Physical Aimbot Shoots For Success In Valorant

Modern competitive games have a great deal of anti-cheat software working to make sure you can’t hack the games to get a competitive advantage. [Kamal Carter] decided to work around this by building a physical aimbot for popular FPS Valorant.

The concept is straightforward enough. [Kamal] decided to hardmount an optical mouse to a frame, while moving a mousepad around beneath it with an off-the-shelf Cartesian CNC platform, but modified to be driven by DC motors for quick response. This gave him direct control over the cursor position which is largely undistinguishable from a human being moving the mouse. Clicking the mouse is achieved with a relay. As for detecting enemies and aiming at them, [Kamal] used an object detection system called YOLO. He manually trained the classifier to detect typical Valorant enemies and determine their position on the screen. The motors are then driven to guide the aim point towards the enemy, and the fire command is then given.

The system has some limitations—it’s really only capable of completing the shooting range challenges in Valorant. The vision model isn’t trained on the full range of player characters in Valorant, and it would prove difficult to use such a system in a competitive match. Still, it’s a neat way to demonstrate how games can be roboticized and beaten outside of just the software realm. Video after the break. Continue reading “Physical Aimbot Shoots For Success In Valorant”

Teaching A Machine To Be Worse At A Video Game Than You Are

Is it really cheating if the aimbot you’ve built plays the game worse than you do?

We vote no, and while we take a dim view on cheating in general, there are still some interesting hacks in this AI-powered bot for Valorant. This is a first-person shooter, team-based game that has a lot of action and a Counter-Strike vibe. As [River] points out, most cheat-bots have direct access to the memory of the computer which is playing the game, which gives it an unfair advantage over human players, who have to visually process the game field and make their moves in meatspace. To make the Valorant-bot more of a challenge, he decided to feed video of the game from one computer to another over an HDMI-to-USB capture device.

The second machine has a YOLOv5 model which was trained against two hours of gameplay, enough to identify friend from foe — most of the time. Navigation around the map was done by analyzing the game’s on-screen minimap with OpenCV and doing some rudimentary path-finding. Actually controlling the player on the game machine was particularly hacky; rather than rely on an API to send keyboard sequences, [River] used a wireless mouse dongle on the game machine and a USB transmitter on the second machine.

The results are — iffy, to say the least. The system tends to get the player stuck in corners, and doesn’t recognize enemies that pop up at close range. The former is a function of the low-res minimap, while the latter has to do with the training data set — most human players engage enemies at distance, so there’s a dearth of “bad breath range” encounters to train to. Still, we’re impressed that it’s possible to train a machine to play a complex FPS game at all, let alone this well.