Voice! This includes having a variety of voice options that come with premium models, but my ultimate goal is to have it sound like Megatron.
- Voice comprehension. Again, premium sub is required (trying to do this with Ollama was…. yeah).
- Thinking. Ok, that is pretty vague. What good is this if you can’t have a conversation with it? The bot has to be able to not only have conversations, but it has to remember the conversation so it has context. This is a core concept in AI, of course.
- Facial recognition. The project came with a generic python library that does face tracking, but that is NOT the same as recognition.
- Personal profile. If you’re going to do everything that I have already listed, you need a way to bring it all together. Having a profile also allows me to tailor a conversation to the person. For example, I can indicate that the person is a child, neighbor, good friend, etc.
- Modes. Some of the ideas that I am working on:
-
- 1. Taunt mode. Back in the day I did a little comedy, and I am still a fan to this day. My thought here is making an “insult bot”. I have played around with mixing AI and comedy – I don’t know that anyone has really played with this idea. Side note: this is where the profiles will come in handy. As a comic, you have to know your audience.
- 2. God of War mode. I actually have this piece mostly working. Here is the scene: the bot is sitting in my backyard bar, and that bar has speakers, alexa, and hue lights. If someone asks the bot if it is the god of war, I want it to have the mother of maniacal laughs. The lights in the bar start to flash and change colors. A smoke machine (a smoke machine!) hidden underneath the bot starts to generate colored smoke. While the bot has its own voice capability, in this mode he will say “I AM the god of war” over the bar’s speakers via Alexa. I was surprised that this was as difficult is it was. I ended up making voice files with a service, sending it to S3 storage, and then sending the URL to alexa by way of Home Assistant (essentially backdooring Alexa’s limitations for personal users).
I’ll continue to update the project as I go along. In the carousel below, you can see the printer (and parts of the skull) along with the raspberry pi (along with a pile of wires, speaker, mic, “eyes”, servos, etc).
If you’re interested in taking on this project, I created a spreadsheet that contains all of the materials that I bought for this project (sorry, I am an architect at heart). I also have a half-finished wiring diagram – I am still finalizing the parts before I put them into the bot. I also created a NotebookLM workspace with all of the project artifacts – I may make that public in the future. You will also see the mini web app that I wrote to create and test all of the voice (and comedy!) functionality.
Here is the current workflow (subject to change once I interact with it more)
This is the utility app that I made to manage profiles and test the various services. It is definitely easier to pilot this here rather than trying to do it in the bot:
