Day: October 2, 2024

Creating Video Games With AI: A Mario Example

October 2, 2024 by 1 Comment

Artificial intelligence (AI) seems to be doing everything these days. Making images, making videos, and replacing most of us real human writers if you believe the hype. Maybe it’s all over! And yet, we persist, to write about yet another job taken over by AI: creating video games.

The research paper is entitled “Video Game Generation: A Practical Study using Mario.” The basic idea is whether a generative AI model can create an interactive video game by first training it on an existing game.

MarioVGG, as it is called, is a “text-to-video model.” It hasn’t built the Mario game that you’re familiar with, though. It takes player commands as text inputs—such as “run, or “jump”—and then outputs video frames showing the result in the ‘game.’ The model was trained on a dataset of frame-by-frame Super Mario Brothers game play, combined with data on user inputs at the time. The model shows an ability to generate believable video output for given player inputs, including basic game physics, item interactions, and collisions. It’s able to do this in a chained way, so that it can reasonably simulate a player making multiple actions and moving through a level of the game.

It’s not like playing a real Mario game yet, by any means. Regardless, the AI model has shown an ability to replicate the world of the game in a way that behaves relatively consistently with its established rules. If you’re in the field of video game development, though, you probably don’t have a lot to worry about just yet—you probably moved past making basic Mario clones years ago, so you’ve got quite an edge for now!

Easily Build This IMU Array Sandbox

October 2, 2024 by 6 Comments

These days we’re used to our devices containing an inertial measurement unit (IMU) that lets it know its position relative to the Earth. They’re mechanical devices at heart, and so they’re not infallible, with a few well-known failure modes — but we can try and help it. One way that’s getting some attention is to put many MEMS IMUs on a single PCB, connect it to an FPGA, then process their data all together to make for a more sensitive IMU or filter out drift. Want to join in? Here’s an open source implementation from [will127534].

With 32 individual ICM-42688-P SPI-connected IMUs and the beloved ICE40 chip at the center of the board, this PCB is a powerful platform to help you jump onto the new direction of the IMU research world. There’s example Verilog code that tests the board’s workings, and you can pair it with a Pi Pico running MicroPython to test out its raw capabilities. After that, the stage is yours.

The board is cheap to order online, easy to assemble yourself if you must, or have JLCPCB assemble it — just solder some capacitors on the backside afterwards. There’s a breakout, but it’s mostly for tests. This board is very much designed to be a module in a bigger system, [will] mentions that he’s building a geophone. Clever array-based hacks are en vogue, it would feel – here’s a LED array from [mitxela] that uses LEDs as sensors.