What is AI in the game?
Artificial intelligence is a program that allows certain characters in a video game, such as non-playable characters (NPCs) and enemies, to act in a way that makes them look like they are being manipulated by humans. control or act by the soul. their own.
AI is used to make games more engaging, but what does that mean in practice?
If you’ve ever played the classic game Pacman, you’ve experienced one of the most famous examples of early AI. As Pacman tries to collect all the dots on the screen, he is relentlessly pursued by four different colored ghosts. But they didn’t just follow him; when playing, they appear to be trying to ambush the player.
How did they do this?
The ghosts were programmed to know Pacman’s location, but each was configured to react to action a little differently. One of the ghosts is ready to roam, one is ready to aggressively follow Pacman, one is willing to go in the direction Pacman is going, one is willing to move randomly unless another ghost is trying. capture Pacman and the final ghost is set to follow Pacman when far away, but travel to a specific location on the map when close. These four behaviors make these ghosts, even in a 1980s game, seem like they have a will of their own. They feel alive. And that is the purpose of AI in video games.
Why is AI important?
Almost all games use AI to one degree or another. Without it, the game would hardly bring an immersive experience to the players. The goal of the AI is to immerse the player as much as possible, giving the game characters a realistic quality, even though the game itself is set in a fantasy world. As AI improves and matures, the options for interacting with the player’s experience also change. Let’s play a game like “Middle-earth: Shadow of War” and their Nemesis system. In this open-world adventure game from Monolith Productions, the orc enemies you encounter throughout the game have a variety of personalities, traits, and uses.
Any Orc you see in the game can join you, betray you, spy for you, and more. But that’s not all; The Nemesis system makes the most memorable gameplay moments even more memorable, because by defeating a tough orc leader you can create an enemy that will come to you in the future and score remember what you did to him in the past. The system tries to create a whole new way for players to interact with NPCs in the game.
When tough enemies that take you a long time to defeat come back at the worst possible time, the game gets a lot more intense. This experience is tailored to player actions and procedurally generated characters, so will be slightly different for each player. But all of this is more advanced, it still includes pre-programmed instructions by the developers.
As AI uses new technology, a similar game can not only have orcs that look like they are conspiring or befriending the player, but actually planning and having feelings for the game by the player.
How is artificial intelligence evolving in games?
Until now, AI in video games has been mainly limited to two areas, pathfinding and finite state machines. Pathfinder is a program that tells AI-controlled NPCs where they can and can’t go.
From classic 8-bit games to massive open-world RPGs, it’s still important. The developers don’t want the villagers in the town they’re working on to go through walls or get stuck in the ground. They also don’t want them to stand still.
On the other hand, finite state machines allow the AI to change its behavior based on certain conditions. A good example of this in practice are enemy soldiers in the Metal Gear Solid series.
When you get in their sights and are detected, it will trigger an alarm and all enemies in the area begin to focus on your location and attack.
You have to get out of their sight and hide long enough for the guards to give up their pursuit and return to their original position. They are basically two different states, the “Hunting” state and the “Patrol” state.
These may seem like rudimentary ideas, but these two concepts govern most AI programs today. In the SIMS series, when the AI is hungry, it will get food. When they are tired, they go to sleep.
This mimics real life decision making, but it’s actually the SIM’s state changing from “neutral” to “Go to nearest food source” and programming the orientation to tell them the source is near. where most. So how is AI evolving? This has changed a lot with the amount of pathfinding and status that developers can give NPCs. After all, there is a world of difference between Pacman and Skyrim.
But for now, the same AI technology used to create self-driving cars and facial recognition is set to change the AI world in games forever. Soon, pathfinding may not only tell the AI where it can go. The AI can create an entire realistic landscape from scratch, calculating which walls it can and cannot go through instantly.
What kind of storytelling would be possible in video games if we could give NPCs real emotions, with personalities, memories, dreams, ambitions, and intelligence indistinguishable. with humans.
Data scientists have wanted to create real emotions in AI for years, and with recent AI test results from Expressive Intelligence Studio, they’re getting closer. It won’t be long after their success, we will be able to see these AIs in the game.
In other words, the direction and state, the basic principle on which all AI is built, could soon be shaken.
Advantages and disadvantages of AI in video games? artificial intelligence video game
So, what are some of the pros and cons of the evolving state of AI and the new technologies coming out? Here are some pros and cons to think about as we enter a new era of gaming.
Artificial Intelligence: Benefits
As AI evolves, we can expect faster development cycles as AI can take on more and more of the burden. Procedurally generated worlds and characters will become increasingly advanced. You’ll no longer see random NPCs walking around with just one or two statuses, they’ll have a bunch of actions they can take to make the game more engaging.
Also, interestingly, if NPCs had actual emotions, it would fundamentally change the way players could interact with them.
You can learn to really care about the citizens of the town you’re protecting, or hate the nasty enemies that are always one step ahead of you until you finally defeat them. The ever-evolving artificial intelligence presents many opportunities, but also some problems.
Artificial Intelligence: Cons
As AI becomes more advanced, game makers will have less control over it. That means we might miss out on some of the carefully crafted worlds and levels we’ve come to expect, in favor of something that could have been easier but… more robotic.
This could be a similar situation to how players can often tell when a game has been created using archive assets from Unity. It affects the overall experience.
It also means we can get more complex games when the AI programming goes wrong. In Aliens: Colonial Marines, for example, enemy AI acted in strange and peculiar ways, destroying immersion. If AI is essentially self-programmed, will we eliminate this problem altogether or make it more achievable? Hard to say.
Ultimately, the fact that AI can handle more game programming on its own could affect the jobs of many game creators currently working in the industry.
These are all things worth considering as we head into uncharted waters.
Using AI in game development
Over the next few years, we could start to see AI play an increasingly important role, not just in the game itself, when it comes to game development. Recent experiments with deep learning technology have allowed the AI to remember a series of images or text and use what it learns to mimic the experience.
AI is currently being used to create Picasso-like works of art or emails that look like they were written by a human. This same technology is currently being adapted for game development, where in an experiment, the AI can program a playable level of the game using just pictures.
As this technology becomes more reliable, large open world games can easily be created by AI and then edited by developers and designers, speeding up the development process. .
But that’s not all, there is also the advent of facial recognition software and deep spoofing technology that seems to play an important role in future development cycles. Deep Fake technology allows the AI to recognize and use different faces it has scanned.
Although still in its infancy, impressively realistic 3D models have been created using faces that this type of AI can scan. Now imagine if this same technology were used to create a building or a landscape. This will save a lot of developer time.
Thinking more broadly, it’s entirely possible that AI will soon use a combination of these technologies to create entire games from scratch without the need for a developer. They can even create these games from scratch using player habits and tastes as a guide, creating unique personal experiences for players.
It’s hard to say if it’ll get this far anytime soon, but it wouldn’t be surprising if we start to see AI play a bigger role in game development over the next few years.
The future of artificial intelligence in games
While AI technology is constantly being tested and improved, this is largely done by software engineers and robotics, rather than game developers. The reason is that using AI in unprecedented ways for games is a risk.
Right now, developers control the world they create. Leaving their games in the hands of super advanced intelligent AI can lead to glitches, bugs, or unexpected behavior.
If the AI character’s ability to react to the player is endless depending on how the player interacts with the world, it means that the developers can’t test every conceivable action. AI can do it.
While the technology and the prospects it offers are exciting, the major studios are getting off to a slow start. So how long before they do?
It’s inevitable, but hard to say. At some point, technology may be understood well enough that a studio is willing to take that risk. But more than likely, we’ll see aspiring indie developers make their first push within the next two years as the ball rolls.
Given how fast technology advances, it’s possible that we’ll have everything we’ve ever dreamed of with AI by the end of this decade.
Will AI make games too difficult? There’s an old adage that still stands; Be careful what you wish for. It’s entirely possible that as we start to implement more advanced AI in our games, we’ll run into some issues.
For example, if the enemy AI knows how the player works to the point where it can always win against him, that would ruin the fun of the game.